High-throughput acquisition of crop phenotypic information is one of the key technologies for achieving intelligent facility agriculture and precision breeding. Traditional phenotypic data collection methods suffer from low efficiency and strong subjectivity, making it difficult to achieve multi-scale continuous monitoring and meet the demands of modern research and production. This paper systematically reviews the technological framework and development trajectory of optical sensing technology-driven phenotypic platforms for facility crops. First, starting from optical sensing technologies, a comparative analysis highlights the advantages and limitations of RGB, multi-/hyperspectral, thermal infrared, and LiDAR sensors in phenotypic perception. Second, the characteristics and applicable scenarios of stationary, rail-mounted, mobile robot, and unmanned aerial vehicle (UAV) platform architectures are summarized. Furthermore, the evolution of phenotypic data processing methods is examined, focusing on the shift from traditional feature engineering to deep learning-driven approaches. Finally, key challenges such as multimodal data fusion, system cost, and real-time performance are discussed, along with the future direction of phenotypic platforms toward intelligent closed-loop decision-making systems. This article systematically reviews the facility agriculture phenotyping platforms driven by optical sensing technology, and also incorporates representative research progress in field phenotyping studies. These advances provide transferable sensing technologies, methodological frameworks, and platform design concepts that can facilitate the development of phenotyping platforms for controlled-environment agriculture.
Why it matches plant phenotyping methods施設作物の光学センシング型ハイスループット表現型解析プラットフォームを体系的にレビューしており、センサー、プラットフォーム構成、データ処理を中心に扱うため、方法論レビューとして明確に適格です。
abstractThis paper systematically reviews the technological framework and development trajectory of optical sensing technology-driven phenotypic platforms for facility crops.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 14 Sept 2026
Plant Phenomics studies the phenotypic dynamics that form plant phenotypes by systematically measuring traits using phenotyping methods from the quantum to the ecosystem levels. It has emerged as an interdisciplinary field advancing sensing, computation, and plant biology. However, Plant Phenomics has lacked a unifying framework that integrates its community's core concepts from the formal and life sciences. Central to this framework is the definition of the phenome as a set of phenes that govern phenotypic dynamics across all spatial and temporal scales of biological and ecological organization and in interaction with the environment. This paradigm moves beyond gene-centric views and recognizes the equal importance of all spatial and temporal scales in forming plant phenotypes, advancing Plant Phenomics as a data-driven discipline and its emerging profession, the plant phenomicist.
Why it matches plant phenotyping methods植物フェノミクスの概念・枠組みを扱うレビューであり、植物形質の系統的測定とフェノタイピング手法を主題としているため、方法論レビューとして適格。
abstractPlant Phenomics studies the phenotypic dynamics that form plant phenotypes by systematically measuring traits using phenotyping methods from the quantum to the ecosystem levels.
Plant counting functions as a central role in the quantification system of plant phenotyping. Over the years, the field has evolved through successive technological paradigms, and its modern form has been strongly influenced by advances in visual counting from computer vision. In this review, we synthesize the historical origins of plant counting, assess its current fragmented landscape, and outline a roadmap toward standardized, universal plant counting systems. We propose a coherent conceptual framework— the four-level hierarchy of plant counting , which characterizes the environment, platform, sensor, and counting entity in biological organization —grounded in the need of high-throughput plant phenotyping. This framework aims to guide the development of plant counting systems that are not only accurate on individual dataset, but also reusable, comparable, and trustworthy across modern plant phenotyping scenarios. We argue that existing plant counting approaches are constrained by species-specific designs, sensor-dependent assumptions, and local, region-bound assessments. We hope this review can serve as a reference for building cross-species, cross-modal, and cross-scale visual plant counting systems.
Why it matches plant phenotyping methods植物フェノタイピングにおける画像ベースの植物個体数計測を主題とし、手法の歴史、現状評価、標準化・汎用化の枠組みと開発指針を扱うレビューであるため。
abstractPlant counting functions as a central role in the quantification system of plant phenotyping.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 14 Sept 2026
Structural failure of cereal stems during late-season climate extremes is a critical determinant of yield stability. In barley, breakage of the stem below the spike, known as head loss, leads to major yield losses, particularly in hot and dry regions where the crop is widely grown. Despite a predicted increase in head loss risk due to global warming, current understanding of the genetic, physiological, anatomical, and environmental factors that control head loss remains limited. Overcoming these knowledge gaps is essential to providing a systems-level strategy for barley breeders to develop climate-ready cultivars that are resilient to stem breakage and suitable for industry adoption. Here, we review present knowledge and highlight opportunities for innovation to mitigate head loss through interdisciplinary approaches that combine precise phenotyping through mechanical testing of stem strength and flexibility, high-throughput phenotyping through drone-based spike counting, and genetic modification strategies informed by studies on hormonal regulation and cell wall composition. Coupled with genotypic data, these efforts will enable the development of a genomic selection platform to facilitate future breeding programs. The framework and tools discussed here are broadly applicable to improving stem resilience in other cereal crops.
Why it matches plant phenotyping methods茎の強度・柔軟性や穂数を対象とする表現型計測手法をレビューし、機械試験とドローンによる高スループット計測を育種基盤として論じているため、表現型手法が中心的です。
abstractHere, we review present knowledge and highlight opportunities for innovation to mitigate head loss through interdisciplinary approaches that combine precise phenotyping through mechanical testing of stem strength and flexibility, high-throughput phenotyping through drone-based spike counting
Herbarium specimens are physical, verifiable records that form the basis of taxonomic knowledge and biodiversity research. Their large-scale digitization has produced extensive collections of high-resolution images and associated specimen metadata, creating conditions in which artificial intelligence (AI) can play an important role in plant taxonomy, collection management, and ecological research. Early AI applications have primarily focused on automated species identification based on individual specimen images. Although increasingly accurate, such approaches remain limited by their emphasis on single-specimen label prediction and by treating identification outputs as final analytical decisions. Recent methodological advances-including segmentation-based preprocessing, automated trait extraction, structured extraction of label data, detection of potentially misidentified specimens, and multimodal integration of visual, textual, and genetic information-extend AI applications beyond species identification toward broader analytical frameworks, encompassing taxonomic interpretation as well as ecological and biodiversity research. In these approaches, specimens are placed within a shared analytical space, and identification results are used to support comparisons across multiple specimens rather than being treated as final decisions for single individuals. This multi-specimen perspective enables quantitative examination of species boundaries, morphological variation, data inconsistencies, and taxonomic stability within curated collections. In this context, AI serves not as an ultimate decision-maker but as a decision-support tool embedded in expert-guided workflows and biodiversity knowledge infrastructures. These developments can be summarized as Integrative Taxonomic AI, an approach that employs learned morphospaces to interpret and refine taxonomic categories by integrating multimodal evidence and curated specimen data under expert guidance.
Why it matches plant phenotyping methods植物標本画像から形態形質を抽出するAI手法と統合的解析枠組みを中心に扱うレビューであり、植物表現型取得・抽出法との関連が明確。
abstractRecent methodological advances-including segmentation-based preprocessing, automated trait extraction, structured extraction of label data, detection of potentially misidentified specimens, and multimodal integration of visual, textual, and genetic information-extend AI applications beyond species identification
The rapid detection and continuous monitoring of crop health and disease outbreaks are critical components of modern precision agriculture, essential for maintaining global food security. Traditional field-based scouting methods, while accurate, are often labor-intensive, time-consuming, and limited by spatial coverage, making them inadequate for large-scale agricultural operations. Remote sensing (RS) technologies—spanning satellite imagery, drone-based aerial platforms, and proximal sensors—offer a powerful, non-destructive, and scalable alternative for capturing high-resolution spectral and temporal data. This paper provides a comprehensive evaluation of current remote sensing applications in crop health monitoring and disease surveillance. We analyze how vegetation indices derived from multispectral and hyperspectral data, such as NDVI and red-edge parameters, serve as sensitive indicators of physiological stress and pathogen infection, often manifesting before visible symptoms appear. Furthermore, we explore the integration of machine learning and artificial intelligence algorithms in automating disease identification and severity mapping. By synthesizing recent advancements in sensor technology and data analytics, this paper demonstrates that remote sensing is indispensable for proactive, site-specific management. The findings emphasize that a multi-scale RS approach—integrating broad-scale satellite monitoring with high-resolution drone sorties—enables farmers to optimize input efficiency, minimize yield losses, and enhance the overall resilience of agro-ecosystems against biotic and abiotic stressors.
Why it matches plant phenotyping methods作物の健康・病害を対象に、リモートセンシング、センサー、植生指数、機械学習による状態・重症度推定を包括的に評価するレビューであり、フェノタイピング手法が中心です。
abstractThis paper provides a comprehensive evaluation of current remote sensing applications in crop health monitoring and disease surveillance.
Plant disease and plant stress early warning systems have advanced through deep learning, remote sensing, digital phenotyping, disease forecasting, and sensor networks. Detection accuracy, precision, recall, F1-score, and area under the curve remain indispensable, but they are insufficient for judging whether a warning can support timely and proportionate phytoprotection under field variability. This Mini Review argues that intelligent plant health warning systems should be evaluated not only as prediction models, but also as safety-relevant decision-support systems embedded in biological, agronomic, and operational contexts. We first relate AI-based detection to established plant disease forecasting and decision-support traditions, including weather-based models, epidemiological forecasting, and integrated disease management. We then adapt selected safety-assurance concepts, including risk assessment, failure mode and effects analysis, Bow-tie reasoning, warning-threshold governance, reliability analysis, resilience thinking, and response closure, to host-pathogen-environment warning chains. The proposed framework links AI or sensor outputs with pathogen biology, host susceptibility, environmental conduciveness, inoculum pressure, uncertainty assessment, risk classification, threshold decisions, human or automated verification, intervention, and feedback learning. Illustrative crop-pathogen scenarios, including wheat rust, rice blast, potato late blight, grapevine downy mildew, and citrus greening, show how safety assurance can complement existing forecasting and decision-support systems rather than replace them. The framework remains conceptual, and whether these added assurance functions improve existing warning systems requires comparative evaluation under field conditions. Future systems should be evaluated through detection performance and response-oriented indicators such as lead time, calibration, false-alert burden, missed-warning rate, response completion, disease suppression, economic value, and learning after field action.
Why it matches plant phenotyping methods植物病害・ストレスの検出を含む知的警戒システムについて、AI・リモートセンシング・デジタルフェノタイピング・センサーネットワークの評価枠組みを体系的に論じる方法論レビューであり、方法論が中心です。
abstractPlant disease and plant stress early warning systems have advanced through deep learning, remote sensing, digital phenotyping, disease forecasting, and sensor networks.
Abstract Disease management aims to protect crop yield and quality and reduce economic losses caused by plant pathogens. Consequently, reducing disease is a central objective of applied plant pathology. However, what constitutes effective disease control, and how it is measured and analyzed, varies substantially among studies. We conducted a systematic methodological review to characterize how plant disease control has been evaluated in the plant pathology literature over the past 15 years. We searched selected plant pathology journals for articles containing "control" in their titles and used an artificial intelligence-assisted workflow, followed by human verification, to extract and standardize information on experimental settings, disease measurements, measurement scales, and statistical analyses. The final dataset comprised 340 articles representing diverse host-pathogen systems and experimental environments. Disease control was evaluated using a wide range of response variables, most commonly disease severity and incidence, with substantial heterogeneity in measurement scales and sampling practices. Despite this diversity, statistical analysis was remarkably uniform: 79.4% of articles relied exclusively on ANOVA-based approaches. Among studies using ordinal disease scales, 73.3% included ANOVA in the analysis, whereas only 10.6% explicitly reported data transformation. Mean-separation procedures were also common, particularly Tukey, Fisher's LSD, and Duncan's multiple range test; Duncan's test was reported in 20.3% of all articles and varied markedly among journals. Our findings reveal a marked contrast between diversity in how plant disease control is measured and the narrower range of methods used to analyze those measurements. Greater alignment among biological meaning, measurement properties, experimental design, and statistical analysis could improve transparency, comparability, and interpretation in disease-management research.
Why it matches plant phenotyping methods植物病害の重症度・発生率など、植物の病害状態をどのように測定・解析するかを体系的にレビューしており、測定尺度、サンプリング、統計手法の標準化が中心的な方法論的貢献である。
abstractWe conducted a systematic methodological review to characterize how plant disease control has been evaluated in the plant pathology literature over the past 15 years.
Plant diseases destroy 20–40% of global food production annually, posing a critical threat to food security for a projected population of 9.7 billion by 2050. Conventional diagnostic approaches relying on expert visual assessment are slow, costly, and unsuitable for modern agricultural scales. While deep convolutional neural networks demonstrated early promise, single-modality, image-centric systems consistently fail under real-world field conditions characterized by variable lighting, co-occurring infections, and cultivar diversity. This review synthesizes a decade of progress across four interconnected frontiers: the evolution of deep learning architectures for plant disease detection; the adaptation of foundation models including CLIP, SAM, and DINOv2 to agricultural contexts; the development of multimodal fusion frameworks integrating imagery, environmental, genomic, and hyperspectral data; and the transition from static disease diagnosis to descriptive comparison of reported metrics, which suggested that multimodal approaches frequently reported improved diagnostic performance relative to corresponding single-modality baselines, although direct cross-study comparison was limited by methodological heterogeneity. A systematic review following PRISMA guidelines identifies eligible comparative studies. Descriptive comparison of reported performance metrics across these studies indicated that multimodal approaches generally achieved higher accuracy and sensitivity than single-modality models, particularly for pre-symptomatic disease detection. Eight critical research gaps are identified, including the absence of a unified agricultural foundation model and limited climate-aware forecasting under non-stationary climate projections. A structured research agenda is proposed to accelerate translation from laboratory performance to globally equitable, field-deployable crop protection systems.
Why it matches plant phenotyping methods植物病害の画像ベース検出・予測手法を対象とする系統的レビューであり、植物の病徴・病害状態を観測から推定するフェノタイピング手法のレビューとして中心的です。
titleMultimodal Deep Learning and Foundation Models for Early Detection and Forecasting of Plant Diseases
Abstract A systematic review based on 174 Scopus-records of studies using YOLO-type one-stage detectors for detecting citrus fruits, their count, and yield estimation followed PRISMA guidelines 2020. The title/abstract-screening process, done in duplicate (κ=0.920) yielded 90 included study-records, followed by two further post-hoc exclusions. Each study in the 80 reporting on fruit-level detection showed an average precision of 89.6%, recall of 85.9%, and mAP@0.5 of 91.0%. However, coverage for any individual metric rarely exceeded half of the studies, and only 13% were able to report the more stringent mAP@0.5:0.95. Both YOLOv8 and YOLOv5 were each utilized as the backbone architecture by approximately 22.2% of the studies. From 2025, YOLOv11 has also been emerging. Half of all studies modified architectural components including attention modules, lightweight architectures, and variants of IoU loss functions. Original contributions are generally concentrated in downstream tracking, sensor fusion, and yield modeling rather than the detector itself. A custom-made seven-domain risk of bias tool was developed and utilized by two reviewers who arbitrated discrepancies (91.5%). Results showed that all but one of the reviewed studies had a high level of risk due to almost universal lack of statistical validation and limited dataset diversity; a sensitivity analysis excluding the most risky studies left the performance profiles nearly identical. We conclude that the field has converged around a common technical toolkit but continues to lack standardized benchmarks, multispectral data, and rigorous field-deployment validation.
Why it matches plant phenotyping methods柑橘果実の検出・計数・収量推定に用いる画像解析手法を体系的にレビューし、性能評価、リスク・オブ・バイアス、標準化やベンチマーク不足を検討しており、植物フェノタイピング手法が中心である。
abstractA systematic review based on 174 Scopus-records of studies using YOLO-type one-stage detectors for detecting citrus fruits, their count, and yield estimation followed PRISMA guidelines 2020.
Food safety globally is threatened by crop disease, which creates a major obstacle to yield losses, so there is an urgent need for rapid, precise, and large-scale diagnostic methods for all the global risks crops are exposed to from disease. While imaging sensors, as well as Artificial Intelligence (AI), have made great strides in recognising plant disease, most literature does not have a comprehensive analysis that combines methods, technology, and implementation. Therefore, a systematic literature review follows PRISMA methods; we review 61 excellent studies published within the last five years that outline the advancement of imaging modalities (Red, Green, Blue (RGB), multispectral/ hyperspectral, thermal), deep learning architectures, augmentation of data, explanation methods and IoT (Internet of Things)-edge-cloud for managing intelligent agriculture. These modern AI-based systems (AI systems) have consistently produced accurate results above 98%. However, there are problems with the generalisability (across hybrid plant species), robustness (when exposed to environmental stresses), and interpretability of the results presented to consumers. This review represents the first compilation of using imaging sensors, artificial intelligence models, Internet of Things architecture (IoT-edge), and robotics into one comprehensive framework for the detection of plant disease in the next generation. In addition, this review suggests future research directions, including lightweight edge-deployable models, multimodal sensor fusion, interpretable AI, larger validated datasets, and autonomous robotic systems for scalable and sustainable smart agriculture.
Why it matches plant phenotyping methods植物病害の画像・センサーによる検出手法を体系的にレビューしており、病害状態のフェノタイピング手法が中心です。
titleComprehensive Review of Plant Disease Detection: Advancements in Imaging Sensors, AI Techniques, and Future Directions in Smart Agriculture
Plant diseases remain a threat to global agricultural productivity, food security and livelihoods, especially in developing countries where the availability of experts in agriculture is still limited. The recent progress in AI, particularly deep learning and computer vision, has ushered in new possibilities for automated plant disease diagnosis, especially for plant image-based systems. This paper provides a systematic review of the deep learning methods employed for plant disease diagnosis, highlighting CNN-based methods, the application of transfer learning, explainable AI (XAI) methods and deployment issues. In the framework of PRISMA 2020, the relevant peer reviewed literature from 2016 to 2025 was systematically identified, screened and analysed on the most important academic databases. The review compared some of the most popular architectures such as GoogLeNet, DenseNet-121, MobileNetV2, EfficientNet, Attention-CNNs and Vision Transformers. Results showed very high classification accuracy in controlled lab conditions with DenseNet-121 achieving ~99.75% accuracy with good computational efficiency. But it also revealed a big gap between the lab and the field, mainly due to environmental variations, domain shifts, and dependence on datasets. Some innovative and emerging technologies like explainable AI, hyperspectral imaging, few-shot learning, and lightweight mobile architectures showed promise of enhancing the interpretability, early detection of disease, and the use of smart phones in low-resource agricultural settings. In conclusion, the study suggests that in order to be implementable in the field, future intelligent agricultural diagnosis systems must be able to balance predictive accuracy, explainability, computational efficiency and field adaptability. The results enrich the existing knowledge on precision agriculture and serve as useful information for researchers, agricultural technologists, and policymakers working on the creation of AI-based systems for crop protection.
Why it matches plant phenotyping methods植物病害を画像から診断する深層学習手法を体系的に比較・レビューしており、植物の病徴・病害状態の推定方法が中心である。
abstractThis paper provides a systematic review of the deep learning methods employed for plant disease diagnosis
Plant diseases lead to substantial yield losses and pose a persistent threat to global food security, creating an urgent demand for high-throughput, accurate, scalable, and non-destructive disease-monitoring approaches. Remote sensing has emerged as a powerful tool, yet progress in plant disease detection remains fragmented across various disciplines, tasks, sensing methods, and data modalities. This review introduces a hex-view perspective to synthesise remote-sensing-based plant disease detection within a cohesive conceptual framework. Instead of treating sensing technologies, algorithms, and datasets independently, the hex-view incorporates six interconnected dimensions that jointly capture how biological processes, the measurement scale, and data characteristics constrain disease detectability, including when detection is possible and how reliably it can be achieved. The hex-view framework comprises six interconnected dimensions and forms an integrated framework called BTSCAD: (1) Biology (B): plant–pathogen interactions constituting the biological foundation of disease development and expression. (2) Task (T): the diverse disease-detection tasks and their corresponding research objectives. (3) Sensor (S): the sensing modalities that define the data acquisition type and richness of captured information. (4) Condition (C): the environmental conditions, sensing platforms, and spatial scales that shape disease observations and bridge controlled experiments and real-world deployment across leaf, canopy, plot, and regional scales. (5) Algorithm (A): the classical and state-of-the-art data-analysis algorithms used to extract disease-related information from sensor data. (6) Dataset (D): the data sources that underpin model development, evaluation, and generalisability. The hex-view perspective provides a clear framework for interpreting previous research and identifying future research directions. This review lays a structured foundation for developing robust, interpretable, and transferable disease-detection systems, supporting advancements in precision agriculture, high-throughput phenotyping, and sustainable crop production.
Why it matches plant phenotyping methods植物病害を対象としたリモートセンシングによる病徴・病害状態の検出方法を、センサー、条件、アルゴリズム、データセットの観点から体系化する方法論レビューであり、植物フェノタイピング手法が中心です。
abstractThis review introduces a hex-view perspective to synthesise remote-sensing-based plant disease detection within a cohesive conceptual framework.
Existing reviews on AI in tea production are either agriculture-generic or limited to isolated tasks. This review thoroughly compares vision technologies (RGB, hyperspectral, near-infrared, thermal, Light Detection and Ranging (LiDAR), Unmanned Aerial Vehicle (UAV)) and establishes a task-oriented algorithm selection framework for the tea industry. For small-sample or near-linear problems, traditional machine learning (ML) (support vector machine (SVM); partial least squares regression (PLSR)) remains effective. For unstructured field tasks, deep learning achieves superior performance: pest detection accuracy exceeds 97%, tea bud detection reaches 96.8% with RGB images, and hyperspectral imaging predicts nitrogen content with R 2 > 0.90 and tea polyphenols with R 2 up to 0.925. Algorithm choice further differentiates by task granularity: lightweight convolutional neural networks (CNNs) balance speed and accuracy for edge deployment at 16 fps; You Only Look Once (YOLO) series detectors enable real-time localization on mobile platforms at 93.1% accuracy, 24 ms per target. No single algorithm dominates all tea tasks; selection is a trade-off among accuracy, speed, data availability, and computational constraints. These findings outline a structured analysis of the challenges and pathways for transitioning computer vision (CV) from laboratory research toward field-deployable tools.
Why it matches plant phenotyping methods茶作物の画像センシング技術と解析アルゴリズムを体系的に比較し、害虫検出や窒素含量予測など植物状態・形質の推定方法を扱う方法論レビューである。
abstractThis review thoroughly compares vision technologies (RGB, hyperspectral, near-infrared, thermal, Light Detection and Ranging (LiDAR), Unmanned Aerial Vehicle (UAV)) and establishes a task-oriented algorithm selection framework for the tea industry.
Published17 Aug 2026Growth hormone & IGF research : official journal of the Growth Hormone Research Society and the International IGF Research SocietyCited by 0 · OpenAlex ↗
Background ecombinant human growth hormone (rhGH) has been used for four decades under a largely population-based dosing paradigm, yet growth response varies substantially among children with apparently similar auxological phenotypes. Advances in genomics, GH-insulin-like growth factor-1 (IGF-1) axis biomarkers, mathematical and machine-learning (ML) prediction models, and digital health technologies now allow individualized characterization of growth disorders, forming the basis of an emerging precision-endocrinology paradigm. Objectives (1) to synthesize evidence on monogenic and polygenic genetic determinants of pediatric growth faltering and/or short stature and their diagnostic yield; (2) to evaluate GH-IGF-1 axis biomarkers and pharmacogenetic markers, including the IGF-1/IGFBP-3 molar ratio as a likely better indicator of bioactive IGF-1 than IGF-1 alone, together with mathematical/ML prediction models, for individualizing rhGH therapy; and (3) to appraise artificial intelligence (AI) and digital-health tools, bone-age algorithms, facial-recognition phenotyping, adherence-prediction models, and smartphone growth-monitoring, as instruments for operationalizing precision endocrinology in children and adolescents with growth disorders. Methods This is a systematic review employing narrative synthesis (a systematic scoping review). Reporting explicitly followed the PRISMA Extension for Scoping Reviews (PRISMA-ScR) checklist rather than the PRISMA 2020 statement for systematic reviews and meta-analyses, because the heterogeneous outcome metrics across genetic, diagnostic-accuracy, prediction-model, and AI/digital-health studies preclude meta-analytic pooling of a single quantitative effect size; PRISMA-ScR is the methodologically appropriate reporting framework for a review mapping evidence across such conceptually distinct domains. PubMed/MEDLINE was searched for English-language, pediatric (0-18 years) studies published between 2000 and 2026. Two-stage screening (title/abstract, then full text) was performed. Quality was appraised using design-appropriate tools: an adapted Newcastle-Ottawa Scale for genetic-association studies, QUADAS-2 for diagnostic-accuracy biomarker studies, PROBAST/TRIPOD-informed criteria for prediction-model and ML studies, and reference-standard/external-validation criteria for AI-imaging studies. Sixty-two studies were retained for qualitative synthesis. Results Monogenic defects (SHOX, ACAN, NPR2) and exome-sequencing panels explain a meaningful minority (approximately one-quarter) of previously "idiopathic" short stature, while genome-wide association studies and polygenic scores capture a substantial share of the remaining heritable variance, with polygenic risk scores achieving areas under the receiver-operating-characteristic curve up to 0.84 for predicting adult short stature. The IGF-1/IGFBP-3 M ratio outperforms IGF-1 alone for diagnosing GH deficiency (sensitivity 87.5%, specificity 83.0%), reflecting the greater bioavailability of free, unbound IGF-1 relative to that carried in the ternary IGF-1/IGFBP-3/acid-labile-subunit complex. GH-receptor exon-3 (d3) pharmacogenetic variants and machine-learning models (random forest, transcriptomic classifiers) improve prediction of individual rhGH response beyond classical mathematical models. AI-based bone-age algorithms achieve near-radiologist accuracy with reduced inter-observer variability, computer-aided facial-phenotyping tools show comparable diagnostic accuracy for syndromic short-stature disorders such as Noonan and Turner syndrome, and connected-device/ML adherence-monitoring and smartphone growth-tracking tools objectively detect suboptimal adherence and growth faltering earlier than conventional clinic-based surveillance; network meta-analyses of once-weekly long-acting rhGH formulations further suggest that reduced injection burden can translate into modestly improved height outcomes relative to daily rhGH. These findings are synthesized into a Precision-Medicine Cascade, a practice-oriented framework showing how genotype, biomarker, and digital data streams can be layered onto routine auxological assessment to guide same-visit clinical decisions on diagnostic work-up, dosing, and monitoring frequency. Conclusion Converging genetic, biomarker, computational, and digital-health evidence supports a feasible, evidence-grounded trajectory toward individualized therapy, including rhGH and emerging growth-plate-targeted agents, in pediatric growth disorders. The Precision-Medicine Cascade proposed here offers pediatric endocrinologists an immediately applicable framework for integrating these tools into everyday practice. However, current tools remain adjunctive rather than replacement for clinical judgment, and prospective, ethnically diverse validation of integrated precision-endocrinology pathways is required before routine adoption.
Why it matches plant phenotyping methods植物ではなく小児成長障害を対象とするため通常の植物フェノタイピング索引には不適合だが、提示基準上の「plant」要件を満たさないため本来は除外。ただしレビュー自体はAI画像・成長モニタリング等のヒト表現型手法を中心的に扱う。
Sustainable crop improvement is urgently needed to ensure global food security, particularly for developing and densely populated countries. The integration of artificial intelligence (AI) and machine learning (ML) into crop science tri typing is reshaping the conventional agriculture practices into an era of high-throughput phenotyping (HTPP) data-driven modern agriculture. AI tools accelerate data generation, mining, imputation, storage, transfer, and optimal decision-making within agricultural systems. AI tools are paving the way for modern plant breeding strategies by uncovering genetic variability and bridging the genotype-to-phenotype (G2P) gap, thus enabling the future of predictive breeding. Plant genetic gains or phenotype (P), by and large, depend on the genotype (G), environment (E), and their interaction (GEI). This review will provide a comprehensive overview of the historical background, current status, and prospects for integrating AI and ML tools in agricultural tri-typing, encompassing genotyping, phenotyping, and envirotyping. We explore AI-driven tools for genome analysis, HTPP platforms, and environmental data integration, emphasizing how these technologies overcome persistent bottlenecks in predictive breeding. Furthermore, this review will offer the reader key insight into modern trends, including the paradigm shift in phenomics patent filings, global distribution of HTP phenomics facilities, the publications volume and related research over the last two decades, and individual institutions currently leading or prospectively will lead the world in plant phenomics. Similar to plant phenotyping, we also try to address the integration and application of AI/ML algorithms in plant genotyping and envirotyping. Supplementary information The online version contains supplementary material available at 10.1007/s11032-026-01705-1.
Why it matches plant phenotyping methods植物フェノタイピング、ハイスループットフェノタイピング、AI/MLツールを中心に扱う包括的レビューであり、方法論レビューとして該当する。
abstractThis review will provide a comprehensive overview of the historical background, current status, and prospects for integrating AI and ML tools in agricultural tri-typing, encompassing genotyping, phenotyping, and envirotyping.
Photosynthesis is the fundamental biological process underlying plant growth, crop productivity, and global food security. However, its efficiency is highly vulnerable to abiotic stresses, which disrupt chlorophyll biosynthesis, electron transport, carbon assimilation, stomatal regulation, and photoprotective mechanisms, ultimately reducing crop yield. Improving photosynthetic resilience under adverse environments has therefore become a major objective of modern crop improvement. Recent advances in phenomics and high-throughput phenotyping (HTP) have transformed the evaluation of photosynthesis-related traits by enabling rapid, non-destructive, and large-scale assessment across diverse environments, while facilitating quantitative characterization of structural, physiological, biochemical, and thermal responses to abiotic stress. Technologies including chlorophyll fluorescence, gas-exchange analysis, thermal imaging, hyperspectral imaging, LiDAR, and UAV-based sensing provide comprehensive insights into plant physiological responses and stress adaptation. Integration of these phenomic approaches with genomic information and artificial intelligence (AI)-driven analytical frameworks has strengthened genomic and phenomic prediction, enabling more accurate identification of candidate genes, selection of superior genotypes, and accelerated genetic gain. This review critically synthesizes recent advances in photosynthesis-related traits, phenomics, HTP technologies, and their integration with genomics and AI-assisted breeding, highlighting current challenges, knowledge gaps, and future opportunities for developing climate-resilient wheat and rice cultivars and promoting sustainable crop production.
Why it matches plant phenotyping methods植物の光合成形質を対象に、HTP技術やセンサー手法を体系的にレビューしており、フェノタイピング手法が中心である。
abstractThis review critically synthesizes recent advances in photosynthesis-related traits, phenomics, HTP technologies, and their integration with genomics and AI-assisted breeding
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 5 Sept 2026
Calcium ions (Ca2+) function as ubiquitous second messengers that translate environmental and developmental cues into spatially and temporally defined cellular responses in plants. This review summarizes the cellular architecture and molecular mechanisms that generate, shape, and terminate Ca2+ signals, with emphasis on plasma-membrane channels, intracellular stores, pumps, exchangers, and organelle-associated transport systems. We also examine the development of live Ca2+ indicators, from chemical dyes and aequorin to ratiometric and single-fluorophore genetically encoded calcium indicators, and discuss principles for selecting sensors for different tissues and subcellular compartments. Recent studies have applied these tools to abiotic stress, plant immunity, polar growth, development, symbiosis, and systemic signaling. Accurate quantitative imaging nevertheless requires careful matching of sensor properties to the target cellular environment and rigorous control of motion, spectral interference, and analytical procedures. Combining improved indicators with advanced microscopy, genetic validation, and standardized data analysis should help connect distinct Ca2+ signatures with their molecular origins and physiological roles.
Why it matches plant phenotyping methods植物のCa2+シグナルを定量するライブイメージング指標、顕微鏡、解析手順を中心にレビューしており、生理状態の取得方法が主題である。
abstractWe also examine the development of live Ca2+ indicators, from chemical dyes and aequorin to ratiometric and single-fluorophore genetically encoded calcium indicators, and discuss principles for selecting sensors for different tissues and subcellular compartments.
Abstract Crop improvement increasingly depends on resolving how plants move through physiological states during stress rather than where they end up, yet the dominant convention still reduces dense, multi-sensor, longitudinal trait data to a single static value before genetic analysis, discarding information about state, transition and uncertainty. This systematic review asked whether a quantum-inspired, state-based representation of dynamic crop phenotypes could be integrated with established genomic tools to improve trait characterisation and gene discovery, and what the literature reports about the components it would require. Reporting followed the PRISMA 2020 statement and the Synthesis Without Meta-analysis (SWiM) guideline. Scopus, Web of Science Core Collection, PubMed and a Google Scholar grey-literature sweep were searched from January 2017, retrieving 2,413 records, after de-duplication 1,777 titles and abstracts were screened, 279 full texts were assessed, and 82 studies met the eligibility criteria and entered a thematic synthesis. Studies were dual-screened, appraised with an adapted Mixed Methods Appraisal Tool, and their comparable within-study outcomes synthesised by vote counting on direction of effect; meta-analysis was inappropriate because outcomes were not commensurable. Every component of the paradigm probabilistic state representation, temporal trait modelling and trajectory-aware genomic prediction was independently validated, but no included study unified them for crop-stress genetics. All comparable comparisons favoured the temporally richer method, an asymmetry indicating probable reporting bias, and certainty was moderate for representation and modelling and low for realised genetic gain. The phenotyping bottleneck has migrated from measurement to representation.
Why it matches plant phenotyping methods作物の動的表現型を状態表現・時間的形質モデル・軌跡対応ゲノム予測で扱う方法論の系統的レビューであり、表現型の表現・解析手法が中心である。
abstractThis systematic review asked whether a quantum-inspired, state-based representation of dynamic crop phenotypes could be integrated with established genomic tools to improve trait characterisation and gene discovery
Field / plotMultimodalNeRF / 3D Gaussian SplattingLiDAR / point cloudRGB / grayscaleStereoFruitWhole plant / canopy / plot / fieldMorphology / geometry measurementObject detection
Binocular stereo vision is a low-cost and scalable 3D perception technology that shows strong potential in agricultural phenotyping and smart agriculture. By estimating depth from multi-view RGB images, it enables non-contact, high-precision sensing of crop structure, canopy morphology, growth dynamics, and livestock traits, providing essential support for digital and intelligent agricultural production. With recent advances in deep learning-based stereo matching, multimodal sensor fusion, and 3D reconstruction, its robustness and accuracy in complex field environments have been significantly improved. This paper systematically reviews recent progress in agricultural applications of binocular stereo vision, covering system architectures, traditional and deep learning-based stereo matching methods, point cloud reconstruction techniques, and emerging supervision strategies such as 3D Gaussian splatting. It further summarizes key applications, including high-throughput phenotyping, fruit localization and robotic harvesting, weed detection and precision spraying, autonomous navigation, and livestock body condition assessment, highlighting its role in multi-task agricultural perception systems. Finally, the paper discusses major challenges, including low-texture matching difficulty, occlusions in complex environments, cross-domain generalization, real-time lightweight deployment, and limited dataset availability. Future directions are outlined in foundation model-based visual perception, self- and weakly supervised learning, multimodal fusion, and edge-efficient model design, aiming to support large-scale deployment in smart agriculture.
Why it matches plant phenotyping methods農業における双眼ステレオビジョンのシステム、ステレオマッチング、3D再構成を体系的にレビューし、作物構造・群落形態・生育動態の非接触計測とハイスループット表現型解析を主要対象としているため。
abstractThis paper systematically reviews recent progress in agricultural applications of binocular stereo vision, covering system architectures, traditional and deep learning-based stereo matching methods, point cloud reconstruction techniques
Sorghum (Sorghum bicolor L. Moench) is a major cereal in water-limited environments. Its C4 carbon-concentrating pathway suppresses photorespiration and supports comparatively high photosynthetic and water-use efficiency at high temperature, although yield remains sensitive to the timing and intensity of drought. This systematic review critically evaluates how coordinated variation in phenology, canopy development, transpiration regulation, photosynthetic resilience and root-mediated water capture can be phenotyped for sorghum improvement. The review was conducted and reported in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 statement. Eligible primary studies examined sorghum drought physiology, sensing-based phenotyping, trait retrieval, root-associated water capture, or breeding applications. Following duplicate removal and title, abstract and full-text screening, 45 sorghum-specific studies were included. Owing to substantial heterogeneity in experimental design, drought treatment, sensing platform, target trait, and validation metric, evidence was synthesised narratively rather than by meta-analysis. We compare sorghum studies across Light Detection and Ranging (LiDAR), multi-spectral, hyperspectral, thermal, structural, and fluorescence sensing, with emphasis on reported accuracy, transferability and physiological interpretation. We then examine how PROSAIL (PROSPECT coupled with Scattering by Arbitrarily Inclined Leaves) and SCOPE (Soil Canopy Observation, Photochemistry and Energy Fluxes) can be constrained for sorghum canopies and combined with machine learning. The central contribution is a sorghum-specific framework that distinguishes directly observed or model-retrieved canopy traits from indirect root-function predictions requiring ground validation. The synthesis identifies practical routes for measuring functional stay-green, high-vapour-pressure-deficit responses and post-anthesis water capture, while defining priorities for cross-environment validation and breeding deployment.
Why it matches plant phenotyping methodsソルガムの干ばつ適応に関するセンシング型フェノタイピング手法を体系的にレビューし、形質推定の精度・移植性・検証、およびモデルと機械学習の統合を扱うため、方法論が中心である。
abstractThis systematic review critically evaluates how coordinated variation in phenology, canopy development, transpiration regulation, photosynthetic resilience and root-mediated water capture can be phenotyped for sorghum improvement.
Magnetic field (MF) technologies have been explored in agriculture since the 1930s, with research activity increasing markedly since 2016. However, they have not achieved mainstream adoption, partly because no MF-specific validated methodology exists for evaluating their effects under realistic field conditions. Unmanned Aerial Vehicle (UAV)-based multispectral sensing represents a potential pathway to address this limitation by providing spatially explicit, non-destructive estimates of key canopy physiological variables at field scale, thereby enabling, for the first time, the systematic evaluation and validation of MF treatment responses under open-field conditions. To realise this potential, however, a common evidential basis must first be established by identifying crop physiological variables that are both consistently modulated by MF treatments and reliably detectable by UAV remote sensing. This study addressed this challenge through a dual-stream evidence synthesis of 216 peer-reviewed publications, comprising 102 studies on MF treatments in agricultural crops and 114 studies on UAV-based multispectral monitoring. Evidence from both research domains was synthesised to identify physiological variables that are simultaneously responsive to MF treatments and detectable through UAV remote sensing. Five direct bridge variables were identified: chlorophyll content, nitrogen use efficiency (NUE)/nitrogen assimilation, above-ground biomass (AGB), leaf area index (LAI), and yield. Chlorophyll content emerged as the strongest bridge variable, combining consistent MF responsiveness with UAV estimation accuracies of up to R2 = 0.90. Based on these findings, a conceptual framework was developed linking MF treatments, UAV-derived vegetation indices, ground-truth measurements, and machine-learning approaches for field-scale validation. The review revealed a complete absence of integration between the two research domains within the reviewed corpus, despite their strong biological and methodological compatibility. The proposed framework is conceptual and remains to be experimentally validated; it provides the first operational pathway for evaluating MF technologies under realistic farming conditions and may support future research on sustainable and digitally enabled crop production systems.
Why it matches plant phenotyping methodsUAVマルチスペクトルセンシングによる作物生理形質の推定をレビューし、地上真値・植生指数・機械学習を統合した検証フレームワークを提案しており、植物表現型の取得・推定方法が中心です。
abstractUnmanned Aerial Vehicle (UAV)-based multispectral sensing represents a potential pathway to address this limitation by providing spatially explicit, non-destructive estimates of key canopy physiological variables at field scale
Efficient nitrogen (N) management is essential for sustaining crop productivity while minimizing environmental impacts associated with nitrogen losses. However, the high spatial and temporal variability of soil nitrogen dynamics and crop nitrogen status makes field-scale monitoring challenging, while conventional soil and plant sampling methods are labor-intensive, destructive, and provide limited spatial coverage. Recent advances in remote sensing technologies and machine learning (ML) offer promising alternatives for high-throughput, non-destructive monitoring of crop nitrogen status and related nitrogen dynamics in agroecosystems. This review synthesizes current progress in the use of proximal and remote sensing platforms, including unmanned aerial vehicles (UAVs), satellites, and ground-based sensors for assessing crop nitrogen status and inferring soil nitrogen availability. We examine spectral, thermal, and structural indicators, together with emerging sensor-fusion and time-series approaches. We also evaluate ML algorithms, including emerging foundation model approaches, for estimating crop nitrogen status and inferring soil nitrogen indicators, highlighting their performance, limitations, and transferability across environments. Particular emphasis is placed on field-scale applications in heterogeneous and water-limited systems, where nitrogen-water interactions critically influence crop responses. Finally, we discuss current challenges, including data scarcity, model generalization, and operational constraints, and outline future directions toward integrated, real-time decision support systems for precision nitrogen management. Overall, this review provides a comprehensive framework for leveraging remote sensing and data-driven approaches to improve nitrogen monitoring and enhance nitrogen use efficiency in diverse cropping systems.
Why it matches plant phenotyping methods作物の窒素状態という植物形質を対象に、リモートセンシングと機械学習による推定手法を体系的にレビューしており、フェノタイピング手法が中心である。
abstractThis review synthesizes current progress in the use of proximal and remote sensing platforms, including unmanned aerial vehicles (UAVs), satellites, and ground-based sensors for assessing crop nitrogen status and inferring soil nitrogen availability.
Nano- and microplastics (NMPs) are now widely detected across agroecosystems and can act as physiological stressors in plants. Exposure occurs through contaminated soil, irrigation water, or airborne deposition, bringing particles into direct contact with roots and above-ground tissues. Reported entry routes include apoplastic transport, cracks formed at lateral root emergence, leaf stomata, and endocytosis once particles have crossed the cell wall. Once internalized, particles may translocate through the xylem and, in some cases, the phloem, accumulating in roots, stems, and leaves depending on particle size, surface charge, and plant structural characteristics. NMPs have been associated with oxidative stress, disrupted photosynthesis, and altered metabolic pathways. Detecting NMPs within heterogeneous, hydrated plant tissues remains challenging, as particles often show low contrast against biological structures and can be mistaken for cellular components. This review examines how microscopy techniques reveal NMPs size, surface attachment, tissue distribution, and cellular-level interactions, while noting that these approaches primarily provide morphological or localization information rather than confirming polymer identity. Complementary spectroscopic and mass-based analytical methods are discussed for their role in chemical confirmation and quantification. This review supports informed selection among imaging, spectroscopic, and quantitative techniques for studying plant-plastic interactions, while highlighting current analytical challenges facing the field.
Why it matches plant phenotyping methods植物組織内の粒子サイズ・付着・分布・細胞相互作用を測定する顕微鏡、分光、質量分析手法を中心にレビューしており、植物状態の観測手法が主題である。
abstractThis review examines how microscopy techniques reveal NMPs size, surface attachment, tissue distribution, and cellular-level interactions
Crop stress develops through a sequence that begins with molecular and biophysical perturbation, progresses through physiological dysfunction, and only later becomes visually apparent. Precision agriculture therefore requires sensors that can shorten the interval between stress onset and actionable diagnosis while preserving spatial context. This critical narrative review examines the complementary roles of nanosensors, plant-wearable and implantable electronics, proximal sensing, unmanned aerial vehicles, satellite remote sensing, and geographic information systems in early crop-stress detection. Literature published from 2000 to 1 June 2026 was selected through live searches of accessible scholarly indexes, DOI registries, publisher records, institutional repositories, and citation networks, with foundational studies retained where necessary. The evidence shows that nano-enabled interfaces can measure early biochemical, ionic, volatile, electrical, and microclimatic signals at high temporal resolution, whereas geospatial technologies reveal the distribution, persistence, and management relevance of stress across canopies and fields. Optical nanotube sensors, surface-enhanced Raman probes, electrochemical microneedles, ion-selective wearables, and flexible leaf sensors have demonstrated biologically meaningful signals before visible symptoms in controlled or pilot field settings. Yet most remain constrained by sparse sampling, crop-specific calibration, bio-interface effects, power and communication burdens, uncertain durability, and limited agronomic validation. Geospatial methods are operationally more mature, particularly thermal and multispectral imaging for water stress and hyperspectral imaging for disease and nutrient-related changes, but they often infer stress through non-specific proxies that are confounded by canopy structure, atmosphere, soil background, phenology, and co-occurring stresses. The strongest future architecture is therefore not a contest between nanoscale and landscape-scale sensing. It is a multiscale system in which physiologically specific plant sensors anchor and interpret spatial imagery, while remote sensing directs where high-specificity measurements and interventions are most valuable. Progress depends on prospective field trials, reference measurements, uncertainty-aware data fusion, interoperability, lifecycle safety assessment, and decision thresholds linked to economic and agronomic outcomes.
Why it matches plant phenotyping methods植物ストレス状態の検出に用いるナノセンサー、ウェアラブルセンサー、熱・マルチスペクトル・ハイパースペクトル画像などを中心に批判的に統合した方法レビューであり、単なる農業応用紹介ではなく、センサー性能、校正、検証、データ融合を論じている。
abstractThis critical narrative review examines the complementary roles of nanosensors, plant-wearable and implantable electronics, proximal sensing, unmanned aerial vehicles, satellite remote sensing, and geographic information systems in early crop-stress detection.
High perishability of vegetables associated with rapid physiological deterioration and microbial spoilage results in 30-50% post-harvest losses globally. In earlier days, post-harvest diseases were detected by visual inspection, microbial culturing, and molecular assays. These destructive methods are time-consuming and unsuitable for real-time monitoring. Volatile organic compounds (VOCs) have emerged as promising non-destructive biomarkers enhanced for early detection of quality deterioration and pathogen attack, often before visible symptoms appear. This review provides a thorough overview of current knowledge on VOC emissions in postharvest vegetables with their biosynthetic origins, classification, and roles in different kinds of stress responses and host microbe interactions. VOC alterations during spoilage and disease progression are systematically evaluated, highlighting vegetable group-specific patterns and quantitative dynamics of key biomarkers emitted naturally and due to mechanical and microbial spoilage. GC-MS, GC-IMS, PTR-MS, electronic noses, and biosensors are advanced analytical techniques that are critically compared with emphasis on their integration with machine learning for classification accuracy. Despite this significant progress, variability across cultivars and storage conditions, overlap between host- and pathogen-derived volatile metabolites, and an enduring gap between laboratory findings and commercial applications are major challenges that cannot be ignored. The development of real-time monitoring systems, vegetable-specific VOC databases, and integration with smart storage infrastructure powered by the Internet of Things and artificial intelligence must be prioritized in the future.
Why it matches plant phenotyping methods野菜の品質劣化・病害状態をVOCで非破壊推定する分析技術と機械学習を中心に比較・レビューしており、植物状態の取得手法が主題である。
abstractVolatile organic compounds (VOCs) have emerged as promising non-destructive biomarkers enhanced for early detection of quality deterioration and pathogen attack, often before visible symptoms appear.
Grain quality is defined as the suitability of grain for a particular use. It is usually designated by chemical composition or physical properties of the grain. The ability to measure grain quality is important for identity preservation of specialty grain market classes, for development of new varieties with improved quality through breeding, and for basic scientific studies on the genetic or biochemical control of grain quality traits. This review introduces official methods for measuring maize compositional traits, including protein, starch, oil, amino acid, phytate, and phosphorus content. Additionally, we discuss two nonofficial methods: measuring phytate and available phosphorus levels, and assessing amino acid balance. Phytate and available phosphorous impact the mineral nutrition of grain, while amino acid balance reflects the value of grain as a protein source and the bioavailability of protein. We also describe the use of near-infrared spectroscopy (NIRS) to assess levels of various compounds in maize. NIRS relies on the fact that compounds with differing molecular properties uniquely interact with the near-infrared region (750-2500 nm) of the electromagnetic radiation spectrum, and thus, generate spectral information that can be used to develop calibration models/equations for predicting the concentration of the compounds in grain samples. We discuss how sensitivity, accuracy, precision, throughput, and cost influence the choice of assay used to assess grain quality. Furthermore, we discuss how appropriate experimental design and data analysis can improve analytical outcomes when assessing grain quality.
Why it matches plant phenotyping methodsトウモロコシ穀粒の化学・物理形質を測定する方法を中心にレビューし、NIRSによる校正モデルと測定性能も扱っているため、植物形質計測法のレビューとして対象に含める。
abstractThis review introduces official methods for measuring maize compositional traits, including protein, starch, oil, amino acid, phytate, and phosphorus content.
Traditional breeding is approaching its efficiency limit in addressing global food security challenges, climate change, and multi-dimensional information integration. Artificial intelligence (AI) and digital phenotyping have become core driving forces in data-driven breeding. This review systematically elaborates the evolutionary roadmap from AI breeding 1.0 , which relies on traditional phenotypic data, to the emerging paradigm of AI breeding 2.0 . We clarify the core differences between these two paradigms, dissect the “data divide” in the transition process, and summarize the integrated technical framework underlying AI breeding 2.0 . The central argument is that the core limitation of AI breeding 1.0 lies in data inadequacy rather than constraints on algorithmic capacity. The transition to AI breeding 2.0 relies on standardized high-throughput digital phenotyping, multi-modal data integration, and closed-loop data-centric breeding systems. Finally, we propose four priority actions to promote the widespread adoption of data-driven breeding and provide an actionable roadmap for enhancing global crop improvement efforts.
Why it matches plant phenotyping methods植物デジタルフェノタイピングをAI育種の中核技術として体系的に論じるレビューであり、フェノタイピング手法・データ統合・技術枠組みが中心です。
abstractArtificial intelligence (AI) and digital phenotyping have become core driving forces in data-driven breeding.
• First PRISMA-ScR mapping of 79 HSI-ML asymptomatic detection studies (42 species, 74 pathogens) • Controlled-to-field accuracy gap quantified: 91.4% vs. 86.3% (5.1 pp, p = 0.0163 ) • 56.8% of studies omit temporal sampling documentation (CV = 139%) • SWIR underutilization (11.8%) reflects economic, not scientific, barriers • DBVS proposed as standardized temporal metric for cross-study comparability Plant disease management requires non-invasive detection methods capable of identifying infections before visible symptom manifestation, thereby enabling timely intervention. Hyperspectral imaging combined with machine learning and deep learning (HSI-ML) achieves 90.2% classification accuracy in controlled environments for asymptomatic plant detection; however, systematic characterization of methodological practices across this rapidly expanding field remains absent. This PRISMA-ScR compliant scoping review mapped 79 peer-reviewed studies (2010–2025) encompassing 42 plant species and 74 pathogenic agents using a Population-Concept-Context framework. Visible-near-infrared (VNIR) systems dominated deployment (61.8%, n = 49 ), while short-wave infrared (SWIR) systems remained substantially underutilized (11.8%, n = 9 ) due primarily to economic rather than scientific constraints. Among 67 unique algorithms identified, machine learning methods accounted for 30.7% (SVM, random forests, and PLS-DA predominant), whereas deep learning represented 28.4% (2D-CNN, 3D-CNN, and hybrid architectures). Critical methodological gaps emerged: 56.8% of studies omitted temporal sampling documentation (detection latency range: 1–56 days post-inoculation; coefficient of variation = 139%). Platform-stratified analysis revealed controlled environments achieved 91.4% ± 6.6% classification accuracy ( n = 48 ) versus 86.3% ± 9.1% for field/UAV deployments ( n = 26 ), representing a significant 5.1 percentage-point performance decrease ( p = 0.0163 ). Detection accuracy exhibited a weak negative correlation with detection timing ( ρ = − 0.33 , p = 0.067 ), though this association did not reach conventional statistical significance. Methodological heterogeneity—rather than algorithmic limitations—constitutes the primary barrier to field operationalization. Adoption of Days Before Visible Symptoms (DBVS) as a standardized temporal metric could resolve an estimated 40–50% of cross-study variance currently attributed to inconsistent asymptomatic-phase definitions.
Why it matches plant phenotyping methods植物病害の無症状感染をHSIと機械学習で検出する手法群を対象に、79研究の方法、精度、時間指標、標準化課題を体系的に評価したレビューであり、フェノタイピング手法が中心です。
titleEarly detection of plant pathogens in the asymptomatic phase: A scoping review of hyperspectral imaging combined with machine learning
ABSTRACT Timely and reliable assessment of plant health is essential for resilient and sustainable agriculture, yet diagnostic practice remains divided between accurate but laboratory‐bound assays and emerging field‐deployable technologies. Herein, we adopt a plant‐centric and systems‐level perspective to synthesize advances in smart sensing for plant health monitoring reported between 2000 and 2026. Rather than surveying individual devices in isolation, we organize the literature around how sensing technologies are fabricated, integrated, and translated into actionable agronomic insights. Our synthesis reveals a clear shift toward multimodal, minimally invasive sensing architectures that combine material and fabrication innovations with contact and non‐contact modalities spanning organ, canopy, and landscape scales. We find that the most impactful progress arises not from individual sensors alone, but from integrated pipelines that couple sensing hardware with edge intelligence, cross‐scale data fusion, and explainable analytics. Furthermore, persistent barriers, including calibration transfer, long‐term stability, power autonomy, dataset bias, and cybersecurity, continue to impede widespread adoption. Based on these findings, we outline design principles and research priorities needed to accelerate translation, emphasizing standardized validation against biological benchmarks, energy‐autonomous and environmentally responsible sensor systems, and artificial intelligence (AI) frameworks capable of robust generalization across crops and environments. Looking ahead, we argue that plant health monitoring will increasingly be defined by closed‐loop systems that directly link plant physiological or pathological signals to adaptive management, positioning smart sensing as a cornerstone of data‐driven and climate‐resilient agriculture.
Why it matches plant phenotyping methods植物の健康状態・生理・病理シグナルを対象とするスマートセンシング手法を、統合、検証、校正、データ解析の観点から体系的にレビューしており、植物フェノタイピング手法が中心である。
abstractwe outline design principles and research priorities needed to accelerate translation, emphasizing standardized validation against biological benchmarks
Field / plotMRI / PETMultispectral / hyperspectralX-ray / CTRoot2D/3D reconstruction
Mycorrhizal fungi form essential symbiotic relationships with plant roots, facilitating nutrient exchange and promoting plant health. Understanding their interactions can benefit from advanced imaging techniques capable of visualizing nutrient exchange and structural colonization at subcellular resolution across large sample sizes. This review explores novel imaging approaches that are revolutionizing our understanding of root-mycorrhizal fungal symbioses. Several techniques can now visualize and characterize mycorrhizal fungi and associated root structures non-destructively and in three dimensions, for example X-ray computed tomography (micro-CT), X-ray fluorescence (XRF), and X-ray absorption near edge structure (XANES) spectroscopy. Metabolic processes and nutrient exchange can be tracked through positron emission tomography (PET), fluorescent nanoparticles (FNPs), and the monitoring of electrical signalling. Artificial intelligence (AI)-powered image processing software is enabling high-throughput analysis of complex images generated from a range of sources. Mycorrhiza systems are also able to be tracked in-field at multiple scales: hyperspectral imaging can detect mycorrhizal associations at the kilometre scale, while portable MRI imagers can detect changes at the tissue scale. These converging technologies enable the direct, continuous measurement of structural and metabolic root-mycorrhizal fungi interactions, paving the way for a mechanistic understanding of these vital symbiotic partnerships and their impact on plant health and ecosystem functioning.
Why it matches plant phenotyping methods植物根と菌根の構造・代謝・栄養交換を画像およびセンサーで直接測定する手法を扱うレビューであり、植物状態の取得技術が中心である。
abstractThis review explores novel imaging approaches that are revolutionizing our understanding of root-mycorrhizal fungal symbioses.
Accurate and timely crop yield estimation is fundamental for global food security, agricultural policy, and farm management. The Copernicus Sentinel-2 constellation has catalyzed a paradigm shift in Earth observation for agriculture, enabling field and sub-field scale monitoring. This review synthesizes recent advances in crop yield estimation that leverage Sentinel-2 data. A dominant theme is the transition from regional-scale to high-resolution field-level assessments, driven by three approaches: (i) empirical models using vegetation indices coupled with machine and deep learning (e.g., Random Forest, Convolutional Neural Networks); (ii) integration of process-based crop growth models (e.g., WOFOST, SAFY) through data assimilation of Sentinel-2 derived biophysical variables such as Leaf Area Index; and (iii) data fusion of Sentinel-2 with Sentinel-1 Synthetic Aperture Radar to overcome cloud cover. The synthesis shows that Sentinel-2-based frameworks can explain a large fraction of within-field yield variability, while performance remains constrained by limited ground-truth data, cloud gaps, and model transferability. Looking ahead, knowledge-guided models, self-supervised foundation-model pre-training, lightweight edge workflows, improved ground observations, and multi-sensor fusion are key pathways toward robust, operational decision-support tools for precision agriculture.
Why it matches plant phenotyping methods圃場・圃場内スケールの作物収量という植物形質を対象に、Sentinel-2等による推定手法、モデル統合、データ融合、性能制約を体系的にレビューしており、方法論が中心である。
abstractThis review synthesizes recent advances in crop yield estimation that leverage Sentinel-2 data.
Purpose: This paper investigated automated physical quality assessment of harvested seeds. Design/Methodology/Approach: This study provides an extensive review of computer vision-based two-dimensional (2D) and three-dimensional (3D) deployments for the physical inspection of harvested seeds and grains. For this purpose, a total of 75 peer-reviewed articles published between 2022 and 2025 were identified from scientific databases, including Scopus, Web of Science, IEEE Xplore, and ScienceDirect. These articles were based on seed quality assessment, image processing, and artificial intelligence. The selected articles were systematically analysed according to different stages of the processing pipeline, including data acquisition, preprocessing, segmentation, feature extraction, and classification. Research Limitation: This review is restricted to physical quality assessment of harvested seeds, excluding chemical, biochemical, and nutritional parameters. It references 75 peer-reviewed articles published between 2022 and 2025. Findings: This study identified technical problems related to variations in seed samples, hardware setups, segmentation, feature selection, and classification. These problems significantly affect the performance of automated systems. Based on a critical examination of the present automated systems, this paper highlighted the scope for future research. Practical Implication: An advanced, future-ready system can address the need for integrated imaging methods and effective data processing. Social Implication: The adoption of automated seed inspection systems provides assurance of food security. Originality/ Value: This paper identified critical gaps such as the absence of a unified processing framework, the lack of cross-species generalisation, and the limited adoption of explainable AI.
Why it matches plant phenotyping methods収穫種子の物理品質を画像から評価する2D/3Dコンピュータビジョン手法を体系的にレビューしており、植物形質取得法が中心である。
abstractThis study provides an extensive review of computer vision-based two-dimensional (2D) and three-dimensional (3D) deployments for the physical inspection of harvested seeds and grains.
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 5 Sept 2026
Background: Rice breeding requires faster development of high-yielding, climate-resilient, resource-efficient, and high-quality cultivars for production systems exposed to environmental variability and increasing input constraints. Genomic selection offers an opportunity to predict breeding value before extensive field evaluation, although its effectiveness depends on the integration of genomic, phenotypic, and environmental information. Methods: This narrative review critically examines recent advances in genomic selection for rice and its integration with high-throughput genotyping, high-throughput phenotyping, machine learning, multi-environment prediction, and speed breeding. Results: Genome-wide marker data can support early ranking of breeding materials for grain yield, grain quality, disease resistance, drought tolerance, salinity tolerance, and nutrient-use efficiency. Prediction performance is influenced by trait architecture, marker density, training-population size, genetic relatedness between training and candidate populations, phenotypic data quality, and genotype-by-environment interaction. Red-green-blue, multispectral, hyperspectral, thermal, and light detection and ranging platforms can generate temporal traits associated with plant architecture, biomass, water status, nutrient status, and stress responses, which may improve prediction under suitable population and validation designs. Speed-breeding systems shorten generation intervals and facilitate rapid advancement, recurrent selection, and recycling of superior parental lines. Conclusions: Integrated breeding pipelines that combine genomic prediction, high-throughput phenotyping, environmental data, and speed breeding can improve selection efficiency and shorten rice improvement cycles. Wider adoption will require affordable technology platforms, standardized data systems, multi-environment validation, breeder capacity development, and collaborative data-sharing frameworks for smart and greener agriculture.
Why it matches plant phenotyping methods高スループット表現型解析をゲノム選抜との統合という方法論的主題の一部として批判的にレビューしており、各種画像・センサープラットフォームと形質抽出を扱うため、表現型手法レビューに該当する。
abstractThis narrative review critically examines recent advances in genomic selection for rice and its integration with high-throughput genotyping, high-throughput phenotyping, machine learning, multi-environment prediction, and speed breeding.
Agriculture plays a pivotal role in ensuring global food security, economic stability, and sustainable development. Plant diseases significantly reduce agricultural productivity, resulting in substantial economic losses and threatening food supply worldwide. Early and accurate identification of plant leaf diseases enables timely intervention, minimizes crop damage, and enhances agricultural yield. Traditional disease diagnosis relies heavily on visual inspection by agricultural experts, making the process labor-intensive, subjective, and unsuitable for large-scale deployment. Recent advances in artificial intelligence, particularly deep learning, have transformed plant disease diagnosis by enabling automatic feature extraction and highly accurate image-based classification. This review presents a comprehensive analysis of recent developments in deep learning techniques for plant leaf disease identification. Various convolutional neural network (CNN) architectures, including AlexNet, VGGNet, ResNet, DenseNet, EfficientNet, MobileNet, Inception, and Xception, are critically reviewed along with modern transformer-based models such as Vision Transformer (ViT), Swin Transformer, and hybrid CNN–Transformer frameworks. The paper also examines transfer learning strategies, object detection methods including YOLO and Faster R-CNN, and semantic segmentation approaches such as U-Net and DeepLabV3+. Publicly available benchmark datasets, including PlantVillage, PlantDoc, AI Challenger, Cassava Leaf Disease, and Rice Leaf Disease datasets, are discussed in terms of dataset diversity, annotation quality, and practical applicability. Furthermore, image preprocessing techniques, data augmentation methods, evaluation metrics, and deployment considerations for mobile and edge devices are comprehensively reviewed. The paper identifies current research challenges, including dataset imbalance, environmental variability, model interpretability, computational complexity, and limited real-world generalization. Finally, emerging research directions such as explainable artificial intelligence, federated learning, multimodal learning, self-supervised learning, lightweight architectures, and edge AI are discussed to provide future research opportunities. This review serves as a valuable resource for researchers, practitioners, and agricultural technologists interested in developing robust, scalable, and intelligent plant disease identification systems.
Why it matches plant phenotyping methods植物葉の病害状態を画像から識別する深層学習手法を中心に、モデル、データセット、評価、展開を体系的にレビューしており、植物表現型計測手法のレビューに該当する。
abstractThis review presents a comprehensive analysis of recent developments in deep learning techniques for plant leaf disease identification.
Controlled environment agriculture (CEA) is essential for resilient crop production but faces high energy demands and operational costs. While high-throughput phenotyping (HTP) provides critical biological feedback to optimize these systems, conventional HTP platforms remain prohibitively expensive, infrastructure-heavy, and technically complex for widespread adoption. This review examines the emerging shift toward “affordable phenomics”, an approach integrating low-cost, open-source microcontrollers and Internet-of-Things (IoT) devices to continuously capture dynamic plant physiological data. By utilizing customizable tools such as modular chlorophyll fluorometers and wearable sensors, researchers and commercial growers can non-destructively monitor key traits like photosynthetic efficiency and water status in real time. Coupling these accessible sensing networks with artificial intelligence (AI)-driven analytics allows static environmental controls to transition into dynamic, plant-centered feedback systems. We synthesize recent advancements in affordable sensor technologies and review how temporal AI modeling extracts biologically meaningful features from longitudinal datasets to direct adaptive lighting and irrigation strategies. Furthermore, we critically assess current technological limitations, including sensor calibration, signal noise, cross-platform data standardization, and edge-versus-cloud computation tradeoffs. Finally, we highlight essential future research directions, particularly the development of robust edge-computing frameworks and predictive crop digital twins, demonstrating how affordable phenomics offers a scalable, data-driven pathway to improve resource-use efficiency in modern agriculture.
Why it matches plant phenotyping methods植物フェノタイピングの低コストセンサー、IoT、AI解析、校正・標準化などを中心に扱うレビューであり、単なる農業応用ではなく手法・プラットフォームの評価が主題である。
abstractThis review examines the emerging shift toward “affordable phenomics”, an approach integrating low-cost, open-source microcontrollers and Internet-of-Things (IoT) devices to continuously capture dynamic plant physiological data.
Abstract Detecting crop diseases early and responding promptly is vital for protecting agricultural productivity. It also helps maintain the quality and quantity of yields and reduces the risk of disease transmission to humans and livestock. Effective disease management is therefore critical to ensuring both global and local food security. However, traditional methods often based on visual inspection and delayed human judgment, are typically insufficient for identifying diseases at an early stage. Recent developments in Artificial Intelligence (AI) and the Internet of Things (IoT) offer new opportunities to address these challenges. By integrating IoT sensor networks with AI techniques such as machine learning and deep learning, it becomes possible to monitor plant health in real time and detect diseases with greater accuracy. This review explores the strengths and limitations of current AI-enabled IoT solutions in agriculture. It highlights how these systems leverage large-scale data and advanced image processing to outperform conventional methods in terms of speed, precision, and efficiency. Such improvements can significantly reduce crop losses and support more sustainable agricultural practices. Finally, the paper reviews key research trends, identifies current challenges, and outlines future directions in the field. It emphasizes the transformative potential of smart agriculture in advancing plant disease management and promoting environmentally responsible food production. This systematic review was conducted in strict accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines, synthesizing a final selection of 152 peer-reviewed papers. The overarching aim is to critically evaluate and map literature published between 2015 and 2026 using a systematic approach that addresses the integration of the IoT, AI, Machine Learning (ML), Deep Learning (DL), Convolutional Neural Networks (CNN), sensor technologies, and sustainable agricultural practices in the context of plant disease detection.
Why it matches plant phenotyping methods植物病害の症状・健康状態をAI、画像処理、IoTセンサーで検出する手法を主題とした系統的レビューであり、植物フェノタイピング手法のレビューに該当する。
titleA comprehensive review of artificial intelligence and Internet of Things integration based plant disease detection for sustainable agriculture
Salinity stress constrains horticultural production in protected cultivation, hydroponics, coastal agriculture and reclaimed-water irrigation. This critical narrative review and evidence map synthesizes a DOI-verified core corpus of 160 peer-reviewed journal articles to ask how artificial intelligence (AI) can support, rather than overstate, salinity-stress inference in horticultural crops. The evidence base is uneven: 22 retained records were AI-, sensing- or phenotyping-relevant, six treated ML, deep learning, edge intelligence or agentic AI as a central method, and four directly tested salinity- or water-stress AI/sensor phenotyping in a crop-relevant system. Among the six explicit-AI records, none externally validated a salinity-specific AI model; one distinguished salinity from drought, and none reported a prospective AI-guided intervention trial. Accordingly, this article is framed as a validation and reporting framework, not as a quantitative meta-analysis of model or intervention efficacy. Across the broader corpus, evidence for salinity tolerance centres on osmotic limitation, Na+ and Cl− toxicity, K+ retention, ROS regulation, photosynthetic protection, hormonal signalling, root hydraulics, rhizosphere processes and metabolic reprogramming. The review links these mechanisms to measurable traits and to claim-specific AI validation requirements. We propose a mechanism-to-AI map, a validation ladder, an intervention maturity framework and a reporting checklist. The conclusion is deliberately conservative: AI can improve salinity research when it is constrained by rigorous metadata, physiological grounding, external validation, stress-confusion testing and explicit uncertainty, but current evidence is insufficient to support autonomous, economically validated or field-ready AI-based salinity management.
Why it matches plant phenotyping methods植物の塩ストレス表現型推定に関するAI・センシング研究を体系的に整理し、検証枠組み、検証段階、報告チェックリストを提案する方法論的レビューであり、表現型計測・推定が中心です。
abstractThis critical narrative review and evidence map synthesizes a DOI-verified core corpus of 160 peer-reviewed journal articles to ask how artificial intelligence (AI) can support, rather than overstate, salinity-stress inference in horticultural crops.
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 15 Sept 2026
Plant phenomics has undergone rapid development over the past two decades, driven by advances in imaging, robotics, artificial intelligence and data analysis. Whilst field phenotyping is increasingly operational and scalable, the relevance of controlled-environment (CE) phenotyping is questioned because of concerns regarding the limited transferability of results to agricultural conditions. This Expert View first addresses the limitations and risks of using CE as surrogate of outdoor conditions. However, we argue that CE enables the disentangling of interacting environmental drivers allowing causal analysis of plant responses to multiple abiotic and biotic stresses. CE platforms also provide access to complex traits that are difficult or impossible to measure in the field whilst providing a robust framework in combination of field approaches to interpret and predict field performance. We further discuss contexts where CE remains indispensable, including quarantine and biosafety regulations together with emerging opportunities for agricultural innovation. Whilst limitations of CE systems are acknowledged, including issues of extrapolation, pot effects, environmental realism, and the indispensable need for rigorous envirotyping, we conclude that CE phenotyping should be regarded as an enabling analytical framework that complements and strengthens field phenomics for crop adaptation research under climate change.
Why it matches plant phenotyping methods管理環境フェノタイピングとフィールドフェノミクスの役割・限界・分析枠組みを論じる専門的レビューであり、植物表現型計測の方法論が中心です。
titleWhy bother with controlled-environment phenotyping when field phenomics is already up and running?
Traditional crop phenotyping relies heavily on static, discrete, point-in-time measurements, a "static snapshot" approach that inherently overlooks the continuous, dynamic response patterns of living crops under fluctuating environmental conditions. This paper proposes "Crop Phenotypic Rheology", a novel interdisciplinary theoretical framework designed to systematically integrate physical rheological concepts—such as stress, strain, viscoelasticity, creep, and stress relaxation—into the spatio-temporal continuous analysis of dynamic crop phenotypes. Crop phenotypic rheology conceptualizes the crop phenotype as a complex non-linear system that continuously undergoes deformation, recovery, or phase transformation in response to time, environmental stress (e.g., drought, heat, nutrient deficit, and mechanical wind stress), and resource availability. We elucidate three fundamental rheological modes—elastic, plastic, and viscoelastic modes—and formulate the environmental stress-phenotypic strain dynamic equations governing continuous phenotypic responses. Furthermore, we explore multi-scale integration mechanisms bridging micro-scale cellular rheology, meso-scale plant posture rheology, and macro-scale canopy rheology. By overcoming the fundamental limitations of static phenotyping, crop phenotypic rheology transitions crop phenotypic research from static structural measurements to a dynamic science focused on deciphering continuous response mechanisms, providing a transformative paradigm and theoretical support for precision breeding, abiotic stress screening, and smart agronomic management.
Why it matches plant phenotyping methods作物表現型を対象に、動的表現型を連続的に解析する新しい理論的フレームワークと動的方程式を提案しており、表現型計測・解析方法の開発が中心である。
abstractThis paper proposes "Crop Phenotypic Rheology", a novel interdisciplinary theoretical framework designed to systematically integrate physical rheological concepts—such as stress, strain, viscoelasticity, creep, and stress relaxation—into the spatio-temporal continuous analysis of dynamic crop phenotypes.
Traditional crop phenotyping relies heavily on static, discrete, point-in-time measurements, a "static snapshot" approach that inherently overlooks the continuous, dynamic response patterns of living crops under fluctuating environmental conditions. This paper proposes "Crop Phenotypic Rheology", a novel interdisciplinary theoretical framework designed to systematically integrate physical rheological concepts—such as stress, strain, viscoelasticity, creep, and stress relaxation—into the spatio-temporal continuous analysis of dynamic crop phenotypes. Crop phenotypic rheology conceptualizes the crop phenotype as a complex non-linear system that continuously undergoes deformation, recovery, or phase transformation in response to time, environmental stress (e.g., drought, heat, nutrient deficit, and mechanical wind stress), and resource availability. We elucidate three fundamental rheological modes—elastic, plastic, and viscoelastic modes—and formulate the environmental stress-phenotypic strain dynamic equations governing continuous phenotypic responses. Furthermore, we explore multi-scale integration mechanisms bridging micro-scale cellular rheology, meso-scale plant posture rheology, and macro-scale canopy rheology. By overcoming the fundamental limitations of static phenotyping, crop phenotypic rheology transitions crop phenotypic research from static structural measurements to a dynamic science focused on deciphering continuous response mechanisms, providing a transformative paradigm and theoretical support for precision breeding, abiotic stress screening, and smart agronomic management.
Why it matches plant phenotyping methods動的な作物表現型を連続的に解析する新しい理論的フェノタイピング枠組みを提案し、環境ストレス応答の数理モデルとマルチスケール統合を扱うため、方法論が中心である。
abstractThis paper proposes "Crop Phenotypic Rheology", a novel interdisciplinary theoretical framework designed to systematically integrate physical rheological concepts—such as stress, strain, viscoelasticity, creep, and stress relaxation—into the spatio-temporal continuous analysis of dynamic crop phenotypes.
Plant disease phenotyping underpins resistance breeding, epidemiology and crop-loss management, yet it remains a recognised bottleneck. This review asked whether the two metrics that dominate the discipline, the disease severity index (DSI) and the area under the disease progress curve (AUDPC), adequately represent disease as a temporally unfolding process, and what the evidence says about dynamic alternatives. Reporting followed PRISMA 2020 and the Synthesis Without Meta-analysis (SWiM) guideline. Web of Science Core Collection, Scopus, PubMed and a Google Scholar grey-literature sweep were searched for records published between January 2020 and December 2025, retrieving 1,192 records; 874 remained after de-duplication, 128 full texts were assessed and 31 studies met the eligibility criteria. Citation chasing added 24 foundational works, giving 55 included studies. Records were dual-screened (Cohen's kappa = 0.86), appraised with an adapted Mixed Methods Appraisal Tool, and synthesised using vote counting by direction of effect, an evidence map and structured cross-study comparison; meta-analysis was inappropriate because outcomes were not commensurable. Thirty studies (54.5%) represented disease at a single assessment and eight (14.5%) collapsed the epidemic into one integrated area, whereas only twelve (21.8%) retained the full trajectory. Across six outcome domains, all 29 study-level comparisons favoured the temporally richer method and none reported a null or negative result, an asymmetry indicating probable reporting bias. Certainty was high for visual-assessment findings, moderate for sensing and dynamic modelling, and low for field-realised genetic gain. The phenotyping bottleneck has migrated from data acquisition to data representation.
Why it matches plant phenotyping methods植物病害フェノタイピング手法の動的評価を中心に、既存指標と代替手法を体系的に比較した方法論レビューである。
titleA Systematic Review of Dynamic Disease Phenotyping in Plant Pathology
Main conclusion This review highlights that integrating physiological, molecular, imaging, and AI-based approaches enables early and reliable detection of graft incompatibility, improving rootstock-scion selection, orchard sustainability, fruit productivity, and long-term tree performance. One of the most serious problems in fruit growing is the breaking, weakening, or dying of the tree at the graft union, either within a short period of time or after 10-15 years. This condition is often triggered by environmental factors; however, it is certainly not solely caused by environmental conditions. This problem is defined as graft incompatibility. Graft incompatibility refers to the failure of successful anatomical and physiological integration between a rootstock and a scion, primarily due to biochemical, molecular, and genetic mismatches that impair vascular reconnection and long-term stability of the graft union. Graft incompatibility remains a significant constraint in fruit tree production, resulting in reduced longevity, yield, and quality of orchards. This review integrates recent advancements in physiological, molecular, and technological approaches for the early detection of graft incompatibility, with special emphasis on Prunus species such as sweet cherry. Physiological and biochemical markers, including phenolic accumulation, antioxidant enzyme activities, and isozyme patterns, serve as early indicators of incompatibility. At the molecular level, transcriptomic, metabolomic, and epigenetic analyses have revealed differentially expressed genes (DEGs) and post-translational modifications associated with stress signaling, vascular reconnection, and callus formation. Imaging-based non-destructive technologies such as micro-CT, MRI, terahertz, and hyperspectral imaging now allow real-time visualization of graft-union structures without damaging plant tissues. The integration of artificial intelligence and machine learning with multi-omics datasets and imaging tools offers unprecedented potential for predictive diagnosis and compatibility assessment. Collectively, these multidisciplinary advances are reshaping the detection and management of graft incompatibility, enabling faster, more reliable, and sustainable rootstock-scion selection in fruit tree breeding.
Why it matches plant phenotyping methods果樹の接ぎ木不親和性という植物状態の早期検出法を、画像・生理・分子・AI技術の観点から体系的にレビューしており、フェノタイピング手法が中心である。
abstractThis review integrates recent advancements in physiological, molecular, and technological approaches for the early detection of graft incompatibility
Abstract Plants live in a physical world governed by a multitude of mechanical processes which vary over time. The unique features of plant cells, which are turgor-inflated objects surrounded by the cell wall, present an intricate perception and response system for mechanical forces. A powerful tool to investigate how plants adapt and react to these cues is Atomic Force Microscopy (AFM), which can provide information about surface morphology as well as mechanical properties. In the context of cell wall biomechanics, there remains some controversy on appropriate AFM measurement practices and suitable use of common terminologies. Specifically, the interpretation of plant cell indentation curves and derivation of the wall elasticity modulus can be challenging and continues to spark debate. In this Expert View, we discuss recent advances of AFM in plant science as well as best practices for the use of AFM and considerations for data interpretation with a focus on mechanical probing by indentation.
Why it matches plant phenotyping methods植物細胞の表面形態と力学特性をAFMで測定・解釈する実践と標準化を扱うレビューであり、植物形質取得法が中心です。
abstractAtomic Force Microscopy (AFM), which can provide information about surface morphology as well as mechanical properties.
Climate change is intensifying abiotic stresses such as drought and heat, posing significant threats to global food security and the productivity of staple crops including maize (Zea mays L.) and rice (Oryza sativa L.). Conventional breeding approaches are often constrained by the complex genetic architecture of stress-adaptive traits and lengthy breeding cycles, highlighting the need for more efficient, data-driven strategies. This review summarizes recent advances in artificial intelligence (AI) and machine learning (ML) for genomic prediction, high-throughput phenotyping (HTP), and climate-adaptive breeding in maize and rice. We discuss the applications of machine learning architectures, including multilayer perceptron (MLP), convolutional neural networks (CNN), random forest (RF), deep neural networks (DNN), gradient boosting methods, and explainable artificial intelligence (XAI), in improving genomic selection and capturing complex genotype–environment interactions. The review further explores the integration of AI with HTP technologies, including autonomous robotic platforms, drones, hyperspectral imaging, and LiDAR, to enable rapid, accurate, and non-destructive phenotypic assessment. In addition, we examine the role of AI-driven predictive models in identifying stress-responsive genes, improving trait prediction, and accelerating the development of climate-resilient crop varieties. Current challenges, including data heterogeneity, computational demands, model interpretability, and biological validation, are also discussed alongside emerging solutions such as multi-view learning, transfer learning, and intelligent precision design breeding. Overall, the convergence of AI, ML, multi-omics, and advanced phenotyping technologies represents a transformative framework for next-generation crop improvement, offering new opportunities to accelerate sustainable breeding programs and strengthen global food security under changing climatic conditions.
Why it matches plant phenotyping methodsAI・MLを用いた高スループット植物表現型解析と、ロボット、ドローン、ハイパースペクトル、LiDARによる表現型評価を中心的にレビューしているため。
abstractThis review summarizes recent advances in artificial intelligence (AI) and machine learning (ML) for genomic prediction, high-throughput phenotyping (HTP), and climate-adaptive breeding in maize and rice.
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 5 Sept 2026
Drought is recognized as the primary abiotic stress limiting global crop productivity and poses a significant threat to food security. Consequently, the genetic improvement of drought tolerance has become a priority for modern plant breeding. Developing resilient cultivars requires a fundamental understanding of the physiological, biochemical, and molecular mechanisms that plants employ to counteract water deficits. This review provides a comprehensive analysis of drought-induced effects across various developmental stages in legumes, detailing the signaling networks that facilitate stress perception and response. Furthermore, we evaluate the experimental parameters and methodologies frequently used to assess drought tolerance, weighing their respective advantages and limitations. Finally, we analyze the revolutionary role that high-throughput phenotyping could play in stress assessment and precision breeding.
Why it matches plant phenotyping methodsマメ科植物の乾燥耐性評価に用いる実験パラメータ・方法論をレビューし、高スループット表現型解析の役割も論じるため、植物フェノタイピング方法のレビューが中心である。
abstractFurthermore, we evaluate the experimental parameters and methodologies frequently used to assess drought tolerance, weighing their respective advantages and limitations.
Remote sensing has become an important tool for crop monitoring and precision agriculture, yet its applications in sugar beet production remain fragmented across sensing platforms, target traits and modelling strategies. This review synthesises the development, current applications and future directions of remote sensing in sugar beet production, with particular attention to the transition from crop monitoring to precision management. A structured search was conducted in Scopus and the Web of Science Core Collection for publications from 2003 to 2025, and 181 relevant peer-reviewed articles were retained for thematic analysis. The literature shows a clear increase in sugar beet remote sensing studies, particularly after 2015, coinciding with the availability of Sentinel-2 imagery and, from 2016 onwards, the growing use of unmanned aerial vehicle-based sensing. It also indicates a gradual shift from crop mapping and canopy monitoring towards disease detection, weed mapping, yield prediction and management-oriented applications. Current studies demonstrate the value of satellite, unmanned aerial vehicle and proximal sensing for retrieving canopy traits, assessing biotic stresses, estimating root yield and supporting field-scale management. However, sugar beet presents specific challenges because its economic value depends not only on canopy development or root biomass, but also on sucrose concentration, recoverable sugar yield, and processing quality. These quality-related traits remain less studied and are difficult to infer directly from canopy observations. Modelling approaches have evolved from vegetation-index-based empirical models towards machine learning, deep learning, multi-temporal analysis, data fusion and crop model assimilation, but issues of model transferability, ground-truth availability and operational decision support remain unresolved. Future research should strengthen multi-source observations, external validation, quality-oriented prediction and decision-support workflows to promote robust, scalable and economically meaningful remote sensing applications in sugar beet production.
Why it matches plant phenotyping methodsサトウダイコンのリモートセンシングによるキャノピー形質、ストレス、根収量などの推定手法を体系的にレビューしており、センシング基盤とモデル化・検証課題が中心的に扱われている。
abstractThis review synthesises the development, current applications and future directions of remote sensing in sugar beet production, with particular attention to the transition from crop monitoring to precision management.
High-throughput phenotyping (HTP) has advanced rapidly in recent decades, driven by technological developments across research and agricultural frameworks. Despite its success in measuring traits, it remains underutilized in field crop breeding programs. While the most critical and labor-intensive selection is conducted on heterozygous single plants or small plots at early stages, most phenotyping research focuses on stable genotypes grown in large plots. Here, we reconsider how HTP can be effectively integrated into breeding by accounting for methodologies, scale-related constraints, and technological limitations. Our focus remains on self-pollinated field crops, the predominant global food source. In light of climate change and food security needs, improving the integration of breeding and phenomics can accelerate genetic and technological advances in developing elite varieties.
Why it matches plant phenotyping methods圃場作物育種における高スループット表現型解析の方法論、規模制約、技術的限界を中心に論じるレビューであり、植物フェノタイピング手法の統合が主題である。
abstractHere, we reconsider how HTP can be effectively integrated into breeding by accounting for methodologies, scale-related constraints, and technological limitations.
Plant leaf diseases cause severe losses in crop yields and qualities, and account for considerable volume of losses to the agricultural output globally. Recognition of plant disease early and rightly is crucial to disease treatment and to reduce loss to the crop and to maintain agricultural sustainability. Plant disease that occurs on the leaves has been traditionally detected by farmers and experts with naked eyes by checking its symptoms like discoloration, spots and lesions. However, the process requires time, labour, expertise and is subjective, which renders it unusable for large-scale implemented agriculture. Recent years have seen the promising use of Artificial Intelligence (AI) as a tool for automated plant disease identification. The extraction of manually-crafted features from photographs of plant leaves, such as colour, texture, and form, is at the heart of many Machine Learning (ML) approaches used for disease classification. While these ML models have shown acceptable performance, they require significant manual feature engineering and can be poor at operating in real-world settings and with voluminous data. To address these issues, Deep Learning (DL) algorithms have found extensive usage in the identification and categorisation of plant leaf diseases. The You Only Look Once (YOLO) family of detection of objects models is making waves in the DL object detection space thanks to its impressive dual-tasking capabilities: object identification and multiple illness categorisation in a single pass, all at lightning speed and with pinpoint accuracy. For real-time disease identification in precision agriculture, YOLO stands out as an end-to-end feature learning and object recognition method, set apart from typical ML approaches. Understanding the DL models suggested for plant leaf disease detection and classification using the YOLO principle is the primary goal of this survey. It also provides a comparative and performance analysis of these models by examining their techniques, merits, demerits, datasets used, and evaluation metrics.
Why it matches plant phenotyping methods植物葉の病徴を画像から認識・分類するYOLO系手法を主題とした比較・性能分析レビューであり、植物の病害状態を抽出するフェノタイピング手法が中心です。
abstractUnderstanding the DL models suggested for plant leaf disease detection and classification using the YOLO principle is the primary goal of this survey.
Early sex identification is essential for the propagation, cultivation, quality improvement, and germplasm management of dioecious horticultural plants and related functionally dioecious systems, particularly in perennial species with long juvenile phases. However, the reliability and transferability of sex-identification technologies depend strongly on the underlying sex-determining mechanism. Here, we synthesize recent advances in plant sex determination and diagnostic technologies, ranging from morphological and biochemical traits to molecular markers, high-throughput sequencing, structural-variant detection, and emerging non-invasive phenotyping. We propose that sex-identification strategies should be selected according to the biological target generated by each mechanism, including heteromorphic sex chromosomes, homomorphic sex-determining regions (SDRs), functional sex-determining genes, sex chromosome turnover, dosage-dependent systems, and environmentally labile sex expression. We further distinguish genetic, developmental, physiological, and phenotypic layers of plant sex, emphasizing that DNA markers and spectral phenotyping provide complementary information. Genomic markers and non-invasive phenotyping are expected to be consistent when genetic sex is stably expressed, but they may become inconsistent when sex expression is developmentally, hormonally, or environmentally modulated. While molecular markers remain the most reliable tools for confirmatory genotyping, Raman spectroscopy, surface-enhanced Raman scattering (SERS), hyperspectral imaging, and machine learning may serve as rapid prescreening tools in large breeding populations, although their application remains at the proof-of-concept stage. Finally, we present a mechanism-guided decision framework for integrating genomic markers and non-invasive phenotyping to support early sex screening, propagation planning, planting-material optimization, and marker-assisted improvement in dioecious horticultural plants.
Why it matches plant phenotyping methods植物の性表現型を対象に、非侵襲的・スペクトル表現型解析と遺伝マーカーを統合する診断技術および意思決定枠組みをレビューしており、表現型取得法が実質的な中心である。
titleIntegrating Genomic Markers and Non-Invasive Phenotyping for Early Sex Identification in Horticultural Plants: A Mechanism-Guided Framework
Abstract Purpose of Review Ground-based 3D point cloud technologies, including static terrestrial laser scanning (TLS), mobile laser scanning (MLS), and close-range photogrammetry, are increasingly used for estimation of aboveground vegetation biomass as they provide detailed structural representations across vegetation types; however, a comprehensive synthesis of how point-cloud data are translated into biomass estimates remains lacking. This review evaluates current approaches, performance patterns, and methodological gaps in biomass estimation using 3D ground-based point clouds. Recent Findings We systematically reviewed and analyzed 160 research articles (comprising 171 device-specific studies) published until the end of 2025 (first appearing in 2010). Research was dominated by tree-based applications (74%), with limited attention to shrubs, grasslands or crops. TLS was the prevailing acquisition technology (78%), although MLS adoption is growing. Biomass estimation primarily relied on allometric equations, volume-based reconstructions (e.g., quantitative structure models, voxelizations, convex hull), and parametric regression models. Reported model performance was generally high in tree- and shrub-based studies (median R 2 > 0.8), but more variable in non-woody vegetation types. Despite rapid advances in 3D sensing, point-cloud-native deep-learning approaches remain rarely implemented in biomass estimation workflows. Summary Ground-based 3D sensing is maturing technically, yet methodological heterogeneity persists. Many workflows still depend on destructive calibration data, semi-manual preprocessing, and non-standardized modelling strategies, limiting reproducibility and cross-study comparability. Multi-sensor integration is emerging but lacks consistent upscaling frameworks. Future research should expand coverage of underrepresented vegetation types, promote standardized and automated processing pipelines, and systematically evaluate point-cloud-native deep learning architectures, both for extracting structural proxies and for assessing their capacity to estimate biomass directly.
Why it matches plant phenotyping methods3Dセンシングによる植物バイオマス推定手法を体系的にレビューし、取得技術、推定ワークフロー、性能、再現性、標準化を評価しており、表現型測定法が中心である。
abstractThis review evaluates current approaches, performance patterns, and methodological gaps in biomass estimation using 3D ground-based point clouds.
Abstract Purpose Symptom-triggered crop protection acts only after damage is committed, and the intervention window has narrowed. This review reframes pre-symptomatic sensing from a detection problem into a closed decision loop, establishing the physiological lead time of a signal, set against its detection confidence and the latency of the response it can trigger, as the organizing principle for anticipatory, site-specific decision-making. Methods A systematic-narrative synthesis was conducted across major bibliographic databases through June 2026. Studies reporting pre-symptomatic capability under field or realistic conditions were retained and coded onto a coupled lead-time × confidence × actionability framework spanning sensing, inference, and actuation. Results Optical modalities were found to dominate the evidence base, while electrophysiological and volatile signals extended achievable lead time. Single modalities were insufficient to separate biotic from abiotic stress, motivating heterogeneous fusion. Edge inference and temporal onset forecasting remained immature, detection confidence was rarely quantified, and the sensing-to-actuation loop was seldom closed. Reported performance degraded sharply from laboratory to field, particularly in perennial and smallholder systems. Conclusions A unifying Pre-Symptomatic Crop Intelligence framework is proposed, governed by the principle that system value is bounded by the weakest of lead time, detection confidence, and response latency; priorities identified include lead-time-labeled benchmarks, uncertainty-aware inference, field-robust fusion, and economic evaluation for perennial crops.
Why it matches plant phenotyping methods植物の病害・ストレス状態を早期に推定するセンシング手法を体系的に整理し、検出リードタイム、信頼度、融合推論、ベンチマークを評価するレビューであり、植物状態の取得・推定方法が中心である。
abstractThis review reframes pre-symptomatic sensing from a detection problem into a closed decision loop
Plant diseases lead to substantial yield losses and pose a persistent threat to global food security, creating an urgent demand for high-throughput, accurate, scalable, and non-destructive disease monitoring approaches. Remote sensing has emerged as a powerful tool, yet progress in plant disease detection remains fragmented across various disciplines, tasks, sensing methods, and data modalities. This review introduces a hex- view perspective to synthesise remote sensing–based plant disease detection within a cohesive conceptual framework. Instead of treating sensing technologies, algorithms, and datasets independently, the hex-view incorporates six interconnected dimensions that jointly capture how biological processes, measurement scale, and data characteristics constrain disease detectability, including when detection is possible and how reliably it can be achieved. The hex-view framework comprises six interconnected dimensions and forms an integrated framework called BTSCAD: (1) Biology (B): Plant-pathogen interactions constituting the biological foundation of disease development and expression. (2) Task (T): The diverse disease detection tasks and their corresponding research objectives. (3) Sensor (S): The sensing modalities that define the data acquisition type and richness of captured information. (4) Condition (C): The environmental conditions, sensing platforms, and spatial scales that shape disease observations and bridge controlled experiments and real-world deployment across leaf, canopy, plot and regional scales. (5) Algorithm (A): The classical and state-of-the-art data analysis algorithms used to extract disease-related information from sensor data. (6) Dataset (D): The data sources that underpin model development, evaluation, and generalisability. The hex-view perspective provides a clear framework for interpreting previous research and identifying future research directions. This review lays a structured foundation for developing robust, interpretable, and transferable disease detection systems, supporting advancements in precision agriculture, high-throughput phenotyping, and sustainable crop production.
Why it matches plant phenotyping methods植物病害を対象としたリモートセンシングによる観察・検出法を、センサー、条件、アルゴリズム、データセットの観点から体系化する方法論レビューであり、植物状態の推定手法が中心である。
abstractThis review introduces a hex- view perspective to synthesise remote sensing–based plant disease detection within a cohesive conceptual framework.
Accurate yield prediction for major grain and oilseed crops, including soybean, corn, wheat, and rice, is essential for food-security assessment and precision field management. This study presents a structured integrative review of UAV-based crop yield prediction and follows PRISMA-guided procedures for literature search, screening, and evidence synthesis. Seventy peer-reviewed studies published between 2018 and 2025 were synthesized within a "Data-Ground Truth-Model-Decision" framework. Beyond summarizing UAV platforms, sensor configurations, feature-engineering strategies, and model architectures, the review explicitly distinguishes among microplot, field, and regional prediction scales, and evaluates the characteristics and limitations of yield-label acquisition methods, including manual harvest, plot-combine harvest, and combine yield-monitor data. Existing evidence indicates that the reliability of UAV-based yield prediction depends not only on optimal image acquisition windows, multi-source feature fusion, and model architecture, but also on scale-consistent yield labels, spatially aware validation strategies, and clearly defined model outputs, such as plot-level scalar yield, field-scale yield maps, and regional yield estimates. Major bottlenecks include scale mismatch between UAV imagery and yield labels, error propagation during yield-map generation, limited cross-year and cross-region transferability, weak causal interpretability, and difficulties in deploying models under complex operational field conditions. Future research should emphasize scale-explicit benchmark datasets, quality-controlled ground-truth yield acquisition, UAV-satellite-ground data fusion, spatiotemporal deep learning, and edge-cloud collaborative systems that can translate prediction outputs into agronomic decisions. This review provides a practical pathway for developing robust, interpretable, and deployable UAV-based yield prediction systems for major grain and oilseed crops.
Why it matches plant phenotyping methodsUAV画像から作物の収量という植物形質を推定する手法を中心に、プラットフォーム、特徴量、モデル、検証尺度、グラウンドトゥルースを体系的にレビューしているため、方法レビューとして収載。
abstractThis study presents a structured integrative review of UAV-based crop yield prediction and follows PRISMA-guided procedures for literature search, screening, and evidence synthesis.
India’s economy is primarily based on agriculture. Agriculture has significant contribution in nation’s GDP. Food security and employment significantly influenced by agriculture. However factors like uncertain weather conditions, poor quality of seeds and plant diseases impact on agriculture productivity. Computer vision and DL algorithms are most crucial components of precision agriculture. Early detection can improve decision making, maximize pesticide use, and preserve harvests. Using CNN architectures, segmentation-based approaches, handcrafted feature-based methods, and hybrid approaches incorporating Machine Learning and Deep Learning this study seek to provide review of recent publications from 2020 to 2026. The review was carried out using a variety of publications with different datasets, methodologies, and outcomes. The findings show that DL, especially CNN and transfer learning models, performed better than machine learning techniques. It points out several significant problems, such as dataset imbalance, insufficient generalization, computing inefficiency, and a dearth of real-world data. Future research topics are also suggested which includes IoT-driven real-time solutions, lightweight architecture, domain adaption, and multimodal imaging. This review aims to develop plant disease detection technologies that are more dependable, scalable, and field deployable.
Why it matches plant phenotyping methods植物葉の病徴を画像から検出する機械学習・深層学習手法をレビューおよび実験的に扱っており、植物フェノタイピング手法が中心である。
titlePlant Leaf Disease Detection Using Machine Learning and Deep Learning: A Review and Experimental Study
Artificial intelligence (AI) has emerged as a transformative tool for plant health monitoring, offering new opportunities for scalable, timely, and data-driven pest and disease management in agriculture. This review provides a comprehensive synthesis of AI-based methods for pest and plant disease detection, systematically organizing existing literature across sensing modalities, learning paradigms, and deployment scales. We distinguish between population-level pest monitoring, plant-centric visual inspection, and field-scale surveillance, as well as between post-symptomatic disease recognition and pre-symptomatic detection enabled by spectral imaging technologies. Beyond summarizing recent advances, this work places strong emphasis on critical analysis, discussing fundamental limitations related to data scarcity, domain shift, generalization under field conditions, and the challenge of disentangling biotic from abiotic stress factors. The review further examines the distinction between correlation-driven AI predictions and causal disease understanding, positioning AI as a complementary decision-support tool alongside established diagnostic methods. Building on these insights, we outline key future research directions, including multimodal sensor fusion, explainable and trustworthy AI, edge-based deployment for real-time monitoring, and the development of foundation models for unified agricultural intelligence. This review aims to serve as both an accessible entry point and a critical reference for advancing AI-driven plant health management.
Why it matches plant phenotyping methods植物の病害・害虫状態を画像・スペクトルなどで検出するAI手法を対象としたレビューであり、植物状態の取得・推定手法が中心である。
titleA Review on Artificial Intelligence Methods for Plant Disease and Pest Detection
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 15 Sept 2026
Field / plotCell / cellular structureWhole plant / canopy / plot / fieldGrowth / development / phenologyStress response / tolerance
Abiotic stress tolerance has been significantly weakened in modern crops during the domestication process. Regaining tolerance has become a critical task in light of current climate trends and their impact on global food security. Abiotic stress tolerance is an extremely complex trait and is conferred at various levels of plant functional organization and developmental stages, with regulatory mechanisms operating across multiple scales, from individual cells to tissues and the entire plant. The emergence of advanced molecular tools such as single-cell RNA sequencing and spatial omics technologies has revolutionized the field, advancing our understanding of plant responses to hostile environments. However, the implementation of this knowledge in crop breeding programmes is handicapped by the lack of appropriate phenotyping platforms. Here, we argue that current phenotyping methods may be excellent tools for functional validation of previously discovered traits but have limited predictive value in stress biology. We also propose that bridging the mismatch between omics technologies and phenotyping is the only way to account for cell-specific operation of key genes conferring stress tolerance and implementing them in breeding programmes. Some practical examples using cell-based phenotyping tools such as fluorescence dyes or electrophysiological methods are given, and current limitations and prospects of cell-based phenotyping are discussed.
Why it matches plant phenotyping methods細胞ベースの植物フェノタイピング手法を扱い、蛍光色素や電気生理学的方法の例、限界、展望を論じる方法論レビューである。
abstractSome practical examples using cell-based phenotyping tools such as fluorescence dyes or electrophysiological methods are given, and current limitations and prospects of cell-based phenotyping are discussed.
(L.) Merrill) is a highly important crop widely used for food, edible oil, animal feed, and microbial fermentation products. Traditional phenotypic measurement methods are often time-consuming, labor-intensive, destructive to plants, and prone to human error. High-Throughput Phenotyping (HTP) enables precise assessment of multiple soybean phenotypic features, including morphology, physiology, diseases, pests, and agronomic traits. Artificial Intelligence (AI) is a research field dedicated to developing algorithms for multiple tasks. This review highlights the application of HTP and AI in soybean breeding programs. We discuss the challenges of implementing HTP in soybean breeding and focus on the potential and limitations of Deep Learning (DL) to support soybean breeding goals. We demonstrate the application of HTP to key soybean traits, several HTP platforms, as well as DL applications across different datasets and strategies for developing large foundation models. While integrating AI into soybean breeding programs remains a challenge, leveraging HTP data and Large Language Models (LLMs) could reshape soybean breeding.
Why it matches plant phenotyping methods大豆育種におけるHTPとAIの応用、形質評価、プラットフォーム、データセットおよび深層学習を中心に扱うフェノタイピング手法レビューであり、方法論が中心的です。
abstractThis review highlights the application of HTP and AI in soybean breeding programs.
Posidonia oceanica meadows form one of the most important coastal habitats in the Mediterranean Sea, providing key ecosystem services including carbon sequestration, sediment stabilization, biodiversity support, and coastal protection. Despite their ecological importance, these meadows have declined in many parts of the Mediterranean over recent decades due to coastal development, pollution, anchoring activities, and climate-related pressures. Detecting such changes requires reliable and comparable monitoring data. Among the available approaches, quadrat-based field surveys remain one of the most widely used methods for describing meadow structure through indicators such as shoot density, percent cover, and leaf biometry. In practice, however, these methods are applied in different ways across monitoring programs. Variations in quadrat size, sampling design, replication strategies, and measurement protocols often make it difficult to compare results among studies or regions. This review examines the methodological foundations of quadrat-based monitoring of P. oceanica and discusses the main sources of bias that may influence monitoring outcomes. A structured literature search identified five recurrent sources of methodological bias across the studies reviewed: sampling design, quadrat size effects, observer variability, depth gradients, and seasonal variability. These factors can affect both the precision of measurements and the interpretation of ecological trends. The review also evaluates commonly used monitoring designs and ecological indices and considers recent technological developments such as photogrammetry, remote sensing, and machine-learning-based image analysis that may help reduce some methodological limitations. Drawing on this synthesis, a conceptual framework is proposed linking sources of methodological bias with their potential consequences for monitoring outcomes, and practical recommendations are outlined to improve methodological consistency and enhance the comparability of P. oceanica monitoring across the Mediterranean basin.
Why it matches plant phenotyping methodsPosidonia oceanicaの構造形質を測定する方形区モニタリング手法のバイアスと標準化を中心に扱う方法論レビューであり、植物フェノタイピング手法が中心的です。
abstractThis review examines the methodological foundations of quadrat-based monitoring of P. oceanica and discusses the main sources of bias that may influence monitoring outcomes.
Abstract Faba bean ( Vicia faba L.) is a widely cultivated legume in temperate regions, valued for human consumption, animal feed, hay production, and as a cover crop. Improving faba bean productivity requires accurate characterization of morphological and physiological traits that govern crop performance and yield. Although conventional phenotyping methods are available, they are often constrained by high cost, limited accuracy, and insufficient spatial and temporal coverage. In recent years, high-throughput phenotyping (HTP) approaches have shown potential to overcome these limitations. HTP integrates sensors, unoccupied aerial and ground vehicles, and imaging systems to enable rapid, and non-destructive monitoring of crop traits at high spatiotemporal resolution. Despite increasing adoption of HTP, no study has comprehensively compared and synthesized these methods for faba beans, therefore is the goal of this study with emphasis on advanced sensing and data analytics including machine learning (ML) and deep learning (DL). A systematic evaluation of 24 peer-reviewed articles from an initial pool of 381 publications between 2015 and 2025, identified research trends, performance benchmarks, and integration challenges with HTP-based faba bean characterization. Substantial increase in faba bean HTP studies has been noted after 2021, with ML approaches dominating current applications (37.5%). Most studies have relied on small datasets, single-season experiments, and limited environmental variability, restricting model robustness and scalability. Such limitations, research gaps, and future directions are also outlined to support reliable, and scalable phenotyping for improved faba bean production.
Why it matches plant phenotyping methodsソラマメの高スループット表現型解析手法を体系的に比較・評価し、センサー、画像、UAV・地上車両、データ解析の性能と課題を扱う方法論レビューである。
titleHigh-Throughput Phenotyping of Faba Bean Crop Using Remote Sensing Technologies and Data Analytics: A Systematic Assessment of Status and Trends Over Past Decade
Accurate perception and 3D reconstruction of fruit tree branch structures are fundamental to smart orchard development, with broad applications in intelligent harvesting, crop phenotyping, and precision management. However, the slender and highly branched morphology, multi-scale distribution, weak surface texture, and severe occlusion inherent to fruit tree branches pose substantial challenges to high-fidelity modeling. This paper systematically reviews advances in branch feature extraction and 3D reconstruction for fruit tree canopies. A structured literature search was conducted using the Web of Science, Scopus, and Google Scholar databases, with search terms including “fruit tree branch”, “point cloud reconstruction”, “3D canopy modeling”, “branch feature extraction”, and “agricultural robotics”. Studies published between 2000 and 2025 were considered, with inclusion criteria requiring relevance to branch structure perception, reconstruction accuracy, or orchard application; non-peer-reviewed sources and studies lacking quantitative evaluation were excluded. We trace the evolution of feature extraction from classical 2D image processing and geometric fitting, through point cloud segmentation and skeleton extraction, to modern deep learning approaches and multimodal perception techniques. For 3D reconstruction, we compare active and passive sensing strategies alongside both explicit and implicit scene representation methods, discussing their respective strengths and applicable scenarios. A five-dimensional evaluation framework is also proposed, encompassing geometric accuracy, structural consistency, feature stability, computational efficiency, and generalization capability. Finally, we identify key bottlenecks in fine-grained structure recovery, occlusion handling, and cross-scene generalization, and highlight future directions in structural prior integration, multimodal collaborative modeling, and lightweight neural representations—offering a structured reference for advancing 3D perception research in smart orchards.
Why it matches plant phenotyping methods果樹の枝構造の特徴抽出と3D再構成を対象とする、植物形態計測・表現型取得手法のレビューであり、方法論が中心です。
abstractThis paper systematically reviews advances in branch feature extraction and 3D reconstruction for fruit tree canopies.
Field / plotMultimodalLiDAR / point cloudMultispectral / hyperspectralWhole plant / canopy / plot / fieldArchitecture / morphology / geometry
Crop phenotyping serves as a fundamental basis for crop breeding, precision cultivation, and smart agriculture. In recent years, it has evolved toward multi-modal integration and multi-scale coordination. This paper analysed indoor and outdoor phenotyping platforms across diverse application scenarios, and reviewed sensing technologies including RGB imaging, multi-spectral imaging, hyperspectral imaging, thermal imaging, fluorescence imaging, LiDAR, and nuclear magnetic resonance (NMR). The applications of these technologies were summarized in capturing crop morphological traits, physiological status and biochemical components. The phenotyping acquisition methods and intelligent analytical techniques were also analyzed at different scales such as plant cells, tissues and organs, individual plants, population plot and field. Additionally, the advancements were explored in high-throughput phenotyping technologies and their integration with crop gene function analysis, providing a reference for future phenotyping research.
Why it matches plant phenotyping methods作物表現型センシング技術・装置、取得法、解析技術、プラットフォームを主題とする包括的レビューであり、表現型手法が中心です。
abstractThis paper analysed indoor and outdoor phenotyping platforms across diverse application scenarios, and reviewed sensing technologies including RGB imaging, multi-spectral imaging, hyperspectral imaging, thermal imaging, fluorescence imaging, LiDAR, and nuclear magnetic resonance (NMR).
Plant diseases remain one of the most persistent and economically damaging threats to global food security, with yield losses across major staple crops running into the tens of billions of dollars each year. The rise of artificial intelligence, and convolutional neural networks (CNNs) in particular, has opened genuinely new possibilities for detecting plant disease early, accurately, and at scale. This review critically examines the state of CNN-based plant disease detection within the wider context of smart agriculture and agribusiness sustainability. Drawing on peer-reviewed literature published between January 2016 to February 2026, the paper traces the evolution of CNN architectures, training methods, and benchmark performance across a wide range of crops and disease categories. Particular attention is given to transfer learning, data augmentation, and lightweight architecture design as responses to the recurring problem of limited annotated training data. The paper also considers how CNNs are being combined with complementary technologies, including the Internet of Things, unmanned aerial vehicles, and edge computing, and what this means for deployment in real farming conditions. Economic and sustainability dimensions are explored throughout, with attention to whether the gains from AI adoption are likely to reach smallholder farmers or remain concentrated among larger, better-resourced agribusinesses. Despite genuinely impressive results under controlled benchmark conditions, several barriers to field deployment persist: dataset bias, poor generalisation in complex agricultural environments, computational constraints, and a continuing shortfall in model interpretability. The review closes by identifying priority research directions, including cross-domain transfer learning, explainable AI, the development of field-representative datasets, and participatory approaches to tool design. Taken together, the evidence suggests that CNN-based disease detection holds real promise for agribusiness sustainability, but realising that promise will depend on sustained interdisciplinary collaboration and deployment strategies that are sensitive to local context rather than assuming one-size-fits-all solutions.
Why it matches plant phenotyping methods植物病害を画像から検出・評価するCNN手法を中心に、モデル、学習法、ベンチマーク、汎化性、データセット、実運用上の課題をレビューしており、植物状態の画像ベース推定に関する方法論的レビューである。
abstractThis review critically examines the state of CNN-based plant disease detection within the wider context of smart agriculture and agribusiness sustainability.
SUMMARY Plants display complex structural tissue arrangements and cell shapes that are intimately related to their functionality and whose precise geometry influences the metabolic and physical processes performed by different organs. Analyzing these structure–function relationships requires accurate information on the complex 3D anatomy and its changes over time at meaningful spatial resolution. A non‐invasive approach, micro‐CT imaging, can produce such 3D or 4D datasets and can be leveraged for finite element (FE) simulations of mechanical and physical processes. This combination of techniques has been employed to study biomechanical properties, gaseous diffusion, light propagation, hydraulics, and thermodynamic processes in plant organs. A deep understanding of structure–function relationships also paves the way to design bio‐inspired structures using plant anatomy as a reference. Here, we illustrate how the combination of micro‐CT‐based imaging and FE modeling can be leveraged in plant science for advanced investigation of structure–function relationships.
Why it matches plant phenotyping methods植物器官の3D/4D構造をmicro-CTで取得し、有限要素モデルと組み合わせて構造・機能特性を解析する方法を中心に扱うレビューであり、植物フェノタイピング手法に該当する。
titleQuantification of plant structure–function relationships through micro‐ CT imaging‐based finite element modeling
Accurate yield estimation and crop load monitoring are essential for precision orchard management, supporting targeted fertilization, pruning, thinning, harvest planning, and marketing decisions. However, reliable in-situ monitoring remains challenging because commercial orchards are characterized by severe canopy occlusion, fruit overlap, heterogeneous tree architecture, variable illumination, and complex backgrounds. This review synthesizes advances in multi-modal sensing and deep learning for orchard yield estimation, breaking down the paradigm into intermediate fruit-counting or crop-load monitoring steps and supplementary spectral quality-assessment dimensions. First, yield-related indicators are summarized, including direct phenotypic traits such as fruit number, size, volume, and spatial distribution, as well as indirect structural and physiological proxies such as canopy volume, vegetation indices, flowering intensity, and spectral maturity attributes. Second, representative sensing devices and carrying platforms are reviewed, including red-green-blue (RGB) cameras, red-green-blue-depth (RGB-D) sensors, light detection and ranging (LiDAR), hyperspectral and multispectral systems, unmanned ground vehicles (UGVs), and unmanned aerial vehicles (UAVs). Third, the evolution of estimation methods is discussed, from traditional image processing and machine learning to object detection, instance segmentation, multi-object tracking, point-cloud analysis, remote-sensing regression, and multi-modal fusion. The review shows that no single sensor or algorithm can satisfy all orchard monitoring requirements. Ground-based vision and depth sensing are more suitable for fine-scale fruit counting and sizing, whereas UAV and spectral sensing provide advantages for regional yield mapping and quality-enhanced assessment. Future research should emphasize occlusion-aware perception, robust cross-environment generalization, lightweight edge deployment, standardized benchmarks, and integrated quantity-quality monitoring frameworks for actionable crop load management.
Why it matches plant phenotyping methods果実数・サイズ・体積・空間分布などの植物形質を対象に、センシング機器と画像解析・深層学習による収量推定法を体系的にレビューしており、フェノタイピング手法が中心である。
abstractThis review synthesizes advances in multi-modal sensing and deep learning for orchard yield estimation, breaking down the paradigm into intermediate fruit-counting or crop-load monitoring steps and supplementary spectral quality-assessment dimensions.
Plant electrophysiology is undergoing a profound paradigm shift from traditional phenomenological observation to systemic signal decoding, with mature methodologies from computational neuroscience and brain-computer interface technologies providing critical theoretical and engineering support for this interdisciplinary evolution. This review first systematically summarizes the evolution of flexible wearable electrodes and ultra-high impedance amplification hardware systems tailored to the ultra-slow signal dynamics and continuous morphological growth characteristics of plants. Second, we discuss the application pathways of introducing standardized sequential evoked paradigms from neuroscience—such as steady-state visual evoked potentials and event-related potentials—into the plant domain. This aims to replace traditional destructive stimuli with non-invasive, reproducible rhythmic stimulation to acquire data with high signal-to-noise ratios. In the dimension of data analysis, we explore modeling strategies that incorporate physics-informed neural networks and multi-modal heterogeneous sensor fusion technologies under the constraint of sample scarcity, aiming to resolve the equifinality problem inherent in single-modality electrical signal decoding. Building upon this decoding foundation, this paper proposes the construction of a bidirectional Plant-Computer Interface architecture, exploring the engineering feasibility of utilizing the plant itself as an active sensory node to directly drive closed-loop regulation within agricultural environments. Establishing cross-species standardized open-source datasets and unified hardware/software testing benchmarks will be the core driving force in overcoming current data fragmentation. Ultimately, the deep integration of multidisciplinary approaches will lay a rigorous scientific foundation for precision agricultural resource management and the development of next-generation bio-inspired intelligent hardware.
Why it matches plant phenotyping methods植物の電気生理シグナル取得用センサー、刺激、デコード、マルチモーダル解析、データセットとベンチマークを体系的に扱うレビューであり、植物状態の計測・推定手法が中心です。
abstractThis review first systematically summarizes the evolution of flexible wearable electrodes and ultra-high impedance amplification hardware systems tailored to the ultra-slow signal dynamics and continuous morphological growth characteristics of plants.
The convergence of multi-omics profiling, high-throughput phenotyping (HTP), and artificial intelligence (AI) has expanded our ability to characterize crop stress responses at unprecedented resolution (Danilevicz et al., 2025;Pacheco-Ruiz et al., 2025;Tsega and Mullualem, 2026). Researchers can now routinely identify candidate genes, construct gene regulatory networks, and train machine learning models to predict terminal phenotypes, such as yield under drought, biomass under salinity, and disease severity scores. Yet the practical impact remains limited: delivering a single improved crop variety to market still requires approximately one decade and more than 14 million euros, a timeline that has barely changed in 30 years despite the exponential growth in data generation (Pacheco-Ruiz et al., 2025). We argue that a fundamental cause of this translational gap is what we call the temporal poverty of current GP: models often predict static endpoints rather than the dynamic processes that determine them.Classical GP models, including multi-omics-informed variants, are overwhelmingly trained on traits measured at single time points, such as final yield or end-of-season stress scores. However, stress tolerance is inherently temporal, reflecting a cascade of physiological decisions whose sequence and timing ultimately determine field survival: when to close stomata, how rapidly to accumulate osmolytes, and whether to prioritize root extension or shoot preservation. A model that predicts terminal drought tolerance without distinguishing whether it arises from early water conservation, sustained photosynthesis, or post-stress recovery offers limited support for rational gene stacking or knowledge transfer across environments and crops (Danilevicz et al., 2025). Based on these observations, we hypothesize that making the dynamic trajectories of intermediate physiological traits the direct targets of GP, rather than treating them as auxiliary variables, will substantially improve prediction accuracy, mechanistic interpretability, and the rate of genetic gain for stress resilience in crop breeding.To bridge this temporal gap, we propose a dynamic explainable genomic prediction framework centered on intermediate physiological trajectories (Figure 1). The framework integrates dynamic phenotyping, environmental information, and mechanistic multi-omics anchors to support trajectory-aware prediction and climate-resilient breeding.Conventional genomic prediction focuses on static endpoint prediction, whereas the proposed framework targets dynamic intermediate phenotypes and integrates environmental and multi-omics information to enable trajectory-aware, interpretable prediction for climate-resilient crop breeding.This reframing is becoming increasingly feasible. The recent dynamicGP model combines GP with dynamic mode decomposition (DMD) to predict full temporal trajectories of multiple morphometric and colorimetric traits scored by HTP in maize and Arabidopsis thaliana (Hobby et al., 2025). DynamicGP was also shown to predict traits at time points beyond the training period. It was the only model tested with this capability and showed superior longitudinal accuracy in capturing developmental dynamics (Hobby et al., 2026). The model further revealed that traits with more temporally stable heritability can be predicted with higher accuracy, providing practical guidance on which dynamic intermediates to prioritize (Hobby et al., 2025).Mechanistic modeling offers a complementary line of evidence: computational models of grass inflorescence morphodynamics recently guided the discovery of the duo2 mutant allele in wheat, which accelerates developmental progression and improved yield by 7-11% under field conditions (Wang et al., 2026b). These two independent advances, one data-driven and one mechanism-driven, converge on the same insight: incorporating time as a central dimension in prediction can provide predictive power and mechanistic understanding that are inaccessible to static models, thereby connecting prediction with actionable breeding decisions.A realistic view of current data availability shapes this strategy. The current and near-future foundation for dynamic intermediate phenotype prediction is largely HTP.The marginal cost of repeated phenotyping with automated platforms, UAVs, and low-cost sensors has decreased substantially, and public time-series datasets covering wheat, sorghum (LeBauer et al., 2020), soybean, and several other crops are rapidly expanding. This supports a pragmatic, asymmetric integration strategy: HTP provides the dense temporal skeleton of dynamic trait trajectories, while multi-omics is deployed selectively at a small number of mechanistically critical time windows, such as the onset of stress signaling, the transition from alarm to acclimation, or the peak of a known physiological trade-off. These sparse but information-rich omics snapshots serve as "explainability anchors." When explainable AI approaches are used to link these molecular profiles to parameterized dynamic modes extracted from HTP, the resulting model can reveal which genes, transcripts, or metabolites modulate specific phases of the dynamic response and when. For instance, SHAP-based interpretation of Random Forest models applied to soybean multi-omics data revealed that the isoflavone derivative daidzin and specific drought-tolerant microbes are major contributors to phenotypic variation under drought stress, while SHAP-based interaction networks uncovered cross-omics links between metabolites and microbial taxa (Yoshioka et al., 2026). Extracting biologically meaningful signals from such comparisons requires specialized computational tools. The MODAS2 pipeline, for example, uses contrastive principal component analysis, a machine learning algorithm, to disentangle stress-responsive molecular QTLs from background genetic effects in multi-omics data, enabling the identification of salt-responsive genetic variants in maize (Liu et al., 2025). Such tools are essential for implementing the explainability-anchor strategy at the stress-transition windows targeted by our framework.Advocating for dynamic intermediate phenotypes as prediction targets does not mean abandoning terminal agronomic traits. The two approaches serve complementary roles at different stages of the breeding pipeline. In early-generation selection, when thousands of lines must be evaluated and resources for multi-environment yield trials are limited, dynamic intermediates, which are often measurable earlier, at lower cost per data point, and with higher heritability, can help enrich populations for stress-resilient candidates (Melsen et al., 2025). In later-stage trials, direct prediction of yield under target stress environments remains indispensable for final variety release decisions. In practice, the central question is not which target is superior in isolation, but whether their combined use can accelerate genetic gain for stress tolerance.Dynamic intermediate phenotypes can contribute to genetic gain through three main routes. First, many dynamic intermediates show higher heritability and earlier measurability than terminal yield under stress, enabling more accurate early-generation selection and shorter breeding cycles. Second, a dynamic physiological module, such as rapid osmotic adjustment within 48 hours of soil drying, can become a reusable building block once it has been genetically dissected and validated. Such modules could then be stacked, introgressed, or transferred across genetic backgrounds and crop species. Third, selecting on the shape of a response curve rather than a single terminal value can reduce environmental noise, because temporal patterns are often more genetically determined than absolute end-point values (Hobby et al., 2025). This framework is also inherently cross-crop: a conserved physiological module such as "stomatal response speed to soil drying" is unlikely to be restricted to a single species. Orthologous genes and conserved pathways can inform candidate selection in legumes, vegetables, and under-researched crops, extending advanced breeding methodologies beyond the major cereals (Kundu and Tanti, 2026;Wang et al., 2026b).The dynamic GP framework we advocate remains incomplete without explicit environmental inputs. At present, many AI-driven prediction models treat the environment as a categorical label or a set of static summary statistics. This approach can conflate genetic and environmental effects and limit performance forecasting across mega-environments or novel climatic scenarios. To support the development of climate-resilient varieties, models should instead incorporate environmental data as an explicit, dynamic data layer, including time series of temperature, soil moisture, and vapor pressure deficit, that co-determines the trajectory of intermediate phenotypes.Recent advances suggest that this is increasingly feasible. Enviromics and reaction-norm approaches that incorporate high-dimensional environmental covariates through penalized regression can now approach the accuracy of deep learning while retaining interpretability and an explicit description of genotype-by-environment interactions (Avagyan et al., 2025). In parallel, hybrid frameworks that couple crop growth models with whole-genome prediction can link genetic, environmental, and management inputs to dynamic physiological outputs (Laurent et al., 2025). Building on these developments, embedding environmental time series into the temporal kernels of dynamic models such as dynamicGP could, in principle, enable prospective, environment-aware forecasting of genotype-specific response curves. This would shift selection from retrospective mega-environment classification toward forward-looking prediction across single or multiple target mega-environments. However, robust extrapolation to untested environments and stress combinations remains a key open challenge. Careful envirotyping and cross-environment validation will therefore be essential before such models can guide variety deployment decisions in practice.The framework proposed here has important implications for future crop production.By shifting the breeding target from terminal yield to the temporal architecture of stress responses, breeders could develop selection strategies that are both physiologically informed and operationally efficient. Dynamic intermediate phenotypes, captured through increasingly affordable HTP platforms, can serve as early indicators of resilience, allowing breeders to discard susceptible lines long before harvest. This could shorten the breeding cycle, especially when combined with genomic selection and speed breeding, while also enabling the deliberate assembly of stress-resilience modules that are robust across environments. Empirical evidence already shows that integrating HTP-derived spectral data with genomic information can substantially improve cross-environment prediction accuracy (McBreen et al., 2025;Nannuru et al., 2025). As climate variability intensifies, the ability to design varieties with predictable temporal behavior under drought, heat, or salinity will become increasingly important for enhancing yield stability and food security.Challenges remain. Dynamic GP models have yet to be systematically validated across radically different environments, and their ability to predict trait dynamics under novel stress combinations remains unproven. Data from controlled HTP platforms must also be calibrated against field conditions. In addition, the integration of heterogeneous multi-omics datasets creates persistent bottlenecks that constrain practical application beyond proof-of-concept studies (Pacheco-Ruiz et al., 2025;Tsega and Mullualem, 2026). Multi-omics time series, even at the sparse sampling density we advocate, remain limited by high technology costs and scalability challenges that restrict their routine deployment in breeding programs (Syeda, 2025;Younas et al., 2025). However, pilot-scale time-series multi-omics studies demonstrate both feasibility and value. For example, transcriptomic and ionomic profiling of Sorghum bicolor across a 21-day micronutrient stress time course revealed iron-zinc regulatory crosstalk and conserved gene regulatory networks (Mishra et al., 2025), while high-resolution time-series transcriptomic and metabolomic profiling of salt-tolerant and salt-sensitive maize inbred lines identified the hub gene ZmGLN2 and constructed dynamic regulatory networks governing salt-responsive metabolite biosynthesis (Zhang et al., 2025). Furthermore, the MODAS2 pipeline, which uses contrastive principal component analysis to extract stress-responsive signals from multi-omics comparisons, illustrates that the computational methods needed to integrate heterogeneous omics layers are already under active development (Liu et al., 2025).Equally important is the ability of AI models to capture the non-linear genetic interactions that underpin complex stress responses. Linear mixed models, the backbone of classical GP, primarily model additive effects and therefore have limited capacity to capture epistasis, gene-by-environment interactions, and threshold-type responses (Wang et al., 2026a). In contrast, deep learning architectures can learn hierarchical, non-linear mappings from high-dimensional input spaces. When applied to dynamic intermediate phenotypes, these models could learn not only which genomic regions influence the temporal shape of a trait, but also how those regions interact with each other and with environmental triggers over time. For example, convolutional neural networks have outperformed classical methods such as LASSO and Bayes C in predicting integrative traits, with the combination of CNNs and crop model parameters further enhancing prediction accuracy (Larue et al., 2024). Fully harnessing non-linear interactions for dynamic trait prediction will likely require hybrid approaches that embed mechanistic constraints into flexible AI architectures, ensuring that predictions remain both powerful and biologically plausible.As outlined in the preceding section, integrating environmental time series into dynamic GP models remains a frontier, but the computational tools and conceptual frameworks are now within reach. The integration of environmental data with multiple omics layers for genotype-by-environment prediction has been identified as a major emerging frontier, although it is currently addressed in fewer than 20% of studies (Tsega and Mullualem, 2026). This gap underscores the urgency of the framework we advocate. These are not sequential prerequisites, but parallel investments that reinforce one another. We therefore call on the crop science community to: (i) prioritize the generation of time-series phenotypic data in multi-environment stress trials, leveraging increasingly affordable HTP platforms; (ii) adopt explainable AI as standard practice, not merely reporting prediction accuracy but also elucidating which features drive predictions, when, and through which physiological mechanisms (Danilevicz et al., 2025); and (iii) develop selection indices that explicitly reward favorable dynamic trajectories alongside terminal trait values.Multi-omics and AI should not merely describe how stress resistance appears at harvest; they must reveal how it unfolds over time and how it can be rationally assembled. Bridging this temporal gap will connect current data abundance with the practical goal of delivering climate-resilient crops to farmers' fields.In
Why it matches plant phenotyping methods動的HTP phenotypingと軌跡予測を中核とする概念・方法論的枠組みを提案し、既存モデル、環境データ統合、検証課題を体系的に論じているため。
abstractThe recent dynamicGP model combines GP with dynamic mode decomposition (DMD) to predict full temporal trajectories of multiple morphometric and colorimetric traits scored by HTP in maize and Arabidopsis thaliana
Multispectral / hyperspectralWhole plant / canopy / plot / field
In recent years, hyperspectral imaging has been widely adopted in agriculture and plant phenotyping, while its application in forestry has been increasing. From that point onward, hyperspectral imaging has become a valuable tool for plant phenotyping, enabling the assessment of a broad range of plant traits. Given that seedlings of forest trees are one of the most widely used types of forest planting stock, advancements in hyperspectral technology have created new possibilities for improving seedling quality assessment. High-quality forest seedlings are important for the successful establishment of forest stands, especially after outplanting within restoration initiatives. Even though hyperspectral imaging brings numerous advantages, continued technological improvements are necessary to address its several limitations and challenges. Despite its widespread use in agricultural phenotyping, applications in forest nursery production remain limited. Therefore, this review focuses on research involving hyperspectral imaging in forest seedling production and its potential for assessing seedling quality parameters.
Why it matches plant phenotyping methods森林苗木の品質形質評価に用いるハイパースペクトル画像解析を中心に扱うフェノタイピングレビューであり、方法論的役割が明確。
titleThe role of hyperspectral imaging in forest seedling phenotyping
Field / plotWhole plant / canopy / plot / fieldObject detectionPhysiological trait estimationStress / disease detectionGrowth / development / phenologyPigment / colour / senescenceStress response / toleranceWater status / transpiration
Plant wearable sensors are emerging as flexible, non-invasive platforms for continuous assessment of plant physiological status and plant–environment interactions. This review examines recent progress in wearable sensing systems for real-time monitoring of water status, growth dynamics, chlorophyll content, volatile organic compounds, humidity, temperature and stress-associated responses. It summarises major sensing approaches, including capacitive, chemical, photodetector-based and piezoresistive sensors, with attention to their materials, fabrication strategies, operating principles and potential applications in plant health monitoring. Advances in flexible substrates, conductive materials, nanostructured sensing layers, biodegradable polymers and wireless communication have improved sensor compatibility with plant surfaces and enhanced the detection of physiological changes under field-relevant conditions. Integration with the Internet of Things, artificial intelligence, machine learning, cloud platforms and data analytics further supports continuous data acquisition and interpretation for precision crop management. These systems may contribute to early detection of biotic and abiotic stresses, enabling timely interventions and improved resource-use efficiency. However, broader adoption remains limited by sensor durability, environmental interference, power requirements, scalability, cost and the complexity of interpreting plant-derived signals. Continued interdisciplinary research is required to develop reliable, affordable, energy-efficient, biodegradable and multifunctional sensing platforms that support sustainable agricultural management under changing environmental conditions.
Why it matches plant phenotyping methods植物の生理状態・成長・クロロフィル・ストレス応答を測定するウェアラブルセンシング手法を中心に扱うレビューであり、植物フェノタイピング手法が中核である。
abstractThis review examines recent progress in wearable sensing systems for real-time monitoring of water status, growth dynamics, chlorophyll content, volatile organic compounds, humidity, temperature and stress-associated responses.
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 5 Sept 2026
Field / plotLiDAR / point cloudWhole plant / canopy / plot / fieldMorphology / geometry measurement2D/3D reconstructionSegmentationStress / disease detectionArchitecture / morphology / geometryGrowth / development / phenology
Three-dimensional (3D) crop phenotyping is increasingly used to capture crop structure, but its value for crop protection is conditional rather than automatic. 3D approaches are operationally justified only when reconstructed geometry adds decision-relevant information beyond simpler 2D, spectral, scalar, or conventional baselines. This review examines 3D crop phenotyping through a reconstruction-trait-task-maturity framework for crop protection and synthesizes evidence across disease assessment, pest and stress interpretation, pesticide dose adjustment, spray deposition, weed-target perception, protection-oriented breeding, and digital-twin development. The literature is organized through four connected lenses: reconstruction routes that generate crop geometry, 3D traits that may alter protection reasoning, decision pathways that link traits to intervention variables, and maturity levels that distinguish static 3D models, validated phenotypic traits, process-coupled systems, protection outputs, and outcome-updated decision twins. The strongest decision-facing evidence currently comes from canopy-based dose adjustment, deposition prediction, drift reduction, and related spraying applications in which 3D traits are linked to intervention variables and field-facing comparators. Disease, stress, and architecture-aware modelling provide important but more heterogeneous evidence, while many point-cloud datasets, segmentation pipelines, neural reconstruction methods, and agricultural digital-twin frameworks remain upstream of practical crop-protection decisions because they do not yet connect 3D measurements to validated protection labels, comparator baselines, decision thresholds, intervention outputs, or outcome updating. A central conclusion is that high-fidelity 3D representation should not be conflated with decision-twin maturity. Protection-oriented digital twins require explicit coupling among synchronized crop geometry, functional or epidemiological models, decision rules, and recorded field outcomes. This review therefore identifies the evidence and reporting priorities needed to move 3D crop phenotyping toward validated, deployment-oriented, and feedback-aware crop-protection support.
Why it matches plant phenotyping methods3D作物フェノタイピングの再構成、形質抽出、検証、デジタルツイン成熟度を中心に扱うレビューであり、植物フェノタイピング手法が中核。
abstractThis review examines 3D crop phenotyping through a reconstruction-trait-task-maturity framework for crop protection and synthesizes evidence across disease assessment, pest and stress interpretation, pesticide dose adjustment, spray deposition, weed-target perception, protection-oriented breeding, and digital-twin development.
In modern agriculture, artificial intelligence (AI) is doing excellent work in crop monitoring, crop disease detection, crop yield prediction, and crop stress assessment. Various techniques such as deep learning, generative models, vision transformers, explainable AI (XAI), multimodal fusion, etc., have helped in building intelligent crop analysis. This paper provides the comparative crop analysis of various crop species, data modes, and environmental conditions for the review of benchmark studies for the current framework, experimental methodologies, and datasets. The important challenges and open issues identified are limited field datasets, class imbalance, dataset bias, high computational complexity, privacy concerns, etc. Based on these, we suggested future work that can include foundation models, digital twin techniques, federated learning, multimodal frameworks, and interpretability architecture. This review provides a review for creating reliable, scalable, and sustainable AI-driven crop analysis systems. In addition to that, the survey seeks to give researchers and AI practitioners a comprehensive analysis of the current situation.
Why it matches plant phenotyping methods作物の病害・収量・ストレス評価を対象に、AI手法、データモード、ベンチマーク、実験方法、データセットを体系的にレビューしており、植物表現型取得・推定手法のレビューが中心です。
abstractThis paper provides the comparative crop analysis of various crop species, data modes, and environmental conditions for the review of benchmark studies for the current framework, experimental methodologies, and datasets.
Generally, plants possess great medical benefits that are tremendously diverse and complex to identify the species. There are different varieties of plants that are yet to be fully explored. The plants are made up of some essential parts that are needed for their survival, such as roots, flowers, leaves, shoots, and others, which often appear to be alike with each other. This makes manual sorting of plants more difficult for botanists. Concurrently, image processing performs some operations by extracting useful information from the image for human interpretation. The resulting dataset from the image processing method is then classified by ML (Machine Learning) classifiers. The existing methods have focused on several dimensions; this study provides an overall view of the conventional works of plant species identification and its related plant health. This study was initiated with the purpose of giving a precise review of the advancements in image processing, such as segmentation methods, feature extraction techniques and ML-based models for the identification of plant species and diseases with its leaf because that can be available at all times. Hence, this study discusses the current research between (2019–2024) related to the use of image processing and ML and DL techniques for effective image quality enhancement and plant identification performance. Moreover, it discusses unique contributions in the field, such as agriculture and ayurveda. Moreover, a comparative analysis is carried out by considering the conventional ML models and the varied applications of widely used ML models for the effective classification of plant species.
Why it matches plant phenotyping methods葉画像のセグメンテーション、特徴抽出、機械学習・深層学習による植物病害の画像分類を対象とする方法レビューであり、植物の病態推定手法が中心です。種同定も含みますが、病害・植物健康の画像解析手法を体系的に扱っているため採用します。
abstractThis study was initiated with the purpose of giving a precise review of the advancements in image processing, such as segmentation methods, feature extraction techniques and ML-based models for the identification of plant species and diseases with its leaf
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 5 Sept 2026
Crop ideotype breeding aims to design plant architectures that enhance yield and resource use efficiency. Accelerating this process demands a framework for assembling accurate three-dimensional (3D) architecture. This Perspective synthesizes advances in technologies and methodologies in 3D architectural phenotyping. Rapid progress has enabled translating these advances into tangible gains in breeding efficiency. To this end, we propose integrating functional-structural plant models as an overarching framework that optimizes plant architecture combinations, shifting breeding from experience-driven to predictive ideotype design. Convergence of 3D phenotyping, plant modeling and artificial intelligence holds transformative potential to accelerate breeding cycles, enhancing productivity, sustainability, and food security.
Why it matches plant phenotyping methods3D植物形態フェノタイピング技術・方法論を中心に統合し、機能構造モデルやAIとの連携を論じる方法論的Perspectiveである。
abstractThis Perspective synthesizes advances in technologies and methodologies in 3D architectural phenotyping.
Abstract Forest biometrics has evolved from a measurement-driven discipline focused on field efficiency and statistical rigor to a data-rich, technology-enabled science integrating multisensor information and advanced modeling approaches. This special issue, inspired by the Second North American Forest Mensurationists Conference held in 2022, highlights this transformation through nine studies that collectively span scales from individual branches to regional forest dynamics. Together, they emphasize a shift from identifying single optimal models to developing integrated, uncertainty-aware model systems that support operational decision-making. At the finest scale, advances in terrestrial laser scanning enable improved characterization of branch geometry under challenging conditions, yielding robust taper and form factor estimates for volume. At the tree level, extensive benchmarking of height–diameter relationships demonstrates that model form and stand origin strongly influence predictive performance, with generalized additive models often outperforming traditional approaches. Complementary work shows that calibration strategies are not universally transferable across model forms, underscoring the need for careful alignment of function choice and calibration design. Addressing biases in young stands, Bayesian model averaging offers a practical interim solution where traditional volume models trained on mature cohorts fail. At broader scales, studies demonstrate the operational potential of integrating public and low-cost remote sensing data. Freely available USGS 3DEP LiDAR supports highly accurate dominant height and site index estimation, while bias-corrected digital aerial photogrammetry provides a viable alternative in areas lacking LiDAR coverage. Landscape-level analyses using Landsat time series and permanent plots enable mapping of basal area growth, revealing spatial variability and temporal trends driven largely by stand dynamics. Collectively, these studies define a cohesive framework for modern forest biometrics: combining multiple data sources, selecting model families deliberately, applying light but effective calibration, and explicitly quantifying uncertainty. This integrated approach supports scalable, reliable predictions tailored to the needs of forest managers and policymakers. The special issue thus outlines a forward-looking research agenda that prioritizes resilient modeling systems over isolated solutions, enabling forestry to meet contemporary challenges across scales from tree components to landscapes.
Why it matches plant phenotyping methods森林の枝形状、樹高、林分指標などの植物形質を、レーザースキャン、航空写真、LiDAR、時系列衛星データ、統計モデルで推定・検証する方法群を中心に扱う特集概説であり、測定・推定手法が中心である。
abstractAt the finest scale, advances in terrestrial laser scanning enable improved characterization of branch geometry under challenging conditions, yielding robust taper and form factor estimates for volume.
Accurate and non-destructive volume estimation of agricultural products is essential for precision agriculture, yet remains challenging when transitioning from controlled laboratory conditions to complex orchard environments. Although 2D image-based volume estimation methods provide a cost-effective and scalable solution, existing studies are fragmented and lack a unified perspective on their real-world applicability. This review presents a systematic synthesis of 2D image-based volume estimation methods, explicitly framed through the laboratory-to-orchard transition. We categorized existing volume estimation approaches according to the sensing modality into monocular RGB-based approaches and depth-assisted methods, and further reviewed them based on the image processing methods. A key finding is that high-precision geometric estimation can be achieved in laboratory environments, whereas deep learning and RGB-D fusion have driven a shift from conventional geometric modeling toward data-driven and hybrid learning frameworks in orchard settings. However, 2D image-based volume estimation remains fundamentally limited by scale ambiguity, severe occlusion, and sensitivity to illumination and background variability in real orchard environment. Overall, this review provides a unified perspective for understanding volume estimation methodology across environments and offers guidance for developing robust, scalable, and field-deployable volume estimation systems for real-world agricultural applications.
Why it matches plant phenotyping methods農産物の2D画像から体積を推定する手法を体系的にレビューしており、植物器官・果実の形態形質取得方法が中心である。
abstractThis review presents a systematic synthesis of 2D image-based volume estimation methods, explicitly framed through the laboratory-to-orchard transition.
Dielectric permittivity describes how a material becomes polarized in response to a time-varying electric field and provides a powerful framework for probing the physical organization of biological systems. This review aims to clarify the origin of dielectric permittivity in plants, offering a conceptually grounded interpretation while keeping mathematical formalism to the level necessary for biological interpretation. We first outline the fundamental mechanisms of polarization, their characteristic time scales, and the frequency-dependent nature of the dielectric response, including the concept of complex permittivity, together with commonly used measurement approaches in biological materials. Particular attention is given to water, whose dielectric properties play a dominant role in plant tissues. We then examine how permittivity varies across different plant organs, including leaves, fruits, and roots, highlighting the relationship between dielectric response and structural and compositional features. Modeling strategies linking microscopic organization to macroscopic dielectric behavior are also discussed. Because dielectric permittivity is intrinsically connected to plant structure and composition, non-invasive measurements offer significant potential for assessing plant physiological status, including the detection of changes induced by abiotic and biotic stresses. By bridging engineering approaches with plant physiology, this review provides a unified framework to interpret dielectric measurements in plants and supports their application in plant science and phenotyping.
Why it matches plant phenotyping methods植物の誘電率測定を植物構造・組成や生理状態の非侵襲的評価に結び付けるレビューであり、植物フェノタイピング手法の解釈と応用が中心です。
abstractThis review aims to clarify the origin of dielectric permittivity in plants
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 5 Sept 2026
RiceGrowth / development / phenologyStress response / tolerance
The reliance on traditional or manual phenotyping creates significant operational bottlenecks in rice breeding due to its resource-intensive and time-consuming nature. This review focused on the significance of high-throughput phenotyping (HTP) as a promising technology that enables rapid, accurate, and non-destructive phenotyping of large populations. HTP has great potential to accelerate rice breeding by revolutionizing phenomics. This review examined the various applications of HTP in rice research, phenomics, and breeding. The use of HTP in rice has been substantiated through a range of cutting-edge technologies, such as drones, imaging systems, and sensor networks, that facilitate precise monitoring of key traits at various growth stages, assessment of responses to biotic and abiotic stresses, and the identification of genes or quantitative trait loci (QTLs) associated with essential characteristics. Also, this review discussed HTPs' contributions to current rice breeding programs and documented notable challenges in scaling them. This review offers insights into optimizing HTP strategies to advance rice research, phenomics, and rice breeding.
Why it matches plant phenotyping methodsイネのハイスループット表現型解析技術の応用、技術、課題を中心に扱うレビューであり、植物フェノタイピング手法レビューに該当する。
abstractThis review focused on the significance of high-throughput phenotyping (HTP) as a promising technology that enables rapid, accurate, and non-destructive phenotyping of large populations.
Why it matches plant phenotyping methods植物の水分状態を測定する古典的方法（重量法、プレッシャーチャンバー、サイクロメトリ等）を中心に原理・手順・検証用途をレビューしており、植物生理形質のフェノタイピング方法レビューに該当する。
abstractIn Part 1 of a two-part review, we provide insights into using leaf water content as a reliable proxy for assessing water status and synthesize classical, destructive methods for measuring plant water status, encompassing gravimetric techniques, Scholander pressure chamber and psychrometric techniques.
Why it matches plant phenotyping methods植物の水分状態を非破壊・遠隔センシングで測定する手法を体系的に比較・評価したレビューであり、植物フェノタイピング手法が中心です。
abstractThis second of a two-part review synthesizes recent advances in non-destructive approaches for measuring plant water status, evaluating their principles, applications and limitations.
Abstract Objective Minimizing crop losses through the early detection of plant diseases is vital for enhancing global agricultural efficiency. While deep learning has emerged as a promising solution, a significant gap exists between laboratory performance and practical, in-field utility. This study evaluates this discrepancy through a dual-methodological approach. Methods First, a tertiary systematic literature review was conducted, synthesizing 22 secondary reviews encompassing over 750 unique primary studies to establish the current state of the art. Second, an empirical validation was performed using a VGG16 transfer learning model trained on three distinct dataset types, which vary in scale (small vs. large), environment (laboratory vs. in-field), and condition (raw vs. pre-processed). Results The tertiary review identifies Convolutional Neural Networks, particularly VGG architectures, as the leading model but highlights a critical reliance on private and unrealistic datasets. Furthermore, the analysis reveals that Accuracy, the most common metric, is often insufficient for evaluating the imbalanced datasets typical of the field. Empirical results corroborate these findings, demonstrating that VGG16 performance is highly dependent on dataset characteristics; models perform significantly better on large, pre-processed laboratory data than on realistic in-field datasets. Conclusion These findings suggest that many current models remain inapplicable to real-world agricultural scenarios. To bridge this reality gap, future research must prioritize the development of open-source, standardized, and validated in-field datasets to ensure the reliability and scalability of automated disease detection systems.
Why it matches plant phenotyping methods植物病害を画像から検出する深層学習手法を体系的にレビューし、VGG16を異なるデータセット条件で実証評価しており、病害状態の取得・推定方法が中心である。
titleA tertiary systematic literature review and experimental evaluation of deep learning models for plant disease detection
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 5 Sept 2026
Agriculture plays a crucial role in the development of countries whose economies rely heavily on food production. In the face of climate change and growing global population, plant breeders are challenged to adopt more efficient crop improvement strategies. The advances in artificial intelligence (AI), particularly in large-scale data integration, analysis, and pattern recognition, have revolutionized several scientific disciplines, including plant breeding. In this review, we provide a comprehensive survey of the potential of AI tools in plant breeding with four key objectives: (i) revolutionizing high-throughput phenotyping, (ii) exploring AI-driven breeding methodologies beyond traditional approaches, (iii) optimizing breeding pipelines through improved modelling of genotype × environment × management interactions, and (iv) highlighting the limitations of AI in plant breeding and future directions. Case studies published during the past two decades illustrate successful implementations of AI-powered phenotyping and breeding frameworks for major traits across diverse crop species. Furthermore, AI tools show great promise in refining crop traits at the molecular level by increasing the accuracy and precision of emerging fields including gene editing and genomic selection. We emphasize the importance of interdisciplinary collaboration to maximize the benefits of AI in plant breeding programs and to support the sustainable and food-secure future. This review bridges the gap between AI and agricultural applications, offering a roadmap for researchers, industry professionals, and policymakers to harness information fusion and computational models for advancing precision agriculture. It will serve as a valuable resource for future plant breeding, accelerating crop improvement from phenotyping to genomic selection and breeding decision support.
Why it matches plant phenotyping methodsAIを用いた植物のハイスループット・デジタルフェノタイピングを主要対象として扱うレビューであり、フェノタイピング手法の方法論的総説に該当する。
abstractIn this review, we provide a comprehensive survey of the potential of AI tools in plant breeding with four key objectives: (i) revolutionizing high-throughput phenotyping
Strawberry greenhouse cultivation is increasingly supported by sensing technologies, artificial intelligence (AI), and decision-support infrastructure, but their horticultural value depends on whether heterogeneous measurements can be translated into biologically meaningful crop states and practical management decisions. This review synthesizes strawberry phenotyping, multimodal sensing, AI-based crop-state interpretation, and supervised agentic coordination as a phenotyping-to-action framework for greenhouse strawberry cultivation. The reviewed studies show substantial progress in measuring and interpreting vegetative, reproductive, fruit-quality, stress-related, and environmental crop states through imaging, spectral, environmental, root-zone, and modeling approaches. However, much of the literature still emphasizes measurement accuracy, model performance, or infrastructure capability, whereas fewer studies validate whether AI-derived outputs improve crop response, management decisions, workflow, resource use, or production outcomes. The review therefore distinguishes sensing technologies for data acquisition and measurement from AI-based methods for interpretation and prediction, and examines how crop-state information can be connected to practical greenhouse decision making. It also compares established decision technologies, including expert systems, model predictive control, digital twins, and closed-loop coordination, with supervised agentic coordination as bounded decision-support concepts rather than as evidence of unrestricted autonomous control. Future work should emphasize phenotype-to-action validation, domain-aware benchmarking, and supervised deployment studies that connect model outputs with decision rules, crop outcomes, operational constraints, and grower oversight. By grounding sensing technologies and AI-based interpretation methods in crop-response validation, strawberry greenhouse systems can progress toward supervised, crop-state-driven decision support.
Why it matches plant phenotyping methods温室イチゴのフェノタイピング、マルチモーダルセンシング、AIによる作物状態解釈を中心に整理する方法論レビューであり、植物状態の取得・推定手法が主題。
abstractThis review synthesizes strawberry phenotyping, multimodal sensing, AI-based crop-state interpretation, and supervised agentic coordination as a phenotyping-to-action framework for greenhouse strawberry cultivation.
Global food security requires crop improvement strategies that can respond to population growth, climate variability and increasing constraints on agricultural resources. Conventional plant breeding has contributed substantially to crop productivity, yet long selection cycles and dependence on extensive field evaluation can limit the rate of genetic gain. This review synthesises advances in genomics, phenomics and machine learning for next-generation crop breeding, with emphasis on their combined contribution to selection accuracy and breeding efficiency. Key genomic approaches discussed include whole-genome sequencing, reference and pan-genome resources, genome-wide association studies, genomic selection and CRISPR-Cas-based genome editing. The review also examines high-throughput phenotyping platforms, including controlled-environment systems, ground-based robots, UAV-based remote sensing and root phenotyping tools. Machine learning approaches, ranging from random forest and support vector machines to convolutional neural networks, recurrent networks, transformers and explainable artificial intelligence, are considered in relation to genomic prediction, image analysis and breeding decision support. Multi-omics integration, data management, FAIR principles and an integrated genomics-phenomics-ML breeding pipeline are reviewed as enabling components for practical deployment. Crop-specific examples from wheat, rice, maize, soybean and legumes illustrate the potential and constraints of these technologies. The review further identifies key challenges, including phenotyping bottlenecks, genotype-environment interaction, data governance, model interpretability and regulatory uncertainty.
Why it matches plant phenotyping methods植物フェノタイピング手法を中心に、ハイスループット計測プラットフォーム、画像解析、機械学習、UAV・ロボット・根系計測などをレビューしているため。
abstractThis review synthesises advances in genomics, phenomics and machine learning for next-generation crop breeding
Remote sensing using uncrewed aerial vehicles (UAVs) and AI, particularly machine learning and deep learning, is increasingly applied to crop pest and disease detection. However, the real-world robustness of these models remains uncertain. We conducted a meta-analysis of 121 UAV-based studies published between 2018 and 2024, examining dataset construction and model validation practices. We found that 89% of studies lacked truly independent test datasets, resulting in inflated performance estimates and limited generalisability. Only 11% evaluated models on independent fields, and successful transferability was uncommon. Our analysis identifies key methodological limitations underlying this issue and provides recommendations to improve robustness, reproducibility, and practical relevance. Overall, current validation practices require substantial improvement to ensure reported model performance reflects field-level applicability.
Why it matches plant phenotyping methodsUAV・AIによる作物の病害検出手法を対象に、121研究のデータセット構築とモデル検証をメタ分析し、独立圃場での性能や再現性を評価する方法論的レビューである。病害検出は植物の病態・重症度に関わるため、手法中心の研究として採用する。
abstractWe conducted a meta-analysis of 121 UAV-based studies published between 2018 and 2024, examining dataset construction and model validation practices.
MaizeRoot2D/3D reconstructionGrowth / development / phenologyRoot system architecture
Maize (Zea mays L.) is a major cereal crop whose productivity across diverse agro-ecological environments is strongly influenced by belowground traits. The root system functions as the primary plant-soil interface, regulating water and nutrient uptake, providing mechanical support and enabling adaptive responses to abiotic and biotic stresses. Despite its central importance, maize root biology has historically received less attention than aboveground characteristics. The maize root system comprises primary, seminal, nodal and lateral roots differing in developmental origin, growth behaviour and physiological role. Key architectural traits-such as rooting depth, root growth angle and branching density-play a crucial role in root system development. These traits, along with anatomical features like cortical aerenchyma and root hair development, are governed by complex genetic networks involving regulatory genes, quantitative trait loci and hormone-mediated signalling pathways. Root growth and spatial distribution are further shaped by soil properties and agronomic practices, including irrigation and nutrient management. Recent advances in high-throughput phenotyping, three-dimensional (3D) reconstruction and artificial intelligence (AI) based image analysis technologies have enhanced quantitative assessment of root traits. This review consolidates recent progress in maize root research with emphasis on root system architecture (RSA), developmental regulation and their functional relevance to crop productivity. Uniquely, it integrates structural, genetic and phenotyping advances in maize root research into a unified framework, while explicitly linking RSA with its functional significance, an aspect often treated separately in earlier reviews. Optimising maize root systems is therefore essential for improving productivity, resource-use efficiency and agricultural sustainability under changing climatic conditions.
Why it matches plant phenotyping methodsトウモロコシ根系研究のレビューであり、根系形態形質の定量評価に用いるハイスループット表現型解析、3D再構成、AI画像解析を明示的に扱うため、表現型解析手法レビューとして中心的です。
abstractRecent advances in high-throughput phenotyping, three-dimensional (3D) reconstruction and artificial intelligence (AI) based image analysis technologies have enhanced quantitative assessment of root traits.
Crop diseases cause 20-40% of food losses every year and cause economic damage of more than USD 220 billion per year on a global scale. The basic problems in precision agriculture remain the same as early and accurate disease detection. Hyperspectral imaging (HSI) is a type of imaging technique that captures hundreds of contiguous wavelengths of the electromagnetic spectrum spanning from 400 to 2500 nm that has been found to be a useful non-destructive diagnostic tool that can detect the subtle biochemical differences that occur in plant tissue before symptoms are visible. The paper critically summarizes and reviews the literature from 2000 to 2024, especially focusing on the application of AI and machine learning (ML) for HSI-based crop disease detection. A total of 48 primary studies are reviewed and grouped into five thematic categories: (1) spectral vegetation index methods, (2) classic machine learning classifiers, (3) deep learning architectures, (4) attention and transformer mechanisms and (5) disease severity quantification. Based on this review, four gaps in the literature are identified: (1) lack of comparison of classical and deep learning models on the same splits of the same datasets, (2) underutilisation of the SWIR-2 spectral range (>2000 nm) for the discrimination of diseases, (3) lack of integrated spatial mapping of the disease severity from spectral index fusion, and (4) lack of lightweight deep learning spectral-only architectures for field deployment in resource-constrained environments. These gaps together form a promising research program based on this AI approach to automated crop disease detection, and the experimental research work reported in our companion paper is fueled by these gaps.
Why it matches plant phenotyping methods植物病害の症状・重症度をハイパースペクトル画像とAIで推定する手法を対象とした体系的レビューであり、植物フェノタイピング手法のレビューが中心。
abstractHyperspectral imaging (HSI) is a type of imaging technique that captures hundreds of contiguous wavelengths of the electromagnetic spectrum spanning from 400 to 2500 nm that has been found to be a useful non-destructive diagnostic tool that can detect the subtle biochemical differences that occur in plant tissue before symptoms are visible.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 13 Sept 2026
Modern agriculture operates at an unprecedented crossroads, it must simultaneously accelerate crop yields to feed an expanding global population and adapt to the severe, fluctuating pressures of climate change, structural soil degradation, abiotic water deficits, and evolving biological threats. Historically, selecting resilient crop varieties and implementing field-scale management strategies relied extensively on destructive, labor-intensive, and fundamentally subjective visual metrics. This manual processing approach has long been recognized as the primary operational bottleneck in agricultural advancement.To bridge the gap between rapidly expanding genomic data and actual field performance, the systematic, non-destructive quantification of structural and functional plant traits, plant phenotyping, has emerged as a transformative frontier. By integrating high-throughput engineering, multi-scale remote sensing, deep learning, and advanced molecular biology, modern phenotyping transitions crop science away from qualitative estimation toward highly reproducible, multidimensional data frameworks. This Research Topic presents new advances in advanced 3D reconstruction and deep semantic segmentation at the seedling stage; amodal fruit segmentation, morphological extraction, and early water-stress diagnostics; high-throughput in-field seedling counting and dynamic density modeling; multimodal foundation models, network pruning, and intelligent phytoprotection; aerial and spaceborne remote sensing for canopy analysis and weed monitoring; plant physiology, functional spectroscopy, and functional genomics under abiotic stress; and automated diagnostics for real-time orchard scouting and vineyard management.Automating the characterization of complex spatial layouts under controlled or greenhouse environments is essential for early variety selection and early-stage structural evaluation. Several contributions within this volume provide key breakthroughs in navigating overlapping tissues, severe occlusions, and low-contrast edge regions. showcases how substituting standard convolutions with deformable convolutions enables deep neural networks to accurately isolate the main stem of mature, high-density crops like soybeans. This architecture overcomes the traditional challenges of color mimicry and severe occlusion by pods and leaves, achieving an outstanding mIoU of 90.58% and providing reliable indices for lodging resistance and structural yield modeling (R 2 = 0.9746).Accurately extracting fruit morphology under commercial greenhouse conditions remains heavily constrained by overlapping crop structures, foliage cover, and variable shadows. Simple semantic masks typically fail when a target fruit is partially blocked, leading to a loss of key volumetric data.To resolve the challenge of hidden boundaries, Li, Yin, et al. (2025) developed CGA-ASNet, a specialized RGB-D amodal segmentation network driven by a Contextual and Global Attention (CGA) module designed to restore occluded tomato regions. Trained on a high-fidelity synthetic greenhouse dataset (Tomato-sim) generated via NVIDIA Isaac Sim's Replicator Composer and optimized with a mean coordinate fusion algorithm for real-world validation, this architecture expands the network's receptive field to predict the complete, hidden circular forms of occluded tomatoes, achieving an F@0.75 score of 94.2 and an amodal mIoU of 82.4%. This proves that simulation-to-real (Sim2Real) domain pathways can successfully decode full physical volumes under dense commercial canopies.Complementing this structural restoration, Yang, Li, et al. (2025) designed an integrated diagnostic framework to identify early water stress dynamics in greenhouse tomatoes. Built upon an optimized YOLOv11n core, their system integrates adaptive kernel convolutions (AKConv) into the network backbone's C3k2 modules and implements a recalibration feature pyramid detection head based on the specialized P2 small-target layer. This combination achieved a 5.4% increase in mAP50-95 for identifying fine phenotypic parts. By applying automated geometric analysis to the extracted bounding boxes, the system extracts plant heights and petiole count with low relative errors, feeding these phenotypic parameters into a Random Forest classification routine that flags water-stressed plants with 98% accuracy to guide targeted, automated drip irrigation.Accurate plant stands during early vegetative stages represent the foundational metric required to establish true field emergence rates, validate seed vigor across diverse breeding blocks, and perform early yield predictions.To solve the challenges of small targets, extreme spatial density, and adjacent leaf overlap, Zang et al. (2025) designed DM_IOC_fpn, a wheat seedling counting framework that balances local and global contextual features. By structuring a point-annotated dataset and embedding a densityenhanced encoder module, their network balances micro-scale spatial limits with macro-scale canopy structures. Optimized through a combined loss function tracking counting, classification, and regression parameters, this architecture achieved low error scores (RMSE = 2.91; MAE = 2.23), outperforming standard object-detection benchmarks in complex field environments.At the same time, scaling up to real-time aerial monitoring required major reductions in model complexity to support resource-constrained edge computers on autonomous aerial platforms. Feng, Nie, and Li (2025) engineered an ultra-lightweight YOLOv8n variant tailored for real-time maize seedling counting from high-speed UAV RGB overflights. By reparametrizing RepConv with HGNetV2, they constructed a lean Rep_HGNetV2 backbone, integrated a Bidirectional Feature Pyramid Network (BiFPN) for multi-scale feature alignment, and implemented a Task Dynamically Aligned Detection Head (TDADH). This architecture compressed total model parameters by 47% and reduced weight sizes to 3.5 MB while maintaining a 96.5% detection accuracy and an ultra-fast processing speed of 146.3 FPS, paving the way for low-cost, real-time field scouting.Automated phytoprotection requires machine-vision architectures capable of generalizing across highly diverse species, complex field conditions, and varying computational boundaries. A significant subset of the published papers addresses these challenges through foundation model adaptation, multi-modal alignment, and efficient network compression.A major paradigm shift presented in this collection involves moving away from task-specific training and toward foundation model adaptation. Chen, Ruan, et al. (2026) introduce a novel architecture integrating the DinoV3 foundation model with a Unet framework to achieve robust leaf lesion segmentation across diverse species (such as coffee and black gram). By incorporating a Spatial Prior Module (SPM), their approach surpassed standard benchmark networks by over 10.5% in IoU while reducing inference times by approximately 93.6%, demonstrating that highparameter foundation models can be highly optimized for resource-constrained edge devices in real-time scouting.To solve the perennial problem of limited training data for rare or emerging crop diseases, Cooper et al. ( 2026) developed an ingenious synthetic data generation pipeline. Combining 3D procedural leaf modeling in Blender with diffusion-based disease synthesis (Stable Diffusion fine-tuned with LoRA and ControlNet), they synthesized highly accurate plant disease images with perfect groundtruth annotation masks. When deployed in low-resource data settings, combining these synthetic pipelines with restricted real-world datasets consistently drives significant improvements in downstream segmentation tasks. To tackle specific, complex pathologies, Xu, Chang, et al. (2025) developed the TSSC deep learning model, which embeds three-neighbor channel attention paired with a complementary squeeze-and-excitation mechanism. This specific architecture minimizes structural degradation risks while pushing classification accuracy to 99.61% for highly complex pea leaf pathologies. Similarly, Feng, Liu, et al. (2025) tackled overlapping leaf occlusions and small lesion footprints in citrus groves with YOLO-Citrus, an optimized framework integrating C3K2-STA, ADown modules, and a Wise-Inner-MPDIoU loss function to strike a balance between edge computational constraints and field deployment.UAVs and high-resolution satellite imagery have expanded the operational scale of phenotyping from individual pots to vast breeding blocks and commercial fields, allowing researchers to capture macro-dynamic parameters over time.In complex canopy systems that defy standard top-down aerial sensing, such as single-staked white Guinea yams, Iseki et al. (2026) demonstrated the distinct advantage of utilizing multi-angle (combined nadir and oblique) UAV imaging configurations. When coupled with support vector regression, this method captures complementary canopy-structure information to model shoot biomass trajectories (R 2 = 0.79) across multiple years and management zones. These nondestructive, time-series datasets enabled the fitting of genotype-specific Richard's growth curves using Bayesian inference, isolating valuable genetic variations in early growth allocation.To capture full-season vertical physiological changes over large scales, Li, Yue, and Luo (2025) developed a hybrid CNN-LSTM-Attention (CLA) model designed to estimate the full-period Leaf Area Index (LAI) in rice using multi-temporal UAV multispectral imagery. By using the CNN layer to extract instantaneous spatial features, the LSTM block to process seasonal time-series intervals, and a self-attention mechanism to weight critical growth transitions, their platform achieved a high coefficient of determination (R 2 = 0.92) and kept relative root mean square errors (RRMSE) below 9%. This network minimized soil background noise during early vegetative stages (LAI values 1-
Why it matches plant phenotyping methods植物フェノタイピングの技術動向を扱うEditorialであり、画像解析、UAVセンシング、深層学習、形質抽出などの方法が中心的に整理されている。
Maturity at harvest is a critical determinant of yield, storability, market value, and nutritional quality, making accurate and objective maturity assessment essential for sustainable crop and fruit production. The agricultural sector is under pressure to satisfy rising global food demand while reducing losses and environmental impacts, yet conventional maturity assessment methods remain largely manual, subjective, and labour-intensive. Against this backdrop, computer vision and deep learning have emerged as powerful tools for non-destructive, high-throughput evaluation of maturity traits in the field and along the supply chain. This review consolidates recent advances in deep learning-based maturity assessment across a wide range of crops, with a particular emphasis on citrus fruits, where external colour change, internal quality, and heterogeneous orchard conditions pose distinctive challenges. The paper analyzes state of the art architectures for classification, segmentation and detection, associated datasets and imaging modalities, and the metrics used to benchmark performance. By critically examining their advantages and limitations for real-world deployment, the review outlines key research gaps and future directions toward robust, scalable, and sustainable DL-driven maturity assessment systems for both citrus and other major crops.
Why it matches plant phenotyping methods作物の成熟度という植物形質を対象に、画像・深層学習による評価手法、データセット、画像モダリティ、ベンチマーク指標を体系的にレビューしており、フェノタイピング手法が中心です。
abstractThis review consolidates recent advances in deep learning-based maturity assessment across a wide range of crops
Magnetic field (MF) technologies have been applied in agriculture for decades. However, they have not achieved mainstream adoption, partly because no validated methodology exists for evaluating their effects under realistic field conditions. UAV-based multispectral sensing represents a potential pathway to address this limitation: by providing spatially explicit, non-destructive estimates of key canopy physiological variables at field scale, it could provide the monitoring infrastructure through which MF treatment responses are, for the first time, systematically evaluated and validated under open-field conditions. To exploit this complementarity, however, a common evidential ground must first be established, identifying which crop physiological variables are both consistently modulated by MF treatments and reliably detectable by UAV remote sensing. This study addressed this challenge through a dual-stream systematic review of 216 peer-reviewed publications, comprising 102 studies on MF treatments in agricultural crops and 114 studies on UAV-based multispectral monitoring. Evidence from both research domains was synthesised to identify physiological variables that are simultaneously responsive to MF treatments and detectable through UAV remote sensing. Five direct bridge variables were identified: chlorophyll content, nitrogen use efficiency/nitrogen assimilation, above-ground biomass, leaf area index, and yield. Chlorophyll content emerged as the strongest bridge variable, combining consistent MF responsiveness with UAV estimation accuracies of up to R² = 0.90. Based on these findings, a conceptual framework was developed linking MF treatments, UAV-derived vegetation indices, ground-truth measurements, and machine-learning approaches for field-scale validation. The results reveal a complete absence of integration between the two research domains despite their strong biological and methodological compatibility. The proposed framework provides the first operational pathway for evaluating MF technologies under realistic farming conditions and may support future research on sustainable and digitally enabled crop production systems.
Why it matches plant phenotyping methodsUAVマルチスペクトルセンシングによる作物生理形質の推定を体系的にレビューし、地上検証と機械学習を含むフィールドスケール評価フレームワークを提案しており、植物フェノタイピング手法が中心である。
abstractUAV-based multispectral sensing represents a potential pathway to address this limitation: by providing spatially explicit, non-destructive estimates of key canopy physiological variables at field scale
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 5 Sept 2026
Improving nitrogen use efficiency (NUE) in wheat is critical for addressing the dual challenges of global food security and environmental sustainability. Globally, only 42%-47% of applied nitrogen (N) fertilisers taken up by crops, with remainder lost to the environment, driving soil and water pollution, greenhouse gas emissions, and ecological imbalances. This review provides a comprehensive synthesis and integrative framework- integrating agronomic practices, advanced remote sensing and genomic approaches to enhance wheat NUE. We first examine the physiological basis of NUE, emphasising the synergy between photosynthetic carbon assimilation and N metabolism, the critical role of Rubisco in carbon-nitrogen coupling, and the temporal dynamics of N uptake, transport, and remobilisation throughout the wheat growth cycle. The temporal mismatch between source-sink N partitioning during grain filling emerges as a major physiological constraint limiting NUE in modern high-yielding varieties. We then explore transformative advances in remote sensing technologies, highlighting the paradigm shift from traditional vegetation indices to physiological sensing approaches. Through integration of multispectral imaging, LiDAR, thermal infra-red sensing, and solar-induced chlorophyll fluorescence, coupled with three-dimensional radiative transfer models and machine learning algorithms, these technologies enable non-destructive, real-time monitoring of crop N status while overcoming spectral-structural ambiguity and saturation limitations. From a genomic perspective, we synthesise recent progress in quantitative trait loci mapping and genome-wide association studies (GWAS), identifying key genetic loci controlling root architecture, N uptake transporters (NRT/AMT families), and grain filling efficiency. Multi-omics integration-spanning genomics, transcriptomics, and metabolomics-reveals temporal genetic networks distinguishing short-term nitrogen signalling responses from long-term adaptive remodelling, with genes such as TaNAC2-5A, TaNPF6.2, and QMrl-7B emerging as promising targets for molecular breeding. High-throughput phenotyping platforms enable time-series GWAS analysis, capturing developmental dynamics and genotype × environment interactions that traditional approaches miss. Finally, we discuss sustainable N management strategies, including enhanced efficiency fertilisers, precision application technologies, and soil health optimisation. By integrating these multidisciplinary approaches within a Genotype × Environment × Management framework, this review provides a roadmap for developing climate-smart, N-efficient wheat varieties and precision N management systems that simultaneously enhance productivity, reduce environmental footprints, and ensure sustainable agricultural intensification.
Why it matches plant phenotyping methods小麦の窒素状態を非破壊・時系列に測定するリモートセンシングと高スループット表現型解析を、技術的課題や統合手法とともにレビューしており、表現型取得法が実質的に扱われている。
abstractWe then explore transformative advances in remote sensing technologies, highlighting the paradigm shift from traditional vegetation indices to physiological sensing approaches.
Electrochemical monitoring of plant phytohormones offers a powerful route toward real-time assessment of plant stress and physiological status, yet remains technically challenging due to ultra-low analyte concentrations, strong matrix interferences, and the limited redox activity of several key hormones. Conventional analytical techniques provide high sensitivity but are incompatible with in situ, continuous, and field-deployable measurements required for precision agriculture. This review critically examines recent advances in electrochemical sensing strategies for major plant phytohormones, including salicylic acid (SA), abscisic acid (ABA), jasmonic acid (JA), and indole-3-acetic acid (IAA), with a focus on how material design, interfacial engineering, and sensor architecture address fundamental limitations. Hybrid nanomaterials, affinity-based and direct electrochemical transduction mechanisms, and flexible or wearable platforms were critically evaluated for their potential to enhance sensitivity, selectivity, and operational stability under realistic plant and environmental conditions. Beyond individual sensor performance, particular emphasis is placed on multiplexed architectures and data-driven integration with wireless platforms and artificial intelligence, enabling the simultaneous decoding of multiple hormonal signals and their temporal dynamics. By comparing design strategies, performance trade-offs, and remaining bottlenecks, this review provides a conceptual framework for the rational engineering of next-generation electrochemical phytohormone sensors and outlines key directions toward robust, field-ready monitoring systems for smart and sustainable agriculture.
Why it matches plant phenotyping methods植物ホルモンを用いた生理状態・ストレスのセンサー計測法を中心に扱うレビューであり、植物フェノタイピング手法の方法論的レビューに該当する。
abstractThis review critically examines recent advances in electrochemical sensing strategies for major plant phytohormones
Abstract Accurate detection of strawberry fruit, reliable ripeness estimation, and precise localization of the picking point are essential for automated harvesting and yield prediction in smart farming. However, real-world environments introduce significant challenges, including occlusion, illumination variability, and high visual similarity between ripeness stages. Deep learning (DL)-based object detection methods have become the dominant approach to address these issues. This paper presents a systematic review of 60 peer-reviewed studies published between 2023 and 2026, focusing on detecting strawberries and their ripeness using the YOLO family (v5–v11) of DL algorithms. The studies are analyzed with respect to dataset characteristics, preprocessing and augmentation strategies, model architectures, and evaluation protocols. Our results show a clear dominance of YOLOv8, used in 28 (46.7%) of the 60 reviewed works, due to its real-time capability and architectural flexibility. Despite its short history, YOLOv11 has been adopted in 13 studies (21.7%) owing to its balanced precision and computational efficiency. Hybrid CNN–ViT models that integrate Transformer modules or networks into YOLO are gaining attention (8 studies, 13.3%) and show improved performance in complex scenarios, but they still incur higher computational cost. However, we identify critical methodological issues that affect the validity of reported results. In particular, the improper application of data augmentation prior to dataset splitting — a practice observed in precisely one-third of the reviewed studies — poses a significant risk of data leakage and can result in overly optimistic performance estimates. Additional challenges include inconsistent evaluation metrics, limited dataset diversity, and a lack of standardized benchmarks. This review provides a structured overview of current approaches, a critical assessment of existing research practices, and actionable guidance for developing robust, deployment-ready DL solutions for precision agriculture.
Why it matches plant phenotyping methodsイチゴ果実の検出・成熟度推定を対象とする画像ベース手法の系統的レビューであり、データセット、モデル、評価法、データリークやベンチマーク不足を批判的に検討しているため、フェノタイピング手法レビューとして中心的である。
abstractThis paper presents a systematic review of 60 peer-reviewed studies published between 2023 and 2026, focusing on detecting strawberries and their ripeness using the YOLO family (v5–v11) of DL algorithms.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 5 Sept 2026
Plant diseases result in the estimated loss of 20–40% of the world’s crop production annually, amounting to more than $220 billion in economic losses and threatening food security for a rapidly expanding world population. While the conventional methods for detecting plant diseases rely on visual inspection of the symptoms, they are resource-consuming. For effective plant disease detection at a pre-mature stage, hyperspectral imaging (HSI) represents a paradigm shift in technology. It can be used to obtain subtle spectral signatures outside the visible spectrum, which enables pre-symptomatic and highly specific plant disease diagnosis. Concurrently, deep learning (DL) has become the prevalent analytical paradigm for decoding the complex and high-dimensional data that HSI produces. This paper covers a comprehensive narrative review of the intersection of these two transformative technologies from 2008 to 2026. We first set out the biological and physical principles by which HSI is uniquely suited to detecting plant–pathogen interactions in the absence of visible symptoms. We then present a detailed taxonomy of deep learning architectures for Vision Imaging and HSI data, ranging from basic 1D and 3D convolutional neural networks (CNNs) to hybrid models with attention mechanisms and, most recently, vision transformers, which have achieved greater robustness to real-world conditions. There is currently a major and consistent “lab-to-field” performance gap. A critical analysis of various studies reveals a persistent and significant performance gap between models that perform well on controlled lab datasets (ranging from 95 to 99%) and field-collected data (typically 70–85%). This paper also addresses the practical gap of environmental variability, image noise, and the domain gap between the controlled environment and the real dataset. Finally, this review concludes by providing strategic research recommendations and a roadmap, highlighting that the future of the field is contingent upon not only architectural innovation but also a holistic approach, with robustness, scalability, affordability, and interpretability as the main focus to bring the proven potential of HSI-DL systems from the lab to the field, ultimately contributing to global food security.
Why it matches plant phenotyping methods植物病害の症状・状態をハイパースペクトル画像と深層学習で推定する手法を中心に扱うレビューであり、植物フェノタイピング手法レビューに該当する。
abstractThis paper covers a comprehensive narrative review of the intersection of these two transformative technologies from 2008 to 2026.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 5 Sept 2026
Genomics, including all molecular omics, is driven by molecular data, while phenomics and enviromics rely on phenotypic and environmental data. Yet phenotyping is often conducted under poorly characterized environments, limiting the interpretation of phenotypic variation and constraining genetic gain. Integrating high-throughput phenotyping with envirotyping is hence vital to resolve genomic effects. This perspective introduces phenomics-enviromics (PE) crosstalk as a framework for coordinated data collection and integration to advance omics and precision plant breeding. Satellites, unmanned aerial and ground vehicles, and controlled indoor facilities, combined with AI-assisted typing technologies and modeling, are establishing the basis for synchronous, high-throughput PE crosstalk to enhance interpretability, prediction, and crop resilience. Genomics, phenomics, and enviromics constitute the G–P–E triangle in plant breeding, yet enviromics and its interaction with phenomics remain underexplored. Here, the authors introduce phenomics–enviromics (PE) crosstalk and discuss its coordinated data-collection and -integration into next-generation plant breeding.
Why it matches plant phenotyping methods植物フェノタイピングと環境タイピングの統合 framework を中心に扱う展望論文であり、高スループット表現型取得技術とデータ統合が主題。
abstractThis perspective introduces phenomics-enviromics (PE) crosstalk as a framework for coordinated data collection and integration to advance omics and precision plant breeding.
The world suffers from 10–40% loss in crop yields each year because of plant disease. This threat is serious and growing; it threatens food security, rural livelihoods, and agricultural economies. Advances being made through deep learning, computer vision, and mobile technology have presented a unique opportunity to use leaf images to automatically recognize plant disease. Published classification accuracies on benchmark datasets now exceed 97%, which is an important achievement but achieving high accuracy on a benchmark alone does not indicate that traditional methods will work when deployed in the real world: all four stakeholders (i.e., farmers, agronomists, regulatory authorities, and extension agents) must therefore have the ability to understand, and interpret the output of automatically recognized plant diseases in a way that enhances human expertise rather than replacing it. In this chapter, we provide a compendium of technical deep learning architectures and methods related to Explainable Artificial Intelligence (XAI) for plant disease detection, including convolutional networks, residual architectures, dense architectures, transformer networks, and hybrid models. We also systematically evaluate the explainability methods used in both post-hoc and intrinsic explanation and evaluate the applicability of these methods across a variety of imaging modalities used in agriculture, including RGB, multispectral, and hyperspectral. This chapter characterizes major benchmark datasets; discusses major challenges to their deployment, including class imbalance, domain shift, model size reduction, and human–AI trust calibration; then ends with potential new directions for research in areas such as foundation models (FM), causal interpretable models (Explanations), federated learning, and continual learning to build resilience for each evolving pathogen landscape.
Why it matches plant phenotyping methods植物病害を葉画像から自動認識する画像ベースの表現型推定手法と、その説明可能性・データセット・評価課題を体系的に扱うレビューであり、方法論が中心である。
abstractIn this chapter, we provide a compendium of technical deep learning architectures and methods related to Explainable Artificial Intelligence (XAI) for plant disease detection
Driven by artificial intelligence, multi-source sensing, agricultural robots and big data technologies, global agriculture is rapidly upgrading from precision agriculture and agriculture 4.0 to agriculture 5.0. Artificial intelligence has evolved from a single diagnostic tool to an intelligent system that integrates the “perception-decision-execution” process throughout. It is widely applied in crop phenotype analysis, remote sensing monitoring, yield prediction, and autonomous operation of intelligent equipment, etc. This article takes the framework of “intelligent perception-cognitive decision-autonomous execution” to systematically review the core technologies, typical applications, and frontier directions of agricultural artificial intelligence. It focuses on introducing the progress of key technologies such as three-dimensional phenotype, hyperspectral remote sensing, multimodal fusion, and causal machine learning, as well as their value in improving resource utilization efficiency, enhancing climate resilience, and supporting field precision management. At the same time, it points out that current agricultural AI still faces practical bottlenecks such as insufficient generalization ability of models, scarce data and high annotation costs, difficulties in edge deployment, barriers in multi-source data integration, and weak interpretability and engineering reliability. Future research will focus on the construction of closed-loop autonomous farms, the collaboration of agricultural large models and intelligent agents, the construction of data centers and AI and data infrastructure, and the development of green and low-cost AI research. This will provide support for the technological innovation and industrialization implementation of agricultural artificial intelligence.
Why it matches plant phenotyping methods農業AIの総説であり、作物表現型解析を明示的に扱い、三次元表現型・ハイパースペクトルリモートセンシング・マルチモーダル融合などの表現型取得技術を主要テーマとしてレビューしている。
abstractIt is widely applied in crop phenotype analysis, remote sensing monitoring, yield prediction, and autonomous operation of intelligent equipment, etc.
The detection technology of crop diseases and pests is transitioning from single sensor monitoring to intelligent perception and multimodal fusion. This paper follows the PRISMA 2020 standard and systematically reviews the relevant core literature. This paper systematically summarizes the development history of spectral sensing technology and analyzes the physical mechanisms of hyperspectral and multispectral imaging in early identification of crop diseases. The focus is on the architectural evolution of deep learning models, including lightweight convolutional neural networks (CNNs), vision transformers (ViTs) with long-range dependency modeling capabilities, and the efficient computing state space model Mamba. In addition, the research progress of spatial spectral joint learning, heterogeneous data fusion, and vision-language models (VLMs) in improving system robustness and interpretability are introduced. By synthesizing the integrated applications of UAV remote sensing, Internet of Things (IoT) edge computing and intelligent robots in staple and cash crops, this paper summarizes the implementation of the integrated system of perception, decision-making and execution. To address the issues of insufficient cross-domain generalization ability and uneven allocation of computing resources in existing models, this paper provides perspectives on the future development of agricultural artificial intelligence (AI) towards foundation model-driven, edge-intelligent collaboration, and green sustainable direction, which can provide theoretical reference for engineering applications in the field of intelligent plant protection.
Why it matches plant phenotyping methods作物病害の画像・スペクトル観測による植物の病徴・病害状態推定を中心に、検出技術と計算手法を体系的にレビューしており、植物フェノタイピング手法のレビューに該当する。
abstractThis paper systematically summarizes the development history of spectral sensing technology and analyzes the physical mechanisms of hyperspectral and multispectral imaging in early identification of crop diseases.
Unmanned aerial vehicle (UAV) based remote sensing has emerged as a disruptive technology for detecting crop water stress (CWS) in real time, precisely and at low cost offering significant advancements over conventional approaches. The study examined the red green blue (RGB), multispectral (MSP), hyperspectral (HSP), thermal image sensors integrated with UAVs, which offers a high-spatial and temporal resolution of physiological indicators such as chlorophyll content and canopy cover, canopy temperature, stomatal conductance. The study highlights that in spring maize, random forest (RF) models using UAV-derived MSP and thermal indices with leaf area index (LAI) performed well (R² > 0.575, root mean square error (RMSE)
Why it matches plant phenotyping methodsUAV搭載センサーによる作物の水ストレスや生理形質のモニタリング技術をレビューしており、表現型取得法が中心である。
titleRecent trends in crop water stress monitoring using remote sensing technologies: A review
Abstract— Plant diseases significantly affect agricultural productivity, food quality, and global food security [1], [16] Traditional disease diagnosis methods rely heavily on human expertise and manual inspection, making the process time-consuming, expensive, and prone to errors [1], [20]. Recent advancements in artificial intelligence and deep learning have transformed plant disease detection systems by enabling automatic, accurate, and real-time identification of plant diseases using digital images [2], [3], [20]. This review paper presents a comprehensive analysis of recent deep learning approaches used for automated plant disease detection. The study discusses various convolutional neural network architectures, transfer learning methods, attention mechanisms, Vision Transformers, and hybrid deep learning techniques applied in agricultural disease diagnosis [2]– [5], Publicly available datasets, evaluation metrics, preprocessing techniques, and comparative analyses of existing methods are also presented. Furthermore, the paper identifies current research challenges such as dataset imbalance, environmental variability, computational complexity, and limited real-world adaptability[16]. Finally, emerging trends including explainable artificial intelligence, federated learning, lightweight edge computing models, drone-based monitoring systems, and multimodal agricultural intelligence are explored [6]. This review aims to provide researchers and practitioners with a detailed understanding of the current state-of-the-art deep learning techniques for intelligent plant disease detection and future research opportunities. Keywords: Plant Disease Detection, Deep Learning, Convolutional Neural Network, Transfer Learning, Precision Agriculture, Computer Vision, Smart Farming, Vision Transformer.
Why it matches plant phenotyping methods植物病害を画像から自動検出する深層学習手法を体系的に比較・レビューしており、植物状態の画像ベース表現型計測が中心である。
abstractThis review paper presents a comprehensive analysis of recent deep learning approaches used for automated plant disease detection.
Crop diseases pose a serious threat to agricultural productivity and global food security. Early and accurate detection of plant diseases is essential to minimize yield losses and reduce excessive pesticide usage. Traditional disease identification methods rely heavily on manual inspection by agricultural experts, which is time-consuming, subjective, and impractical for large-scale deployment. Recent advances in deep learning and computer vision have enabled automated, image-based crop disease detection with significantly improved accuracy and scalability. This review critically examines state-of-the-art deep learning techniques employed for crop disease detection using leaf images. It analyses commonly used datasets, preprocessing strategies, neural network architectures, evaluation metrics, and deployment challenges. Furthermore, existing research gaps and future directions toward robust, real-world agricultural applications are identified.
Why it matches plant phenotyping methods葉画像から植物病害を検出する画像ベース手法を対象とした包括的レビューであり、データセット、前処理、モデル、評価指標を体系的に扱うため、植物フェノタイピング手法が中心です。
abstractThis review critically examines state-of-the-art deep learning techniques employed for crop disease detection using leaf images.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 5 Sept 2026
Abstract Deep learning, as a pivotal branch of machine learning, has demonstrated remarkable potential in advancing crop science by effectively integrating genomics and phenomics. This review systematically outlines the application of diverse deep learning architectures—such as convolutional neural networks, recurrent neural networks, and transformers—across key crop genomic tasks, including gene expression prediction, alternative splicing analysis, cis ‐regulatory element identification, epigenomic profiling, and genome‐based trait prediction. In phenomics, these models facilitate high‐throughput extraction of crop phenotypic traits from multispectral, unmanned aerial vehicle, and ground‐based imagery, supporting yield forecasting, disease diagnosis, and stress response monitoring. We critically evaluate the performance and limitations of each model type across tasks, considering trade‐offs between complexity, accuracy, and interpretability, to offer practical guidance for crop researchers. Additionally, the review addresses major challenges in deploying deep learning—such as data scarcity, model transparency, and computational demands—and proposes future pathways to enhance model generalizability, multimodal data integration, and applications in intelligent breeding and sustainable agriculture.
Why it matches plant phenotyping methods作物フェノミクスにおける深層学習による画像からの形質抽出を中心的にレビューしており、フェノタイピング手法の方法論的整理に該当する。
abstractIn phenomics, these models facilitate high‐throughput extraction of crop phenotypic traits from multispectral, unmanned aerial vehicle, and ground‐based imagery
Magnetic sensors offer a physically grounded and non-invasive approach to probing biological processes that remain inaccessible to optical, electrochemical, and radio-frequency techniques in complex agricultural environments. In recent years, advances in both classical and quantum magnetic sensors have enabled the detection of bioelectromagnetic signals across plants, soils, animals, and aquatic systems, spanning spatial scales from ionic currents to organ-level electrophysiology and population-level dynamics, positioning magnetometry as an emerging modality within the broader biosensor landscape. This review surveys the evolution of magnetic sensing technologies for agricultural and animal systems, from robust classical sensors used in navigation and soil mapping to quantum-enabled platforms, including Optically Pumped Magnetometers (OPMs) and Nitrogen-Vacancy (NV) centers, capable of resolving pT to fT biomagnetic signals. We synthesize the characteristic amplitudes, frequency ranges, and physiological origins of agriculturally relevant magnetic signals, and critically assess how techniques originally developed for medical magnetoencephalography, magnetocardiography, and low-field magnetic resonance imaging (LF-MRI) are being translated into field-deployable agricultural applications. Beyond sensing hardware, we highlight the essential role of artificial intelligence in extracting weak biological signals from dominant environmental noise, enabling synthetic gradiometry, low-field image reconstruction, and scalable interpretation in unshielded settings. Finally, we discuss how the integration of magnetic biosensing with digital twins supports predictive, multiscale monitoring of plant, animal, and ecosystem health. Together, these developments position magnetometry as an enabling technology for next-generation biosensors in precision and sustainable agriculture.
Why it matches plant phenotyping methods植物の生理状態を対象とする磁気センシング技術を農業向けにレビューしており、植物フェノタイピングに関連するセンサー技術が中心です。
abstractThis review surveys the evolution of magnetic sensing technologies for agricultural and animal systems
Maize is a globally important staple that is used as food for human and animal consumption, fuel, and other industrial applications. Pathogens affect all stages of the plant life cycle and every plant organ, and lead to significant yield losses. An integrated strategy incorporating cultural and chemical management practices, as well as development of resistant plant varieties, is needed to prevent yield losses due to plant diseases. Large numbers of breeding material must be screened to develop pathogen-resistant maize varieties. Inoculation methods must be high-throughput to accommodate the large screening experiments. Additionally, there needs to be an extensive understanding of the plant-pathogen interaction to use a targeted biotechnology-based approach, which takes advantage of knowledge of the system to engineer resistance. To evaluate germplasm for breeding and biotechnology approaches, inoculation methods must replicate natural infection, and disease severity must be rated consistently to accurately screen germplasm or gather data on pathogens of interest. Here, we review inoculation and rating methods for Gibberella ear rot, seedling blight caused by Globisporangium ultimum var. ultimum , and Goss's wilt that are efficient and high-throughput. We also introduce fluorescence microscopy techniques for leaf samples infected with Exserohilum turcicum , the causal agent of northern corn leaf blight. These pathogens all cause significant yield losses, and in particular, Gibberella ear rot is associated with the accumulation of harmful mycotoxins. Understanding how pathogens cause disease and how plants defend against attack is a major goal of maize pathology studies and critical for developing integrated management strategies.
Why it matches plant phenotyping methodsトウモロコシ病害の接種および病害重症度評価法をレビューし、高スループットで一貫した植物病害表現型の取得を扱うため、方法論が中心です。感染葉の蛍光顕微鏡法も紹介されています。
abstractInoculation methods must be high-throughput to accommodate the large screening experiments.
Plant diseases are one of the main limiting factors in global agricultural productivity, causing significant losses and compromising food security. The increasing complexity of production systems and the limitations of traditional diagnostic methods, based mainly on visual assessment and laboratory analyses, have driven the incorporation of artificial intelligence (AI) in plant pathology. In this context, the present study aimed to synthesize the advances, challenges, and gaps related to the application of AI in the detection, monitoring, and forecasting of plant diseases. This is an integrative literature review, conducted through systematic searches in national and international scientific databases, encompassing studies that addressed machine learning techniques, deep learning, and hybrid models applied to plant pathology. Approaches based on RGB images, multispectral and hyperspectral data, integration with unmanned aerial vehicles (UAVs), and forecasting models based on climatic variables were analyzed. The results show that convolutional neural networks and temporal architectures, such as LSTM, have substantially increased the diagnostic accuracy and forecasting potential of the systems, especially when integrated with environmental data. However, challenges persist related to the generalization of the models, scarcity of representative databases, field variability, and high computational cost. It is concluded that AI represents a strategic tool for the transition from a from a reactive phytopathology to a predictive and decision-support approach. However, its consolidation under real cultivation conditions depends on robust agronomic validation, methodological standardization, and multidisciplinary integration, aiming at more precise, sustainable systems applicable to precision agriculture.
Why it matches plant phenotyping methods植物病害の画像・マルチスペクトル・ハイパースペクトル観測とAIによる検出・予測を主題とするレビューであり、植物状態（病害）の取得・推定手法が中心です。
abstractthe present study aimed to synthesize the advances, challenges, and gaps related to the application of AI in the detection, monitoring, and forecasting of plant diseases.
Knowing how much information a single pixel can provide is not just a technical issue; it shapes what we learn, and what we will learn, from the field. This article examines how pixel size governs the capture and interpretation of environmental and phenotypic information in remote sensing, phenomics, enviromics, and precision breeding. Spatial resolution, expressed as Ground Sample Distance (GSD), connects image scale to biological meaning, with direct implications for data quality, model accuracy, and the interpretation of genotype × environment (GEI) interactions. The discussion spans multiple observation platforms: ( i ) satellites provide meter-scale data for regional and temporal monitoring; ( ii ) drones offer centimeter-level imagery suited to within-plot variation and high-throughput phenotyping; and ( iii ) intermediate resolutions connect detail, comparability, and computational efficiency. When spatial resolution is mismatched with the biological process, information loss occurs through spectral mixing, aggregation biases, and distortion of derived indices such as NDVI, canopy temperature, and biomass. Spatial scale can also be transformed through superpixel aggregation, which converts fine raster grids into homogeneous spatial objects, and through subpixel refinement, which disaggregates coarse pixels to recover local heterogeneity. Empirical evidence shows that predictive ability improves when the spatial scale of environmental covariates aligns with the ecological and experimental scale under study. These concepts extend to experimental design, Target Population of Environments (TPE) mapping, and recommendation zoning through GEI mapping. This review treats spatial resolution strategically as a modeling parameter, not as a fixed technical constraint. Choosing pixel size through sensitivity analysis and study objectives helps align environmental representation, predictive modeling, and comparability across experiments. We also discuss perspectives involving autonomous sensing, multiscale data processing, computational infrastructure, and the use of different spatial scales for genomic and genomic–enviromic prediction
Why it matches plant phenotyping methods植物表現型解析における画像の空間解像度、スケール変換、予測精度への影響を中心に扱う方法論的レビューであり、表現型情報の取得・解釈が主要テーマである。
abstractThis article examines how pixel size governs the capture and interpretation of environmental and phenotypic information in remote sensing, phenomics, enviromics, and precision breeding.
ABSTRACT Improving genetic gain and optimizing agronomic practices are fundamental to ensuring global food security. Phenotyping plays a pivotal role in accelerating genetic gain, and recent advancements in high-throughput technologies—particularly those based on remote sensing—have significantly enhanced phenotyping capacities. However, the widespread adoption of these innovations has been constrained by high operational and infrastructure costs. In response, affordable yet accurate phenotyping solutions are emerging, enabling large-scale deployment beyond elite research settings. The integration of artificial intelligence (AI) to process and analyze phenotypic data and the open-source nature of the supporting software, combined with the synergistic power of information and communication technologies, is accelerating the development of scalable and cost-effective phenotyping systems. An example of the application capabilities associated with AI is the development in recent years of smartphone-based phenotypic platforms that process information in the cloud. Additionally, the potential use of satellites as future phenotyping platforms promises to further reduce costs and expand access. These low-cost solutions encompass a broad array of components, including sensors, platforms, data processing pipelines, and decision-support tools, collectively ushering in a new era of accessible phenotyping.
Why it matches plant phenotyping methods低コスト植物フェノタイピング技術を総説し、センサー、プラットフォーム、データ処理、AI解析、スマートフォンおよび衛星による測定系を中心に扱っているため、方法論レビューとして適格。
abstractPhenotyping plays a pivotal role in accelerating genetic gain, and recent advancements in high-throughput technologies—particularly those based on remote sensing—have significantly enhanced phenotyping capacities.
Main conclusion The progress of soybean phenotypic detection and intelligent sensing technologies has been reviewed under salt-alkali stress , and an integrated approach combining three-dimensional imaging with near-infrared spectroscopy has been proposed to construct full-spectrum three-dimensional images. The approach could provide a reference for the breeding of salt-alkali-tolerant soybean varieties and the optimization of cultivation practices. Soil saline-alkali is one of the major environmental factors limiting global agricultural development, posing a serious challenge to normal crop growth, resource use efficiency, and sustainable agricultural development. Soybeans are a vital oilseed crop and plant-based protein source, and their phenotypic traits are significantly affected by saline-alkali stress, severely limiting soybean grain yield and quality. With the rapid advancement of technologies such as intelligent sensing and big data, this progress has driven new developments in plant phenomics detection, offering fresh insights into germplasm resource evaluation, breeding, gene function, and the cultivation of salt-alkali stressed soybeans. This article introduces the impact of salinity-alkali stress on soybean "phenotype-environment-gene" information, reviews the technical progress and application fields of traditional phenotypic detection methods for obtaining various phenotypic indicators across crops, and focuses on a rapid detection method of soybean phenotype under salinity-alkali stress. This paper analyzes the current state of research on detecting phenotypic indicators of soybeans under saline-alkali stress using intelligent sensing methods, including near-infrared spectroscopy, image recognition, and three-dimensional imaging. It is anticipated that through the integration of three-dimensional imaging and near-infrared spectroscopy, forming "full-spectrum three-dimensional images" with spatial structure and spectral information, this approach will advance the breeding and cultivation of superior salt-alkali tolerant soybean varieties through "intelligent data-driven" methods.
Why it matches plant phenotyping methods植物フェノタイピング指標の迅速検出技術を中心に、画像認識、三次元 imaging、近赤外分光などをレビューし、統合的な表現型取得法を提案する方法論的レビューである。
abstractThe progress of soybean phenotypic detection and intelligent sensing technologies has been reviewed under salt-alkali stress
Plant phenotyping relevance match · UnverifiedCrossref · OpenAlex · Europe PMC · checked 5 Sept 2026
Abstract Climate change increasingly threatens global agriculture by intensifying abiotic stresses and destabilizing crop productivity, necessitating a deeper understanding of root-mediated traits governing resource acquisition and stress resilience. Here, we synthesize recent advances in root-centred plant phenomics, emphasizing how high-throughput phenotyping enables high-resolution, scalable characterization of complex root traits and robust comparative analysis across diverse genotypes and environments. Innovations in multimodal imaging, notably X-ray computed tomography, MRI, and machine learning-integrated rhizotrons, facilitate detailed reconstruction of root system architecture and its temporal dynamics under both controlled and semi-field conditions. Furthermore, root phenotyping is increasingly interpreted within an integrated whole-plant framework. The integration of organ-specific assessments with physiological phenomics leveraging spectral and thermal data enables the characterization of developmental plasticity and root-mediated processes, including water-use dynamics, nutrient acquisition, and canopy stress responses under heterogeneous field conditions. These approaches link root traits such as rooting depth and spatial distribution to canopy-level physiological responses under stress. Despite these advances, significant bottlenecks persist in data interoperability, analytical scalability, and protocol standardization. Future progress will require integration of root phenomics with genomics, predictive modelling, and digital twin frameworks to improve resource-use efficiency, yield stability, and climate resilience in global cropping systems.
Why it matches plant phenotyping methods根系フェノタイピングの高スループット画像化、計算ツール、機械学習統合、データ標準化を中心に扱う方法論レビューであり、植物形質の取得・解析手法が主題である。
titleAdvances in root phenotyping: high-throughput imaging, computational tools, and integrative approaches for crop improvement.
Abstract Tomato diseases significantly affect crop productivity and food security, necessitating accurate and timely detection methods. This paper presents a systematic and analytical review of deep learning approaches for tomato disease detection and severity assessment, based on 76 research studies. Existing methods are categorized into classification, detection, segmentation, and emerging multi-task frameworks. The analysis shows that convolutional neural networks achieve high accuracy on controlled datasets but exhibit limited generalization in real-world conditions. Advanced architectures, including transformer-based and hybrid models, improve performance but increase computational complexity. A key finding is the limited focus on disease severity assessment, which remains underexplored despite its importance for precision agriculture. The review identifies major challenges, including dataset limitations, lack of standardized benchmarks, and deployment constraints. Future directions emphasize multi-task learning, real-world dataset development, lightweight models, and explainable AI. This study provides a foundation for developing robust and practical tomato disease detection systems.
Why it matches plant phenotyping methodsトマト病害の検出・重症度評価という植物状態の画像推定手法を、研究・データセット・課題の観点から体系的にレビューしており、フェノタイピング手法のレビューが中心である。
abstractThis paper presents a systematic and analytical review of deep learning approaches for tomato disease detection and severity assessment, based on 76 research studies.
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 5 Sept 2026
Climate change is increasing the frequency of compound drought and heat events, threatening forest stability worldwide. While genomics has helped identify resilient genotypes, our ability to characterize adaptive traits - phenotyping - has not kept pace. This creates a bottleneck: we can sequence trees faster than we can understand how they physically respond to stress. Moving away from single-sensor monitoring, the field is now embracing multi-sensor data fusion, in which thermal imaging, Solar-Induced Fluorescence (SIF), hyperspectral remote sensing, and LiDAR are combined on platforms ranging from Unmanned Aerial Vehicles (UAVs) to ground-based robotic systems. These integrated approaches are proving effective for detecting physiological stress - such as changes in stomatal conductance - before visible damage appears. Deep learning models, meanwhile, are beginning to outperform traditional vegetation indices for specific tasks such as tree-crown segmentation and stress classification, although their performance remains constrained by overfitting, limited transferability, and domain shift across forest types in analyzing complex forest canopies. A major limitation remains, however: most high-throughput phenotyping (HTP) focuses on the canopy, largely ignoring the root system and the soil-plant-atmosphere continuum (SPAC), which are critical for drought resilience. In this review, we argue that developing climate-resilient forests requires looking below the canopy. We propose a constraint-based framework that couples aerial sensor data with eco-hydrological approaches and process-based modeling to narrow the range of plausible root functional strategies-rather than to directly identify root phenotypes, while critically evaluating the assumptions and validation challenges inherent in this approach. Future research should focus on standardized protocols, open benchmark datasets, and Explainable AI (XAI) to strengthen the link between above-ground signals and below-ground traits.
Why it matches plant phenotyping methods植物フェノタイピング手法を中心に、マルチセンサー融合、深層学習、検証課題、標準化・ベンチマークをレビューしているため。
abstractIn this review, we argue that developing climate-resilient forests requires looking below the canopy.
Photosynthesis is the fundamental biological process that introduced oxygen into Earth's atmosphere and continues to power life, from the earliest single-celled organisms to entire global ecosystems. Yet, measuring photosynthesis across scales has been challenging because traditional techniques have not transcended scales. The emergence of remote-sensing techniques to measure solar-induced chlorophyll fluorescence (SIF) provides a unique approach to estimate photosynthesis across spatiotemporal scales, representing a new age for optical remote sensing to study photosynthesis and shaping the decades of satellite SIF research. Here, focusing on spatiotemporal scales, we review the mechanisms that drive the relationship between SIF and photosynthesis. Remotely sensed SIF is modulated by biological drivers, environmental drivers, the interaction between biological and environmental drivers, and the viewing geometry. Studying fluorescence at small scales provides the ecophysiological understanding needed to disentangle the biological and environmental drivers of SIF at larger scales. Leveraging progress in satellite SIF, future research should focus on cross-scale mechanistic understanding of the drivers of SIF and using SIF as a metric for plant function beyond photosynthesis.
Why it matches plant phenotyping methods植物の光合成・機能を推定するリモートセンシング手法（SIF）を中心に、その機構とスケール間利用をレビューしており、植物フェノタイピング手法のレビューに該当する。
abstractThe emergence of remote-sensing techniques to measure solar-induced chlorophyll fluorescence (SIF) provides a unique approach to estimate photosynthesis across spatiotemporal scales
Field / plotChlorophyll fluorescenceCell / cellular structureWhole plant / canopy / plot / field
The advent of spatial and quantitative biology has led to immense advances in understanding the complex inner workings of plants, down to the molecular scale. Functional imaging of live plants, which enables the spatial and quantitative mapping of biochemical cues, physicochemical properties of cellular structures, and the dynamics of physical and chemical signals with unprecedented resolution, has become a key technology for advancing the mechanistic understanding of plant cell biology. In this review, we highlight progress in live functional imaging in plants through the use and development of chemical fluorescent probes, which enable plant functional imaging without requiring genetic manipulation of the study object. We explain how probes sense, target, and report on functional features within the plant cell; discuss their limitations, including toxicity; and provide case studies to exemplify how these tools can complement biological studies to unravel the complex machinery that makes plants work. We conclude by outlining the expected future development of this field and identifying key challenges that lie ahead.
Why it matches plant phenotyping methods植物の生体機能を空間的・定量的に可視化する化学蛍光プローブの開発と利用を扱うレビューであり、植物イメージング手法が中心です。
abstractIn this review, we highlight progress in live functional imaging in plants through the use and development of chemical fluorescent probes
Published20 May 20262026 7th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV)Cited by 0 · OpenAlex ↗
The issue of plant diseases remains a significant threat to the worldwide food production and requires solutions to disease detection that are fast, accurate and scalable. Conventionally applied methods of diagnosis, including: hand field scouting and lab tests, are too slow, labor-intensive, and subject to human error, particularly during large scale cultivation. Recent technological progress in Artificial Intelligence (AI) and Machine Learning (ML) has brought in the groundbreaking solutions to early and accurate prediction of the disease. In this paper, the author will review how AI-based models, such as Convolutional Neural Networks (CNNs), Random Forest, Support Vector Machines (SVM), and hybrid deep learning models can be used to detect plant diseases on the basis of visual information, as well as environmental data. These models are very productive in recognizing patterns, automated feature extraction, and real-time prediction, and they are frequently much more precise than their human counterparts. Early warning systems and precision agriculture are further improved by the integration of the IoT sensors, drones, and satellite imagery. Regardless of the issues concerning the lack of data, model generalization, computational cost, and adoption of AI and ML on a farmer level, there are considerable prospects to enhance crop protection, minimizing yield losses, and sustainable agriculture. The paper identifies the current progress, limitations and future research in the development of strong, availability and scaleable AI-based plant disease prediction systems.
Why it matches plant phenotyping methods植物の葉画像から病徴・病害状態を推定するAI手法を中心に扱うレビューであり、植物フェノタイピング手法レビューに該当する。
abstractThe paper identifies the current progress, limitations and future research in the development of strong, availability and scaleable AI-based plant disease prediction systems.
Plant disease and pest surveillance is undergoing a profound technological transition. Conventional crop protection has historically depended on episodic field scouting, expert visual inspection, and broad-spectrum preventative spraying, all of which are constrained by labour intensity, uneven diagnostic accuracy, and weak temporal resolution. In contrast, recent advances in artificial intelligence, deep learning, the Internet of Things, remote sensing, and edge computing have enabled crop-health monitoring systems that are more continuous, data-rich, and spatially explicit. This review analyses the evolution of AI-driven plant disease and pest surveillance, with particular attention to how image-based deep learning, connected environmental sensing, unmanned aerial vehicle platforms, cloud-edge infrastructures, and multimodal analytics are reshaping next-generation crop protection. The article argues that the central innovation is not merely automated diagnosis, but the emergence of surveillance ecosystems capable of recognising symptoms, estimating risk, localising hotspots, and informing more selective intervention. The review synthesises major developments in convolutional neural networks, object detection, semantic segmentation, transfer learning, domain adaptation, transformer-based computer vision, anomaly detection, environmental time-series modelling, and multimodal analytics. It also evaluates the practical obstacles that still limit real-world deployment, including dataset bias, annotation uncertainty, poor cross-domain generalisation, limited interoperability, energy and connectivity constraints, weak model explainability, and uneven economic accessibility. The article further considers how AI-based surveillance may strengthen integrated pest management by supporting earlier warning, more precise treatment timing, reduced blanket pesticide use, and stronger alignment between biological risk and management action. It concludes that the future of crop protection will depend less on isolated improvements in benchmark accuracy and more on the development of trustworthy, scalable, and biologically meaningful surveillance systems that can support sustainable decisions under real agricultural conditions.
Why it matches plant phenotyping methods植物病害の症状認識・リスク推定・ホットスポット局在化を行う画像解析、センサー、UAV、マルチモーダル手法を中心にレビューしており、植物の病害状態を推定するフェノタイピング手法レビューに該当する。
abstractThis review analyses the evolution of AI-driven plant disease and pest surveillance, with particular attention to how image-based deep learning, connected environmental sensing, unmanned aerial vehicle platforms, cloud-edge infrastructures, and multimodal analytics are reshaping next-generation crop protection.
Plant leaf disease detection (PLDD) is a growing active research area with burgeoning practical applications across various sectors such as agricultural monitoring, food security, and environmental conservation. Accurate segmentation and classification of plant leaf diseases remains a key challenge in the field of plant leaf disease prediction. The challenge demands automated methods for the plant disease identification because it needs to develop better crop management systems, which will boost agricultural production. In this article, we provide a systematic review of various machine learning (ML) and deep learning (DL) methods extensively used for PLDD. The review strategy follows a formal protocol, involving structured search, screening, and analysis of studies published between 2020 and 2024. We have proposed a taxonomy of PLDD methods that will be useful for experts and researchers working in this exciting research area. The review thoroughly examines techniques for both segmentation and classification of the PLDD workflow. In addition, we examine several public and private datasets that are accessible to study plant diseases and highlight their significance in developing accurate diagnostic models. The paper also presented multiple performance assessment criteria that researchers can use to evaluate PLDD methods at present and in the future. The study also discusses the current challenges in plant leaf disease classification and offers essential insights about upcoming developments and potential enhancements. The research findings from this study provide essential knowledge that helps experts and researchers to develop automated systems to detect and classify plant leaf diseases effectively.
Why it matches plant phenotyping methods植物葉の病徴を画像から検出・分類する手法を対象とした系統的レビューであり、セグメンテーション、分類、データセット、評価指標を中心に扱うため、植物フェノタイピング手法レビューに該当する。
abstractIn this article, we provide a systematic review of various machine learning (ML) and deep learning (DL) methods extensively used for PLDD.
Crop attribute detection, as a key component of intelligent agricultural harvesting machinery, plays a crucial role in harvesting efficiency, loss reduction, and autonomous operation control. Compared with existing reviews on artificial intelligence and sensing technologies in agriculture, this review focuses on crop attribute detection scenarios oriented toward the intelligent decision-making and control requirements of agricultural harvesting machinery. It mainly analyzes crop attributes that affect harvesting operations, as well as the sensors and algorithms involved in detecting these attributes, and further clarifies the relationship between detection methods and control decisions in agricultural harvesting machinery. For grain crops, the key attributes relevant to harvesting operations include plant height, plant density, spike number, crop lodging, canopy structure, and crop position. For fruit and vegetable crops, the key attributes relevant to harvesting operations include maturity, position, and quality. From the perspectives of multi-source data acquisition, data analysis, and attribute detection algorithms, the key technologies in the field of crop attribute detection are systematically summarized and analyzed, including sensors used in crop attribute detection, such as RGB, spectral, near-infrared, and LiDAR sensors, as well as data analysis and recognition approaches, such as image classification, object detection, and point cloud analysis. The complexity of field environments and the dynamics of machine operation are analyzed, highlighting the technical bottlenecks of current detection systems in environmental adaptability, real-time responsiveness, and resistance to interference. To address these challenges, feasible optimization directions were proposed, including multi-sensor fusion, weakly supervised learning, and few-shot learning. This review aims to provide systematic references and theoretical support for the coordinated development of crop detection and control decision-making in intelligent agricultural harvesting systems.
Why it matches plant phenotyping methods収穫機械向けではあるが、草丈・密度・穂数・倒伏・群落構造・成熟度など植物の形態・状態を検出するセンサーと解析手法を体系的にレビューしており、表現型取得法が中心である。
titleA Review of Crop Attribute Detection for Agricultural Harvesting Machinery
ABSTRACT - Sugarcane is one of the most important commercial crops worldwide but its productivity is greatly affected by diseases such as red rot, rust, mosaic, smut and yellow leaf disease. Conventional disease detection techniques are based on manual inspection which is a time-consuming, labor-intensive and error prone process. This paper gives a detailed review of the deep learning methods for the automated detection of sugarcane diseases with a special focus on the fusion methods of stem and leaf features. Different deep learning architectures such as CNN, VGG, ResNet, EfficientNet, DenseNet, MobileNet, and YOLO are analyzed and compared in terms of accuracy, efficiency, and deployment capability. The study also explores multimodal approaches, such as hyperspectral imaging, thermal imaging and environmental data integration, to enhance prediction performance. Reported results show that advanced models like EfficientNet-B7 and DenseNet201 achieve accuracies above 99%, while lightweight models like MobileNet allow for real-time mobile deployment. The review highlights significant research gaps such as small datasets, lack of stem-leaf fusion studies, no severity classification, and real-world deployment issues. Future research directions are related to explainable AI, multimodal fusion, lightweight edge computing models, and precision agriculture applications for sustainable sugarcane cultivation. Key Words: Sugarcane disease detection, Deep learning, CNN, Stem-leaf fusion, Computer vision, Precision agriculture.
Why it matches plant phenotyping methodsサトウキビ病害の画像・深層学習による検出手法を中心にレビューしており、植物の病態を観測・推定するフェノタイピング手法レビューに該当する。
abstractThis paper gives a detailed review of the deep learning methods for the automated detection of sugarcane diseases with a special focus on the fusion methods of stem and leaf features.
Phenomics, which involves the holistic analysis of plant phenotypes using cutting-edge sensing and data processing technologies, has emerged as an AI-powered technique in plant breeding. Genomics tells us about a plant's genetic potential, whereas phenomics describes the dynamic manifestation of the genes under different environmental conditions. By combining high-throughput phenotyping technologies with AI and machine learning (ML) techniques, complex agronomic traits can be assessed rapidly, accurately and non-destructively, thus speeding up breeding. Advancements in phenotyping technologies, including hyperspectral and multispectral imaging, thermal sensors, LiDAR (Light Detection and Ranging), unmanned aerial vehicles (UAV) and ground robotic systems, provide vast amounts of information about plant growth, physiology, stress, disease, yield potential and other traits. The AI methods such as computer vision and deep learning process the data to discern patterns, forecast traits and detect stress or disease. This helps overcome the phenotyping bottleneck in conventional breeding and improves selection accuracy. AI-based phenomics integrates genomics, phenomics and environmental information to facilitate predictive breeding and mapping of genotype to phenotype to breed climate-adapted, high-yielding varieties. It also helps in precision agriculture for monitoring crops and resource allocation. Phenomics studies are being used in crops like rice, wheat, maize, barley, sorghum and soybean. In India, rice and wheat are extensively studied for high-throughput phenotyping for drought and heat tolerance. Addressing data standardisation and infrastructure issues, phenomics is a disruptive technology, bringing together the genetic potential and field performance for sustainable crop improvement.
Why it matches plant phenotyping methods植物フェノミクス、センシング、画像解析、AIによる形質推定を体系的に扱うレビューであり、フェノタイピング手法が中心です。
abstractPhenomics, which involves the holistic analysis of plant phenotypes using cutting-edge sensing and data processing technologies, has emerged as an AI-powered technique in plant breeding.
Artificial intelligence (AI)-enabled camera sensor systems are increasingly transforming precision agriculture by providing non-destructive, rapid, and scalable methods for monitoring crop health. Two of the most critical applications are the detection of crop water stress and the assessment of pesticide requirement through pest, disease, and symptom recognition. This literature review synthesizes published work on RGB, thermal, multispectral, and hyperspectral imaging integrated with machine learning and deep learning methods for agricultural decision support. The reviewed studies show that thermal and hyperspectral imaging are particularly effective for water stress detection, whereas RGB and multispectral systems are highly practical for identifying disease symptoms, pest infestation, and spray targets. The literature further indicates a shift from simple classification toward real-time decision support, multimodal fusion, explainable AI, and precision input application. This review discusses core sensing technologies, major algorithmic approaches, research findings from key studies, present limitations, and future research directions. Overall, AI camera sensor systems offer substantial potential for reducing water wastage, minimizing excessive pesticide use, and improving sustainable agricultural productivity.
Why it matches plant phenotyping methods作物の水ストレスや病害症状を画像・センサーから推定する手法を中心に整理したレビューであり、植物状態の取得・推定方法が中核です。
abstractThis literature review synthesizes published work on RGB, thermal, multispectral, and hyperspectral imaging integrated with machine learning and deep learning methods for agricultural decision support.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 5 Sept 2026
X-ray / CTRootMorphology / geometry measurement2D/3D reconstructionRoot system architecture
Summary Plant–microbe interactions are inherently spatial, yet the physical structure of the soil and rhizosphere is rarely treated as a mechanistic variable in experimental design. X‐ray computed tomography (X‐ray CT) enables nondestructive, three‐dimensional, and time‐resolved imaging of intact root–soil systems, providing direct access to the structural context in which plant–microbe interactions occur. Rather than a secondary imaging technique, X‐ray CT can offer a wealth of data as a primary experimental platform for future plant–microbe research. Here, we highlight key structural traits that X‐ray CT can quantify and discuss how they may shape microbial behaviour, plant immune responses, and disease outcomes. We expand on how X‐ray CT could be employed in future to provide a framework to disentangle direct microbial effects from indirect, structure‐mediated feedbacks. For breeding and management, it could enable selection for root traits and soil practices that engineer favourable microhabitats rather than targeting organisms in isolation. Despite this potential, broader adoption will require overcoming current limitations related to access to instrumentation, analytical expertise, and the integration of structural data with biological measurements. Overall, we suggest that resolving these issues will enable the integration of X‐ray CT‐derived structure with molecular, microbiome, and modelling approaches to enable the development of digital rhizospheres, offering a pathway from descriptive observations to predictive, structure‐aware in silico frameworks in plant–microbe research.
Why it matches plant phenotyping methodsX線CTを用いて根・土壌系の構造形質を定量する方法を、植物・微生物相互作用研究の主要な実験プラットフォームとして論じる方法論レビューであり、植物フェノタイピング手法が中心です。
abstractX‐ray computed tomography (X‐ray CT) enables nondestructive, three‐dimensional, and time‐resolved imaging of intact root–soil systems, providing direct access to the structural context in which plant–microbe interactions occur.
Crop diseases continue to pose a serious danger to agricultural productivity worldwide, resulting in large losses in crop quality, yield, and economic value. For large-scale farming, traditional disease detection techniques, which mostly rely on specialist knowledge and manual examination, are frequently laborious, subjective and ineffective. Deep learning (DL), a branch of artificial intelligence, has become a potent method for automated and precise crop disease prediction because to developments in information technology. With an emphasis on image-based analysis and data-driven modelling, this paper provides a thorough overview of current advancements in deep learning-based methods for crop disease diagnosis and prediction. Convolutional Neural Networks (CNNs), one type of deep learning architecture, have shown exceptional performance in reliably diagnosing different crop illnesses and extracting complicated characteristics from plant photos. The detection accuracy has been further enhanced by advanced versions like ResNet, VGGNet, and EfficientNet, which frequently surpass 95 percentage under controlled circumstances. Precision agriculture techniques have been improved by the real-time monitoring and early disease identification made possible by the integration of deep learning with Internet of Things (IoT) devices, remote sensing technologies, and drone-based imaging systems. Despite these developments, a number of problems still exist, such as the requirement for sizable labelled datasets, high processing demands, overfitting problems, and restricted model generalisation in practical settings. This paper identifies these drawbacks and explores possible remedies, such as explainable deep learning methods, data augmentation, and transfer learning. Future research will focus on integrating intelligent decision-support systems, scalable deployment approaches, and edge computing. All things considered, deep learning-based crop disease prediction systems have enormous potential to revolutionise contemporary agriculture by facilitating early intervention, enhancing crop health management, and encouraging sustainable farming methods.
Why it matches plant phenotyping methods植物画像から病害状態を推定する深層学習手法を中心に扱うレビューであり、植物フェノタイピング手法レビューに該当する。
abstractWith an emphasis on image-based analysis and data-driven modelling, this paper provides a thorough overview of current advancements in deep learning-based methods for crop disease diagnosis and prediction.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 5 Sept 2026
Global changes in agricultural and environmental systems will necessitate new crop research methodologies in the future years to ensure more effective use of natural resources and food security. The progress in next-generation sequencing has led to the emergence of multi-omics techniques as successful crop improvement strategies. Multi-omics studies using high-throughput techniques have been critical in understanding growth, senescence, yield, and biotic and abiotic stress responses in an array of crops. When multi-omics provide a high-resolution map of the molecular frameworks governing stress responses, advanced deep phenotyping systems can utilize advanced sensors to quantify dynamic physiological and morphological traits non-destructively. The systematic integration of these multi-layered datasets through association mapping and machine learning frameworks allows for the identification of superior alleles and regulatory hubs. Currently, the non-invasive imaging methods have effectively incorporated computer vision, machine learning, and deep learning components of AI. The use of machine learning and deep learning have progressively increased the effectiveness of data gathering and analysis. The supervised, unsupervised, and deep learning architectures have become effective tools for overcoming the genotype-to-phenotype gap, enabling more accurate predictions of yield and stress tolerance. Despite challenges related to data dimensionality, high infrastructure costs, and the need for standardized protocols, the convergence of these fields offers a robust architecture for predictive breeding. By linking microscopic molecular shifts to macroscopic field performance, integrated strategies accelerate the discovery of adaptive traits and the delivery of high-yielding, climate-smart cultivars. This review examines the revolutionary potential of combining deep phenotyping and multi-omics data for developing a thorough, high-throughput crop improvement strategy that can revolutionize crop breeding.
Why it matches plant phenotyping methods深層フェノタイピングと非破壊センサー・画像解析を中心に、作物形態・生理形質の高スループット計測とマルチオミクス統合を論じる方法論的レビューである。
abstractThis review examines the revolutionary potential of combining deep phenotyping and multi-omics data for developing a thorough, high-throughput crop improvement strategy that can revolutionize crop breeding.
Soils exhibit remarkable spatial heterogeneity in environmental conditions, which plants perceive at the levels of the whole root system, individual roots, and root tissues. Cropping practices aimed at reducing the environmental footprint of agriculture are likely to intensify this heterogeneity, highlighting the urgent need to adapt crops to heterogeneous soil environments. Recent advances in soil imaging and spatial omics offer unprecedented opportunities to decipher the molecular, physiological, and ecological processes that underpin plant-soil interactions. In this review, we explore the substantial yet largely untapped potential of integrating soil imaging with spatial omics to uncover the fundamental mechanisms that control root foraging in heterogeneous soils. We present an overview of key imaging and molecular approaches that have particular potential for revealing root foraging behavior. To demonstrate their capabilities for generating spatially explicit insights into root-soil interactions, we highlight selected case studies covering both biotic (beneficial and detrimental soil organisms) and abiotic (physical and chemical soil properties) factors. Finally, we outline a workflow for integrating spatial omics with soil imaging through vertical integration of experimental studies across levels of environmental complexity, coupled with predictive modeling. Unlocking the full potential of these approaches will require linking molecular, physiological, and ecological mechanisms at the root-soil interface to whole-plant growth and crop productivity. These fundamental insights into the edaphic drivers of root foraging will be essential for guiding crop adaptation to future, more heterogeneous soil environments.
Why it matches plant phenotyping methods根の探索行動や根系・根組織の状態を可視化・解析する土壌イメージング手法を空間オミクスと統合するレビューであり、植物表現型取得・解析の方法論が中心です。
abstractRecent advances in soil imaging and spatial omics offer unprecedented opportunities to decipher the molecular, physiological, and ecological processes that underpin plant-soil interactions.
Growth chamberGrowth / time-series analysisGrowth / development / phenology
Plant factories have evolved from automated cultivation facilities into data-driven crop production systems. Over the last decade, artificial intelligence has been applied to non-destructive crop monitoring, sensor correction, nutrient-solution diagnosis, growth prediction, environmental control, digital twins, and product-level inspection. This review summarizes AI technologies for plant factories, focusing on machine vision, deep learning, nutrient-solution intelligence, reinforcement learning, and digital-twin interfaces. The main argument is that plant-factory AI should not be understood only as image-based phenotyping; practical systems require an integrated intelligence stack connecting visual perception, sensor calibration, nutrient modeling, control, remote operation, and industrial inspection. Remaining challenges include dataset scarcity, model generalization, sensor drift, explainability, energy-aware control, and closed-loop decision-making.
Why it matches plant phenotyping methods植物工場における機械視覚・センサー補正・作物モニタリングなどのフェノタイピング関連技術を中心に扱うレビューであり、方法論的役割が明確。
abstractThis review summarizes AI technologies for plant factories, focusing on machine vision, deep learning, nutrient-solution intelligence, reinforcement learning, and digital-twin interfaces.
Plant factories have evolved from automated cultivation facilities into data-driven crop production systems. Over the last decade, artificial intelligence has been applied to non-destructive crop monitoring, sensor correction, nutrient-solution diagnosis, growth prediction, environmental control, digital twins, and product-level inspection. This review summarizes AI technologies for plant factories, focusing on machine vision, deep learning, nutrient-solution intelligence, reinforcement learning, and digital-twin interfaces. The main argument is that plant-factory AI should not be understood only as image-based phenotyping; practical systems require an integrated intelligence stack connecting visual perception, sensor calibration, nutrient modeling, control, remote operation, and industrial inspection. Remaining challenges include dataset scarcity, model generalization, sensor drift, explainability, energy-aware control, and closed-loop decision-making.
Why it matches plant phenotyping methods植物工場におけるAI技術レビューで、非破壊的な作物モニタリング、機械視覚、深層学習、センサー補正など、植物形質取得に関わる方法を中心的に扱っている。
abstractThis review summarizes AI technologies for plant factories, focusing on machine vision, deep learning, nutrient-solution intelligence, reinforcement learning, and digital-twin interfaces.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 15 Sept 2026
Field / plotWhole plant / canopy / plot / fieldPhysiological trait estimationGrowth / time-series analysisWater status / transpiration
Summary Plant water potential is a central integrator of plant water status, linking hydraulic function with physiological performance and ecosystem water dynamics across species and systems. This review is motivated by the need to capture these dynamics under rapidly changing environmental conditions, which are often missed by discrete measurements. We evaluate the main approaches for continuous monitoring of plant water potential, including direct in situ sensors, indirect methods based on plant water content, and remote‐sensing proxies. We discuss the principles, measurement mechanisms, practical constraints, and environmental sensitivities of each approach. Relative to traditional methods, such as pressure chambers, continuous measurements offer major advantages by resolving rapid variation in water status and strengthening inference on plant–soil–atmosphere interactions. These approaches are especially valuable under dynamic field conditions, where temporal variability in vapor pressure deficit, soil moisture, temperature, and radiation strongly shapes hydraulic behavior. We conclude that continuous monitoring has substantial potential to advance plant and ecosystem science, but wider application will depend on careful interpretation and greater harmonization across comparable methodologies. By synthesizing core principles, methodological challenges and best practices, this review provides a practical framework for researchers and practitioners applying continuous water potential measurements.
Why it matches plant phenotyping methods植物の水ポテンシャルという生理形質を連続測定するセンサー手法を比較・整理し、測定原理、制約、標準化、実践指針を扱う方法論レビューであり、フェノタイピング手法が中心である。
abstractWe evaluate the main approaches for continuous monitoring of plant water potential, including direct in situ sensors, indirect methods based on plant water content, and remote‐sensing proxies.
With increasing demand for fine-scale ecological management under carbon neutrality frameworks, multi-temporal assessment of carbon stock change (ΔC) at the individual-plant scale has become essential for understanding plant-level carbon dynamics and supporting management decisions. However, methodologies for repeated monitoring at this scale remain fragmented, showing limited cross-temporal comparability, weak cross-scale consistency, and insufficient integration across methods. Existing approaches can be grouped into three pathways: (i) process-based methods derived from CO2 exchange measurements, (ii) state-based approaches estimating biomass and ΔC, and (iii) sensing-based approaches using structural, spectral, thermal, and fluorescence signals. These approaches offer complementary strengths, yet none simultaneously achieve high accuracy, temporal continuity, and operational scalability for multi-temporal ΔC estimation. Among these, stock-based and structural approaches form the primary estimation pathways, while flux-based and functional sensing methods provide complementary constraints. This review synthesizes and compares these approaches in terms of their theoretical basis, spatial support, temporal characteristics, and uncertainty structures. To address the lack of methodological integration, we propose a structure–function–scale framework that links heterogeneous observations across spatial and temporal domains and emphasizes cross-scale consistency as a prerequisite for reliable ΔC estimation. Within this framework, we further examine how multi-source integration can connect structural and functional observations through segmentation, co-registration, scaling, temporal alignment, and uncertainty propagation. By integrating traditional measurement logic with emerging remote sensing technologies, this review provides a unified methodological framework for ΔC estimation and identifies key directions for advancing fine-scale carbon monitoring, spatiotemporally consistent data fusion, uncertainty-aware inference, and MRV-oriented verification systems.
Why it matches plant phenotyping methods個体植物スケールの炭素蓄積変化を推定するための測定・センシング・統合手法を体系的に比較し、セグメンテーションや不確実性伝播を含む統合枠組みを提案する方法論レビューであり、植物状態の取得・推定が中心である。
abstractmethodologies for repeated monitoring at this scale remain fragmented
Phenotypic traits represent the observable outcomes of interactions between plant genetic architecture and environmental conditions and form the foundation for understanding plant growth, adaptation, and productivity. With the rapid advancement of high-throughput phenotyping and phenomics platforms, trait evaluation has evolved from isolated measurements toward integrative, data-driven frameworks capable of capturing structural, physiological, and functional plant responses across spatial and temporal scales. However, the expanding diversity of measurable traits and analytical approaches has created a need for a coherent conceptual framework that organizes phenotypic traits in a biologically meaningful and experimentally practical manner. This review addresses this gap by synthesizing existing knowledge and presenting a comprehensive classification of plant phenotypic traits based on measurement strategy, including direct and surrogate traits, as well as biological organization, developmental stage, functional relevance, environmental responsiveness, and genetic control. Particular emphasis is placed on the growing role of surrogate image-derived traits as scalable proxies for complex physiological processes, enabling rapid, non-destructive phenotyping across large populations. By integrating traditional trait concepts with modern imaging technologies, sensor systems, and data analytics, the review highlights how multidimensional trait classification strengthens genotype-phenotype interpretation, improves experimental design, and accelerates precision breeding efforts. Ultimately, this synthesis provides a unified perspective linking phenomics technologies with plant biology, offering a conceptual and methodological foundation for advancing crop improvement and developing climate-resilient agricultural systems.
Why it matches plant phenotyping methods植物フェノタイピングおよびフェノミクスの測定戦略、画像由来形質、センサー、データ解析を体系化する方法論的レビューであり、方法論が中心です。
abstractThis review addresses this gap by synthesizing existing knowledge and presenting a comprehensive classification of plant phenotypic traits based on measurement strategy
Abstract Fusarium head blight (FHB) of wheat ( Triticum aestivum L.) is primarily caused by the fungal pathogen Fusarium graminearum . This disease can cause significant economic loss due to decreasing yield, reducing seed quality, and the production of deoxynivalenol (DON); therefore, resistance to the disease is a primary concern for breeders. Phenotyping methods largely depend on the resistance mechanism being evaluated, but traditional approaches are often time‐consuming, subjective, and largely inaccurate. This review explores and contrasts traditional and modern phenotypic methods for various FHB resistance components. Digital image‐based phenotyping spans low‐cost RGB (red, green, blue) (i.e., Bayer array) sensors, multispectral sensors, and hyperspectral sensors. Across these sensors, approaches using spectral indices or deep learning have shown strong promise for detecting and classifying infection in both wheat spikes and kernels. Hyperspectral imaging has been largely explored and can be used to accurately estimate infection in spikes and kernels, as well as estimate DON content in the grain, using spectral indices or models input with specific wavebands. However, waveband‐specific approaches do not generalize well to new data, and hyperspectral imaging is significantly more resource‐intensive than RGB or multispectral cameras, limiting its practicality for most breeding programs. Phenotypic approaches using spectral indices and/or deep learning on digital images show the most potential for use in wheat breeding, due to their scalability and low cost. However, the widespread adoption of these techniques will depend on standardized imaging protocols, robust generalization across diverse genotypes, and effective integration into breeding pipelines.
Why it matches plant phenotyping methodsコムギ赤かび病抵抗性の表現型取得手法を、従来法からRGB・マルチスペクトル・ハイパースペクトル画像解析まで比較・レビューしており、フェノタイピング手法が中心である。
abstractThis review explores and contrasts traditional and modern phenotypic methods for various FHB resistance components.
Abiotic stresses such as heat waves significantly reduce wheat productivity by altering leaf anatomy and physiology, leading to reduced photosynthetic carbon assimilation and crop yield. Despite the advancement in various imaging technologies at the field, canopy, plant, tissue, cellular, and subcellular levels, phenotyping of imaging-based leaf structural traits (e.g. vein density, stomatal density, and stomatal aperture) for abiotic stresses is still time-consuming and expensive without the aid of artificial intelligence (AI) and machine learning (ML). This review consolidates current knowledge of wheat leaf structural and functional adaptations to heat stress and highlights key advancements in imaging technologies for studying these important phenotypic traits. Recent high-resolution, non-destructive imaging technologies, including confocal laser scanning microscopy, X-ray computed tomography, and optical coherence tomography, have enabled in vivo visualization of plants. Integrating these imaging techniques with AI/ML facilitates high-throughput phenotyping and the modelling of stress responses. We emphasize the potential for future research to leverage these technological advancements in imaging and AI, combining imaging data with physiological and multi-omics studies to deepen the understanding of plant heat tolerance mechanisms. Such multidisciplinary integration in leaf structure phenotyping will accelerate the development of resilient wheat varieties, offering critical insights for crop improvement in the face of climate change.
Why it matches plant phenotyping methods植物の葉構造・機能形質を対象とする画像計測技術とAI/MLによる表現型解析を中心に整理したレビューであり、植物フェノタイピング手法レビューに該当する。
abstractThis review consolidates current knowledge of wheat leaf structural and functional adaptations to heat stress and highlights key advancements in imaging technologies for studying these important phenotypic traits.
High-throughput phenotyping is a core prerequisite for breeding climate-resilient crops. To complete related breeding work, breeders must evaluate the performance of large-scale crop populations under seven types of field abiotic stresses including drought and high temperature, and the combined technology of unmanned aerial vehicle (UAV) imaging and artificial intelligence can provide core support to meet this demand. This review centers on three core sets of content: first, the integration of various UAV platforms, five types of imaging technologies, and machine learning and deep learning models to support phenotyping selection of abiotic stress-related traits; second, sorting out the biological significance of 12 categories of image-derived traits; third, breaking down the seven full workflow nodes ranging from flight planning to breeding decision support. Existing prior research on six crop types including wheat and rice has confirmed that this technology can improve the speed, scale and repeatability of field screening, and delivers outstanding effects when combined with multi-environment testing, genomic tools, and breeders’ expertise. This paper also sorts out six core limitations currently restricting the real-world deployment of this technology, and puts forward six future development directions to support its large-scale application.
Why it matches plant phenotyping methodsUAV画像とAIによる作物のストレス関連形質の取得・選抜ワークフローを中心に整理したレビューであり、植物フェノタイピング手法が中核です。
abstractThis review centers on three core sets of content: first, the integration of various UAV platforms, five types of imaging technologies, and machine learning and deep learning models to support phenotyping selection of abiotic stress-related traits;
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 5 Sept 2026
Plant phenotyping captures the integrated structural and functional traits of crops across cellular, tissue, organ, whole-plant, and population scales. It represents the outward expression of genotype-environment interactions and provides essential technological support for precision breeding, smart agriculture, and sustainable crop production. As farming shifts from experience-based to data-driven decision-making, the efficient acquisition and integrated analysis of phenotypic information at multiple spatial scales has emerged as a major research frontier at the intersection of agronomy, plant science, and agricultural engineering.
Why it matches plant phenotyping methods植物フェノタイピングの多尺度取得・統合解析を主題とするレビューであり、方法論分野を直接扱っている。
titleAdvancing multi-scale plant phenotyping for precision agriculture and sustainable crop production.
ABSTRACT Global food security is threatened by crop diseases and nutrient deficiencies. Traditional detection methods—visual scouting, molecular diagnostics and soil testing—are reactive and only identify problems once visible symptoms appear, which often misses intervention windows. This narrative review synthesizes 173 peer‐reviewed articles (from 2012 to 2025) to critically evaluate the synergistic potential of artificial intelligence (AI) and multisensor satellite remote sensing (RS) for presymptomatic detection. We propose a four‐principal framework: (1) sensor choice must align with pathogen infection strategy; (2) detection becomes actionable when spectral deviation exceeds twice baseline noise; (3) spectral time series can estimate epidemiological parameters (e.g., latent period, Area Under the Disease Progress Curve); and (4) explainable AI (XAI) converts black‐box predictions into interpretable diagnostics. Key findings uncovered were that multispectral sensors detect biotrophic pathogens 5–10 days pre‐symptomatically via red‐edge sensitivity; hyperspectral platforms offer 7–14 days warning and that thermal sensors detect vascular wilts 1–7 days earlier. Key challenges remain, including trade‐offs between resolution and revisit frequency, atmospheric interference causing 60%–80% optical data loss in tropical regions, spectral confusion between biotic and abiotic stresses, and limited scalability for smallholder farms (
Why it matches plant phenotyping methods衛星リモートセンシングとAIによる作物病害・栄養欠乏の早期検出手法を体系的に評価するレビューであり、植物の病害状態を推定するセンシング手法が中心です。
abstractThis narrative review synthesizes 173 peer‐reviewed articles (from 2012 to 2025) to critically evaluate the synergistic potential of artificial intelligence (AI) and multisensor satellite remote sensing (RS) for presymptomatic detection.
[Significance]The escalating complexity of genotype-phenotype-environment interactions and the explosive growth of multi-omics big data have necessitated a paradigm shift in crop breeding from empirical selection to intelligent design (Breeding 5.0). The aim of this paper is to systematically explore the underlying logic of the AI-driven crop breeding paradigm shift, comprehensively outline its generational evolution, analyze its core technical implementations in phenomics, genomics, multi-omics integration, and molecular design, and dissect how large agricultural foundation models reconstruct the entire seed industry workflow.[Progress]The historical evolution of crop breeding was first traced from 1.0 empirical domestication to 5.0 smart Breeding characterized by the deep integration of biotechnology (BT) and information technology (IT). In germplasm resource evaluation, deep learning algorithms enabled high-dimensional pattern recognition and unsupervised feature compression to unlock rare alleles from unannotated sequences, large language models (LLMs) like PlantConnectome and wheat germplasm information extraction (WGIE) leverage retrieval-augmented generation (RAG) to automatically construct structural knowledge graphs from unstructured historical literature, achieving predictive and dynamic germplasm evaluations. In high-throughput phenotyping, industrial platforms capture 3D point cloud and multi-spectral data at 0.1 mm resolution, while convolutional neural networks couple with the integrated genomic-enviromic prediction (iGEP) framework to build full-lifecycle digital twin crop models in virtual space. Regarding genomic prediction, the limitations of linear paradigms were dissected and cutting-edge deep learning architectures were highlighted: SoyDNGP applied a 3D-CNN to map chromosomal topology for complex soybean traits; DPCformer employed self-attention mechanisms to dynamically calculate environmental weights under multi-adversarial constraints; and HyenaDNA utilized long-convolution filters to bypass the O(N2) computational complexity limitation of standard Transformers, reducing it to O(N·log N) for chromosome-scale modeling. For multi-omics integration, intermediate fusion strategies were elucidated for their superior capacity to capture cross-layer biological compensatory pathways. In molecular design breeding, foundational plant language models were highlighted, such as AgroNT for zero-shot expression prediction and OpenCRISPR-1, the world's first de novo AI-generated genome editor built to capture underlying physico-chemical syntax. Furthermore, the emergence logic of major domestic and international agricultural foundation models was analyzed through the mathematical lenses of scaling laws, parameter-efficient fine-tuning, and multi-task evaluation benchmarks. Finally, empirical effectiveness was comprehensively evaluated through multinational success stories, including Bayer's Climate FieldView, IRRI's night-temperature thermal models for "Green Super Rice", and China's state-led breeding platforms for stress-resistant maize and high-yield soybean.[Conclusions and Prospects]Key structural challenges that smart breeding faces are thoroughly dissected: data silos and standardization dilemmas, extreme computational resource asymmetry and high training costs, the lack of biological causal logic in deep learning "black boxes", and the structural scarcity of interdisciplinary BT-IT talent. To overcome these bottlenecks, future research and policy efforts should focus on four pillars: 1) Establishing standardized open data ecosystems following FAIR (Findable, Accessible, Interoperable, Reusable) principles and promoting federated learning under a national AI data copyright integration platform to safeguard digital borders; 2) Exploring cloud-to-edge lightweight model deployment pathways through parameter-efficient fine-tuning, quantization, and knowledge distillation to empower real-time field-side decision-making and realize compute equity; 3) Deepening the mechanistic integration of AI and synthetic biology by absorbing breakthroughs from multi-scale modeling frameworks into the virtual "design-build-test-learn" cycle to break natural evolutionary thresholds; and 4) improving regulatory approval frameworks for AI-designed crops and modernizing agricultural education to cultivate a new generation of digital agronomists.
Why it matches plant phenotyping methods作物育種におけるAI・表現型解析を体系的にレビューし、高スループット表現型取得プラットフォーム、3D点群・マルチスペクトルデータ、画像解析モデルを中心的に扱っているため。
abstractThe aim of this paper is to systematically explore the underlying logic of the AI-driven crop breeding paradigm shift, comprehensively outline its generational evolution, analyze its core technical implementations in phenomics, genomics, multi-omics integration, and molecular design
Sugarcane is a high-value industrial crop vital for sugar and biofuel production, yet increasingly constrained by climate variability, biotic and abiotic stresses, soil degradation, and inefficient input use. Traditional breeding and crop management approaches are often slow, labour-intensive, and less precise, emphasizing the need for digital transformation in sugarcane agriculture. AI now offers powerful tools to accelerate genetic improvement, enhance stress resilience, and optimize resource-use efficiency. This review synthesizes recent advances in AI applications across the sugarcane improvement pipeline, including high-throughput phenotyping, genomic prediction, digital crop monitoring, and AI-driven decision-support systems. ML and DL models enable automated, accurate prediction of key traits such as biomass, canopy temperature, nitrogen status, and sugar recovery using UAV, satellite, and proximal sensing data. AI-powered genomic selection approaches leveraging convolutional networks, transformers, and attention mechanisms improve prediction accuracy for yield, ratooning ability, and stress tolerance by integrating SNPs, pedigree, and multi-environment datasets. Emerging innovations such as digital twins, multimodal data fusion, reinforcement learning-based irrigation scheduling, and climate-smart advisory models further strengthen real-time crop intelligence. The integration of blockchain-enabled breeding databases, FAIR data standards, and interoperable analytics pipelines supports scalable and collaborative research. Literature analysis reveals 15-30% gains in selection efficiency, >90% accuracy in disease detection, and phenotyping cost reductions of up to 70%. Key challenges remain, including scarce annotated datasets, genotype × environment complexity, model interpretability, and adoption barriers for smallholders. A future roadmap is proposed featuring multimodal foundation models, edge-AI deployment, and explainable breeder dashboards. AI is redefining sugarcane research from reactive to predictive, enabling climate-resilient, sustainable, and profitable production systems.
Why it matches plant phenotyping methodsサトウキビ育種におけるAI応用の総説であり、高スループット表現型解析、UAV・衛星・近接センシングによる形質推定を主要な対象として扱っているため、フェノタイピング手法レビューとして適格。
abstractThis review synthesizes recent advances in AI applications across the sugarcane improvement pipeline, including high-throughput phenotyping, genomic prediction, digital crop monitoring, and AI-driven decision-support systems.
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 7 Sept 2026
Recent advancements in 3D reconstruction technologies have significantly transformed plant phenotyping, enabling precise, scalable, and automated trait extraction. Traditional manual phenotyping methods are increasingly being replaced by image-based approaches, such as photogrammetry, LiDAR, RGB-D sensing, and deep learning (DL)-based techniques. These tools allow for non-destructive, high-throughput measurements of plant morphology, structure, and physiological traits. This review synthesizes the state of the art in 3D reconstruction methods, including conventional geometric algorithms and emerging DL methods, and evaluates their application across diverse plant species. In addition, we discuss the sensing modalities, evaluation metrics, and crop-specific deployments. Although promising, current technologies still face challenges in terms of computational efficiency, scalability to outdoor environments, and generalizability across crop types. This review concludes by identifying research gaps and future directions for making real-time, field-deployable 3D phenotyping systems.
Why it matches plant phenotyping methods植物フェノタイピングにおける3D再構成技術と形質抽出を主題とする方法論レビューであり、評価指標やセンサー、応用を体系的に扱っている。
abstractThis review synthesizes the state of the art in 3D reconstruction methods
Papaya (Carica papaya L.) is a crop of great economic importance. However, factors such as low genetic variability, abiotic stresses, and technological limitations compromise fruit productivity and quality. In this context, the use of modern tools, such as digital phenotyping, combined with genetic improvement, has stood out in the search for more productive cultivars with improved postharvest quality. The objective of this study was to conduct a comprehensive literature review on papaya cultivation, addressing its main agronomic aspects, as well as postharvest evaluation methods, with an emphasis on digital image-based phenotyping techniques applied to fruit quality analysis. The study was based on scientific publications selected from the Scopus, SciELO, and Google Scholar databases, mainly covering the period from 2014 to 2024. Studies related to papaya cultivation, genetic improvement, digital phenotyping, sensory analysis, and physicochemical evaluation of fruits were included, as well as classical references relevant to the topic. The literature indicates that papaya breeding depends on the exploitation of genetic variability present in germplasm banks, aiming at the development of cultivars with superior agronomic traits and improved fruit quality. Digital phenotyping stands out as an efficient tool for collecting and analyzing phenotypic data, allowing greater precision, cost reduction, and optimization of the selection process. The integration of digital phenotyping with physicochemical and sensory analyses enables the identification of genotypes with higher productive potential and fruits with better consumer acceptance.
Why it matches plant phenotyping methodsデジタル画像ベースの植物表現型解析を果実品質評価に適用する方法を中心に扱うレビューであり、植物フェノタイピング手法レビューとして適格。
abstractThe objective of this study was to conduct a comprehensive literature review on papaya cultivation, addressing its main agronomic aspects, as well as postharvest evaluation methods, with an emphasis on digital image-based phenotyping techniques applied to fruit quality analysis.
Objectives: Multispectral imaging and spectrophotometry are widely used to estimate plant physiological characteristics, yet the literature remains fragmented across sensors, indices, and analytical approaches. Methods: This systematic review followed PRISMA 2020 and was preregistered in OSF (Open Science Framework). Web of Science, Scopus, Google Scholar, and Consensus were searched up to January 2025 for peer-reviewed studies and selected gray literature studies focused on plant physiological trait estimation using multispectral or spectrophotometric methods. From 256 identified records, 96 studies met the eligibility criteria. Methodological quality was assessed across five domains, and results were synthesized narratively owing to high heterogeneity. Results: A total of 96 studies met the eligibility criteria. Among these, multispectral sensors were the most commonly used (40.7%), followed by UAV-mounted platforms (25.9%), while hyperspectral sensors accounted for 18.5% of the studies. The most frequently used vegetation index was NDVI, reported in 87% of the studies, mainly for estimating vigor, biomass, and canopy structure. Discussion: Although multispectral indices reliably capture key agronomic traits, cross-study comparability is currently hampered by significant methodological variability and a lack of consistent validation protocols. Conclusions: Multispectral imaging and spectrophotometry are effective tools for estimating plant physiological traits, but greater standardization is needed across studies. Owing to the limited number of studies on Stenocereus spp., the review was expanded to plants in general; the shortage of reports addressing Stenocereus spp. highlights the need for future research in these species.
Why it matches plant phenotyping methods植物生理形質推定のためのマルチスペクトル画像・分光法を対象とした系統的レビューであり、方法の比較、品質評価、検証標準化を中心に扱っている。
abstractThis systematic review followed PRISMA 2020 and was preregistered in OSF (Open Science Framework).
Plants must constantly adapt to biotic and abiotic stressors, which the global climate change crisis has intensified. To monitor plant health and predict their ability to face these challenges, various target molecules, such as hormones, glucose, and reactive oxygen species, are used as proxies for their physiological status. This review provides a systematic assessment of the current state of biosensor technology, an innovative analytical approach designed for in situ, minimally invasive, and real-time monitoring. Using the PICO (Problem, Intervention, Comparison, and Outcome) strategy, relevant research papers were identified. The review highlights how biosensors can detect physiological responses to stress before visual symptoms manifest, offering a significant advantage over traditional, often destructive, laboratory techniques, like gas chromatography-mass spectrometer (GC-MS) or high-performance liquid chromatography (HPLC). These advancements aim to improve precision agriculture and forestry management by providing sustainable methods to assess resilience in changing environments. Finally, the challenges of translating research from model organisms to complex woody species and choosing the correct target are discussed, and future perspectives, including the integration of biosensors with Artificial Intelligence-driven predictive models for large-scale environmental monitoring, are outlined.
Why it matches plant phenotyping methods植物ストレスの生理状態をリアルタイムに評価するバイオセンサー技術を体系的にレビューしており、植物フェノタイピング手法が中心である。
abstractThis review provides a systematic assessment of the current state of biosensor technology, an innovative analytical approach designed for in situ, minimally invasive, and real-time monitoring.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 15 Sept 2026
Addressing global grand challenges, including food security, climate change, and resource scarcity, requires transcending the limitations of traditional crop science research. Traditional approaches often suffer from low-throughput, destructive nature, and qualitatively macroscopic analyses, hindering the in-depth exploration and precise manipulation of crop growth mechanisms necessary for modern agriculture. This review systematically synthesizes recent advancements and pinpoints critical bottlenecks in key areas of modern crop science research: high-throughput phenotyping, multiscale mechanics of crops, and numerical modeling of crop-environment interactions. Based on this synthesis, we propose and articulate a conceptual framework for the novel interdisciplinary field: “mathematical and physical crop science.” The framework establishes an integrated paradigm of “data-driven, mechanism-based, and system-predictive” research, structured as follows: (1) High-throughput phenotyping, coupled with artificial intelligence and machine learning-driven analysis, quantifies dynamic phenotypic traits emerging from genotype-by-environment interactions. (2) Multiscale mechanics of crops resolves the physical constraints governing crop structure and function across different scales. (3) Numerical modeling of crop-environment interactions simulates the dynamic interactions between crop physiological processes and environmental factors. The overarching goal is to integrate these historically disparate research domains, providing a unified theoretical foundation for the systematic understanding of crop physiological and developmental processes and informing sustainable agricultural practices.
Why it matches plant phenotyping methods高スループット植物フェノタイピングを主要領域として体系的にレビューし、AI・機械学習による形質定量を扱うため、フェノタイピング方法レビューに該当する。
abstractThis review systematically synthesizes recent advancements and pinpoints critical bottlenecks in key areas of modern crop science research: high-throughput phenotyping, multiscale mechanics of crops, and numerical modeling of crop-environment interactions.
Field / plotGrowth chamberStress response / toleranceYield / yield components
The convergence of artificial intelligence (AI), genomics and phenomics is ushering in a new era of smart breeding a paradigm that promises to dramatically accelerate genetic gain while reducing the time and cost associated with developing elite crop varieties. Conventional plant breeding, though enormously successful over the past century, is increasingly challenged by a rapidly changing climate, a growing global population projected to reach nearly 10 billion by 2050 and the biological complexity of quantitative traits. Smart breeding leverages exponential growth in genomic data, high-throughput phenotyping platforms and the analytical power of machine learning and deep learning algorithms to navigate these challenges. This review synthesizes the current state of knowledge across three interdependent pillars: AI and machine learning for genomic selection, trait prediction and decision support; next-generation sequencing and multi-omics tools that have transformed our understanding of crop genetic architecture; and field and controlled-environment phenomics platforms that bridge the genotype phenotype gap. Further discuss integration through digital twins, knowledge graphs and federated learning frameworks and examine applications in gene editing, stress tolerance and yield improvement. Key challenges data standardization, interpretability of black-box models, regulatory frameworks and equitable access are critically assessed and a roadmap for the next decade of smart breeding is proposed. Another point highlighted in this review is the need to conduct collaborative and interdisciplinary research to achieve the full potential of smart breeding technologies. It emphasizes the necessity of capacity-building, data sharing systems and policy support to provide sustainable and inclusive agricultural growth. Moreover, the paper highlights the importance of new innovations in developing resilient and productive and future-oriented crop systems.
Why it matches plant phenotyping methodsAI・ゲノミクス・フェノミクスを統合するレビューであり、高スループット表現型解析プラットフォーム、形質予測、機械学習による表現型解析を主要な構成要素として扱っているため、方法レビューとして採択。
abstractSmart breeding leverages exponential growth in genomic data, high-throughput phenotyping platforms and the analytical power of machine learning and deep learning algorithms
Field / plotRootGrowth / development / phenologyRoot system architecture
Understanding root growth and phenology is essential for improving the productivity, resilience, and sustainability of pasture-based systems. However, roots remain one of the most difficult components of plant systems to measure and monitor, particularly in managed, high-turnover pastures, such as those in New Zealand (NZ) dairy systems. As a result, root processes are often underrepresented in both experimental studies and pasture system models. This perspective paper identifies critical, but underdeveloped areas in root research, with particular focus on root phenology. Current studies are limited by insufficient temporal resolution, a lack of species- and cultivar-specific trait data in mixed swards, and weak integration of root dynamics into breeding programmes and farm system models. These constraints limit our ability to link root processes to pasture persistence, nutrient cycling, and climate resilience. To address this gap, we propose that root phenology should be treated as a dynamic functional trait that links plant responses to environmental and management drivers with ecosystem-level outcomes. This framing provides a conceptual foundation for integrating root dynamics into pasture research and modelling, particularly in systems subject to frequent defoliation and environmental variability. We further highlight opportunities arising from rapid advances in sensing technologies, automation, and data analytics, which enable continuous, high-resolution root monitoring systems at multiple scales. However, realising this potential requires integration of complementary measurement approaches and alignment with system-level research questions. In this context, NZ provides a unique platform for developing scalable, pasture-based root monitoring framework that integrates science, management and policy. We argue for a coordinated effort that bridges fundamental root biology with applied pasture management, supported by long-term datasets, methodological integration, and engagement with end users. Embedding root traits and phenological dynamics into the next generation of pasture models and decision-support tools will be critical for improving system performance and environmental outcomes. This perspective aims to stimulate a shift towards more integrated, temporally explicit approaches for studying root systems in pasture environments, with relevance to grazing system beyond NZ and across temperate regions.
Why it matches plant phenotyping methods根の成長・フェノロジーという植物形質の測定課題と、センシング・自動化・データ解析を統合した高頻度モニタリング手法を中心に論じる方法論的パースペクティブである。
abstractroots remain one of the most difficult components of plant systems to measure and monitor
Diameter at Breast Height (DBH) is a key parameter in forest measurement. However, existing research has mostly focused on improving the accuracy of individual technologies, lacking a systematic synthesis of the evolutionary logic of measurement techniques and a standardized selection framework for forestry applications. To this end, this paper constructs a multi-level classification framework based on measurement platforms and technical principles, establishes for the first time a five-dimensional comprehensive evaluation system (covering accuracy, efficiency, cost, environmental adaptability, and automation) along with a hierarchical technology decision tree, and systematically analyzes the application logic of multi-source fusion technologies across three levels: ground-based, near-ground mobile, and aerial. The review indicates that traditional contact-based measurement has limited efficiency; modern remote sensing technologies (photogrammetry and LiDAR) offer significant advantages in automation and accuracy, but still face challenges such as high equipment costs, complex data processing, and poor environmental adaptability. Multi-source fusion and machine learning are key methods to overcome the limitations of single sensors and improve the robustness of DBH estimation. Finally, it is anticipated that with decreasing sensor costs and the advancement of intelligent algorithms, DBH measurement will continue to evolve toward automation, intelligence, and engineering practicality, providing technical support for large-scale, long-term, and repeatable forest monitoring.
Why it matches plant phenotyping methods森林樹木のDBHという明示的な植物形態形質の測定技術を対象に、測定原理の分類、評価体系、意思決定木、リモートセンシングと機械学習の比較を体系化した方法論レビューであり、フェノタイピング手法が中心である。
abstractDiameter at Breast Height (DBH) is a key parameter in forest measurement.
Seeds are complex living systems that display rich diversity in morphology, physiology, biochemistry, and genetics. Yet phenotyping during seed dormancy remains hampered by limited imaging modalities, insufficient data integration, and underpowered intelligent analytics—constraints that impede the efficiency and accuracy of precision breeding and germplasm evaluation. In the AI-for-Science era, seed phenomics research urgently needs to establish an end-to-end “measure–compute–understand–apply” pipeline, spanning cross-scale multimodal data acquisition to insight. This article systematically reviews the technical evolution of dormancy-state seed phenotyping and delineates five stages—manual observation phenotypes, biochemical phenotypes, image-based phenotypes, digital seeds, and intelligent seeds—summarizing the defining features and principal limitations of each. The deep integration of advanced imaging with artificial intelligence offers new opportunities to overcome existing bottlenecks. Seed Imaging Omics has emerged to meet this need: leveraging multiscale, multidimensional imaging for comprehensive observation and multimodal data capture; coupling these data with multimodal fusion, foundation-model analysis, and virtual seed reconstruction to enable precise feature extraction and pattern discovery from large image corpora. These capabilities clarify complex traits, reveal morphology–function relationships, and advance systems-level understanding of seed biology, ultimately supporting precise germplasm management and evaluation, data-driven elucidation of biological mechanisms, and accelerated innovation in crop improvement. Looking ahead, continued progress in sensing and imaging, foundation models, and large-scale analytics will drive seed phenotyping toward “intelligent” systems capable of autonomous sensing, real-time analysis, and decision-making across the seed life cycle—transforming seeds from passive carriers of genetic and phenotypic information into smart units that integrate phenotypic logging, state monitoring, performance assessment, and management feedback.
Why it matches plant phenotyping methods種子休眠状態の表現型計測技術を体系的にレビューし、画像取得、マルチモーダル統合、特徴抽出、AI解析を中心に扱うため、植物フェノタイピング手法レビューとして含める。
abstractThis article systematically reviews the technical evolution of dormancy-state seed phenotyping
Accurate and timely detection of crop diseases is essential for global food security and sustainable agriculture. This review provides a comprehensive analysis of recent advancements in leaf image-based crop disease detection using machine learning, deep learning (DL), convolutional neural networks, vision transformers, and emerging state-space models. Following PRISMA guidelines, the review systematically examines peer-reviewed studies (2021–2025) and evaluates datasets, model architectures, validation protocols, and deployment constraints. Unlike previous surveys, this review uniquely integrates explainable artificial intelligence (XAI) with emphasis on physiology-based interpretability and real-world field usability. Key findings reveal that while DL models achieve > 95% accuracy on controlled datasets like PlantVillage, performance degrades significantly under field conditions due to dataset bias, domain shifts, and multi-disease complexity. Critical research gaps are identified, including insufficient annotation standards, limited cross-domain validation, and computational constraints for edge deployment. Emerging directions include agriculture-specific foundation models, domain-generalizable vision systems, lightweight mobile strategies, and next-generation XAI frameworks aligned with plant physiology. By bridging technical advancements with agronomic interpretability, this work provides researchers and practitioners with a roadmap for developing trustworthy, field-deployable AI systems for sustainable crop health management.
Why it matches plant phenotyping methods葉画像から植物の病害状態を推定する手法を体系的にレビューし、モデル、データセット、検証、実運用上の課題を中心に扱っているため。
abstractThis review provides a comprehensive analysis of recent advancements in leaf image-based crop disease detection using machine learning, deep learning (DL), convolutional neural networks, vision transformers, and emerging state-space models.
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 5 Sept 2026
High-throughput plant phenotyping (HTPP) is increasingly limited by the mismatch between the need for field-relevant, fine-grained phenotypic information and the restricted capability of conventional observation platforms under complex agricultural conditions. Ground mobile robots are emerging as the key carrier for resolving this gap because they combine close-range sensing, autonomous mobility, and physical interaction within real field environments. In this paper, a structured scoping review is presented using a closed-loop perception-decision-action pipeline as the organizing principle. Within this framework, recent advances are synthesized from the perspectives of multimodal fusion, localization-aware sensing, motion planning, deep-learning-based phenotypic analysis, active observation, robotic intervention, and edge deployment. The review further clarifies the complementary roles of Unmanned Aerial Vehicles (UAVs), Unmanned Ground Vehicles (UGVs), and air-ground collaboration in multiscale phenotyping workflows. Beyond summarizing technologies, the article provides three concrete deliverables: a structured taxonomy of mobile phenotyping systems; comparative tables covering sensing modalities, localization/navigation methods, and AI models; and a research agenda linking technical progress to field deployability. The synthesis highlights four persistent bottlenecks, namely environmental generalization, annotation scarcity, limited standardization and reproducibility, and the gap between advanced models and agricultural edge hardware. Overall, ground robots are identified not merely as sensing platforms, but as the central system architecture for advancing mobile phenotyping toward autonomous, fine-grained, and field-deployable operation.
Why it matches plant phenotyping methods植物フェノタイピング用移動ロボットについて、センシング、表現型解析、プラットフォーム分類、比較、標準化を中心に扱う方法論レビューであり、対象範囲に明確に合致する。
abstractIn this paper, a structured scoping review is presented using a closed-loop perception-decision-action pipeline as the organizing principle.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 5 Sept 2026
As a core resource of traditional Chinese medicine (TCM), medicinal plants are conventionally monitored and assessed using high-cost, low-efficiency methods. Remote sensing offers an efficient technical alternative for large-scale and dynamic evaluation. This study systematically reviewed the literature from 2005 to 2025, summarized remote sensing platforms, sensors, and data analytical methods, and specifically analyzed their applications in medicinal plant resource investigation, planting monitoring, stress monitoring, and TCM quality assessment. These studies mainly focus on resource surveys and quality analysis, targeting root and rhizome herbs. Integrated satellite-, UAV-, and ground-based remote sensing enables distribution mapping, growth retrieval, stress monitoring, and non-destructive quality evaluation in medicinal plants, achieving overall accuracies ranging from 80% to 100%. Currently, remote sensing applications in medicinal plants are evolving toward space–air–ground integration, multi-source data fusion, artificial intelligence empowerment, and multi-omics integration. However, they are constrained by complex wild habitats, difficulties in monitoring root herbs, spectral confusion, and limited model generalization. Future efforts should focus on establishing an integrated monitoring network, developing full-chain quality inversion models for geo-authentic herbs, building climate-adaptive cultivation systems, creating early pest–disease warning technologies, and deepening the integration of remote sensing and multi-omics to support the sustainable utilization and high-quality development of medicinal plant resources.
Why it matches plant phenotyping methods植物の成長・ストレス・品質などの状態を対象に、リモートセンシングのプラットフォーム、センサー、解析手法を体系的にレビューしており、植物フェノタイピング手法が中心です。
abstractThis study systematically reviewed the literature from 2005 to 2025, summarized remote sensing platforms, sensors, and data analytical methods
Agriculture, as a basis of sustainable development, faces increasing pressure to meet rising global food demands while confronting the increasing impacts of climate change. Precision agriculture offers a data-driven approach to address these challenges by optimizing input use, improving productivity, and reducing environmental impacts. Sensor technologies play a critical role in smart and precision agriculture, offering high-resolution spatial and temporal insights into soil conditions, plant development and environmental conditions. This review highlights the current state and future potential of various sensor and imaging systems, particularly their role in monitoring soil properties, crop nutrition, plant health and detecting biotic and abiotic stressors. Special attention is given to accessible paper-based and printed electrochemical devices for on-site soil and plant analysis, as well as active handheld multispectral sensors designed for real-time canopy assessment. The integration of sensor-derived data with predictive models, IoT networks and decision-support tools enables more precise, site-specific management, improves input efficiency and supports climate-resilient agricultural practices. By examining the capabilities, limitations and future potential of these sensing platforms, this review highlights their growing importance in advancing sustainable intensification and strengthening crop production.
Why it matches plant phenotyping methods植物の発達、健康、ストレス、栄養、キャノピー状態を測定するセンサー・画像システムを中心にレビューしており、植物表現型取得技術のレビューに該当する。
abstractSensor technologies play a critical role in smart and precision agriculture, offering high-resolution spatial and temporal insights into soil conditions, plant development and environmental conditions.
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 13 Sept 2026
Global agricultural production is currently limited by ongoing climate change. Approximately 90% of crop species and numerous wild plants are dependent on pollinators for reproduction. The global threat to pollinators posed by climate change has grown considerably, as higher temperatures, shifting rainfall patterns, and more frequent extreme weather events disrupt the fragile relationships between plants and their pollinators. The decline in pollinators is also linked to shifts in land use, the widespread adoption of monocropping, and heavy reliance on agrochemicals. Therefore, the protection of pollinators and the preservation of agrobiodiversity are essential to uphold global food systems. Here, we synthesize the adverse impact of climate change on plant-pollinator interactions; throughput assay for phenotyping floral traits; assessing variability and molecular basis of floral display (flower size, shape, color, attractants etc.) and reward (nectar volume and composition, pollen, and fragrance in case of ornamental plants) traits; crop domestication and inbreeding, ploidy and mating systems differences impacting plant-pollinator interactions; volatiles and metabolites mediating plant-pollinator relationships; trade-offs involving reproductive and pollinator traits; and finally, progress in developing pollinator-friendly crop cultivars through conventional plant breeding and biotechnological interventions. Pollinator-assisted phenotyping and selection platform (DARkWIN) combined with other high-throughput phenotyping assays, has the potential to simultaneously quantify multiple interactions impacting pollinators’ visitation and foraging behaviors, and generate data on other parameters like stress tolerance, yield, and nutrition in the target populations. Assessing and exploiting functional diversity for plant-pollinator interactions, combined with the use of functionally characterized genes and associated markers for floral display ( AT2G31010 , AT4G17080 , CmGEG , CmCYC2c , CmJAZ1-like-CmBPE2 , Cyc2CL-1 , Cyc2CL-2 ) and reward ( SWEET9 , BrCWINV4A , EOBI , EOBII ) traits, can be deployed in breeding programs to develop pollinator-friendly crop cultivars. Numerous candidate genes, reported herein, must be functionally validated before being deployed in crop breeding programs.
Why it matches plant phenotyping methods植物―送粉者相互作用と花形質を対象とするレビューであり、花形質のスループット表現型解析やDARkWINによる送粉者支援型フェノタイピング基盤を主要な方法論として扱っている。
abstractthroughput assay for phenotyping floral traits
RootMorphology / geometry measurementGrowth / development / phenologyRoot system architecture
All plants rely on their roots for survival. Due to the natural plasticity of roots in response to different stimuli, breeders can investigate natural adaptation and uncover advantageous root features to increase plant yield in agricultural system. The plant's physiology, development, and ability to respond to different pressures are all influenced by the root system. Root system architecture (RSA)-related factors are very important for breeding selection. However, quantifying these traits is difficult, requires a lot of resources, and frequently produces a lot of variability. With the development of computer vision and machine learning (ML) technologies, which allow for effective trait extraction and evaluation, the use of RSA traits for genetic improvement to create more robust and resilient crop cultivars has attracted greater attention. Root phenotype is a crucial component of yield improvement which is regulated by the interaction of internal genetic factors and external environmental conditions. To meet the demands of population growth and climate change, significant increases in agricultural productivity are required. Enhancing crop root architecture has the potential to improve water and nutrient use efficiency; however, a major challenge remains in accurately characterizing the structure and function of the root phenome. Numerous advances have been made in recent years in the measurement and analysis of root system, including the development of 2D and 3D root phenotyping platforms. These platforms are high-throughput and non-invasive techniques for root phenotype characterization. These approaches involve the use of advanced imaging and analytical tools to collect data on root structure, growth, and function across a large number of plants, while enabling automated evaluation of multiple root traits. To phenotype root systems numerous imaging tools, software, and platforms have been developed. This study focuses on recent advancements in in-situ root phenotyping techniques that allow researchers and breeders to efficiently assess root characteristics and apply them to different breeding initiatives. In-situ root phenotyping techniques encompass a variety of 2D and 3D platforms for thorough and efficient root analysis. This review highlights current developments in in-situ root phenotyping and stresses their expanding potential to aid in the development of stress-resistant, high-yielding crops for sustainable agriculture.
Why it matches plant phenotyping methods根系表現型取得に関する2D・3D画像化、解析ツール、ソフトウェア、プラットフォームの進展を扱うレビューであり、植物フェノタイピング手法が中心である。
titleAdvances in In-situ Root Phenotyping: A Review
Advances in nanomaterials design have conferred new capabilities for interfacing with plant systems, providing a versatile toolbox for probing and modulating plant responses to environmental stresses with high spatiotemporal control. These nanomaterials-based innovations are particularly important for enhancing agricultural stress resilience as they complement existing agronomic practices by addressing two long-standing technological gaps: nondestructive presymptomatic detection of stress-related biochemical signaling in plants and precise delivery of genetic and bioactive cargoes across plant barriers. This review outlines key design principles, properties, and engineering of different nanomaterial classes that enable their application in agriculture. We highlight recent advances in plant nanosensors, including corona phase molecular recognition (CoPhMoRe) sensors, plasmonic nanosensors that are surface-enhanced Raman scattering (SERS)-active, and reticular framework-based sensors that enable continuous presymptomatic monitoring of key stress-related analytes such as reactive oxygen species (ROS), phytohormones, and metabolites. In parallel, progress in nanocarriers, including carbon-based nanostructures, polymeric nanoparticles, and functional peptides, has enabled delivery of nucleic acids, growth regulators, nutrients, and agrochemicals across plant biological barriers that traditionally impede efficient plant transformation and stress mediation. Together, nanosensors and nanocarriers are highly synergistic for nanoenabled precision agriculture, where real-time monitoring serves as feedback control for responsive interventions, contributing to resilient and sustainable next-generation crop production under a changing climate. While the practical implementation of these plant nanosensors and nanocarriers still faces significant hurdles related to scalability, stability, and environmental safety, progress in rational materials design coupled with plant interface engineering suggests a clear pathway ahead to overcome these limitations and realize their full potential in the field.
Why it matches plant phenotyping methods植物ストレス状態を非破壊・連続的に検出するナノセンサーを中心に扱うレビューであり、植物の生理状態・ストレス関連 analyte の測定法が中核的である。
abstractThis review outlines key design principles, properties, and engineering of different nanomaterial classes that enable their application in agriculture.
Plant diseases are a major problem worldwide, affecting crop yield and quality and impacting food security. Early identification and accurate diagnosis of plant diseases is crucial to minimizing crop damage and maximizing eco-friendly farming practices. Traditional methods of plant disease detection include manual diagnosis by experts, which is time consuming to arrive at the final diagnosis and is prone to human errors. In recent years, Machine Learning (ML) and Deep Learning (DL) algorithms have been used for the automatic detect plant diseases, with no intervention needed by experts. These algorithms are used to detect diseases by analysing images of plant stems, leaves and other parts, differentiating between healthy and diseased plants. Step by step procedures are used to diagnose plant diseases by employing techniques such as image pre-processing, feature extraction, and classification to enhance image quality for accurate disease classification and prediction. This paper details the application of various existing ML and DL algorithms in the detection, classification and prediction of plant diseases, where image-based techniques are also adopted for accurate and swift diagnosis. Performance metrics such as sensitivity, accuracy, and specificity elaborate on the efficacy of ML and DL algorithms, acting as reliable tools for accurate plant disease detection. The outcomes of this study illustrate that these ML and DL models are well suited for the identification and classification of plant diseases.
Why it matches plant phenotyping methods植物画像から病害状態を検出・分類する機械学習手法を体系的に扱うレビューであり、植物フェノタイピング手法が中心です。
abstractThis paper details the application of various existing ML and DL algorithms in the detection, classification and prediction of plant diseases, where image-based techniques are also adopted for accurate and swift diagnosis.
Field / plotClassificationStress / disease detectionDisease symptoms / severity
The integration of artificial intelligence (AI) with computer vision through real-time deep-learning models such as YOLOv5, MobileNetV3, and TinySegformer offers revolutionary solutions, achieving 90–96% accuracy at 30–50 frames per second (FPS) with less than 1W power consumption. This systematic literature review (SLR) analyzes 30 studies from 2015–2024, evaluating real-time plant disease and pest detection systems based on performance, computational efficiency, and agricultural applicability. Findings indicate that YOLO-based models provide the best speed-affordability balance, enabling immediate field diagnoses on Raspberry Pi edge devices, while non-realtime systems (e.g., VGG, ResNet) offer higher accuracy at the cost of longer processing times. Barriers such as occlusion, high costs, limited field datasets, and power constraints are addressed through attention mechanisms, low-cost hardware, crowdsourced datasets, and model optimization. Emerging technologies, including federated learning, IoT integration, hybrid CNN-Transformer models, UAV-based systems, and multimodal data fusion, enhance scalability, robustness, and accessibility, reducing pesticide use by 20–25% and recovering 10–15% of lost yields. This SLR outlines research directions for field model optimization, affordable precision agriculture tools, and policy strategies for equitable technology distribution, supporting sustainable agriculture and global food security.
Why it matches plant phenotyping methods植物病害を画像・AIで検出する手法を対象に、精度、処理速度、計算効率、実用性を比較評価した系統的レビューであり、病害状態の表現型推定手法が中心です。
titleAdvanced AI and computer vision-based real-time plant disease and pest detection system: a systematic literature review
Vegetable crops are the backbone of global food and nutritional security, yet they remain among the most vulnerable agricultural commodities to climate change. Heat, drought, salinity, flooding and escalating biotic pressures now represent existential threats to vegetable productivity, quality and accessibility, particularly in developing nations. This review examines how the synergistic deployment of genomics and phenomics can accelerate the development of climate-resilient vegetable cultivars. The objective is to critically synthesize current advances in genomic tools—including next-generation sequencing (NGS), genome-wide association studies (GWAS), CRISPR/Cas9 genome editing and genomic selection—alongside high-throughput phenotyping (HTP) technologies such as multispectral imaging, thermal sensors and drone-based platforms, and to evaluate their integration as a strategic framework for vegetable breeding. Key findings demonstrate that the integration of genomics and phenomics enables high-resolution genotype-to-phenotype (G→P) mapping, significantly reduces breeding cycle duration and improves selection accuracy for complex, multigenic stress-adaptive traits across major vegetable crops including tomato, pepper, cucumber, lettuce, spinach and Brassica species. Specific discoveries include the identification of heat-tolerance QTL in tomato via GWAS-phenomics integration, CRISPR-mediated improvement of drought signaling in pepper and genomic selection models achieving prediction accuracies of 0.65 for heat stress indices in lettuce. The review also identifies critical limitations including high phenotyping costs, data integration challenges, lack of standardized protocols, regulatory hurdles for genome-edited cultivars and limited capacity in low-income countries. These findings have direct policy implications: so in order to unlock the transformative potential of genomics-phenomics integration, smallholder farmers in climate-vulnerable regions will not have access to improved cultivars. Instead, national agricultural research programs and international funding bodies should prioritize investment in affordable phenotyping infrastructure, open-access pan-genome databases, harmonized data ontologies, and regulatory frameworks that facilitate the deployment of genome-edited vegetables.
Why it matches plant phenotyping methods植物フェノタイピング技術（マルチスペクトル画像、熱センサー、ドローンプラットフォーム等）をゲノミクスとの統合という観点から批判的にレビューしており、方法論が中心的である。
abstractThis review examines how the synergistic deployment of genomics and phenomics can accelerate the development of climate-resilient vegetable cultivars.
The contemporary challenge of sustainable agriculture necessitates the deployment of robust, data-driven decision support systems. This review paper details the architecture and efficacy of an integrated AI-based system, termed 'Sarv Sampoorna Kisan Mitra,' for comprehensive crop disease identification and management. The system is predicated on two core technological pillars: the use of advanced Deep Learning (DL) models, specifically Convolutional Neural Networks (CNNs), for rapid, visual diagnosis of crop diseases; and the implementation of a Knowledge Graph (KG) for prescriptive management recommendations. The paper explores the full lifecycle, from data acquisition via remote sensing and IoT, through predictive modeling for yield forecasting, and culminating in the generation of actionable, customized advice for fertilizer application and pest control. By transforming raw diagnostic data into contextualized, actionable knowledge, this integrated AI-KG framework offers a scalable solution to enhance precision farming efficiency and minimize resource wastage.
Why it matches plant phenotyping methods植物病害を画像から診断する手法と統合システムの構成・有効性が中心であり、病害状態の画像ベース推定を扱うレビューとして収録対象。
abstractThis review paper details the architecture and efficacy of an integrated AI-based system, termed 'Sarv Sampoorna Kisan Mitra,' for comprehensive crop disease identification and management.
Determining the optimal harvest time is among the most critical economic decisions for peanut ( Arachis hypogaea L.) growers, directly influencing yield, quality, and market value. Unlike many other crops, peanuts are indeterminate, continuing to flower and produce pods throughout their life cycle. As a result, pod development and maturation are asynchronous, making harvest timing particularly challenging. Conventional maturity estimation techniques, including the hull scrape method, pod blasting, and visual maturity profiling, are invasive, labor-intensive, time-consuming, and spatially limited. Moreover, differences in cultivar maturity rates and agroclimatic conditions exacerbate inconsistencies in maturity prediction. These challenges highlight the urgent need for scalable, objective, and data-driven methods to support growers in achieving optimal harvest outcomes. This review synthesizes the current understanding of peanut pod maturity and evaluates existing traditional and non-invasive approaches for maturity estimation. It aims to identify the limitations of conventional techniques and explore the integration of advanced sensing technologies, artificial intelligence (AI), and geospatial analytics to enhance precision and scalability in peanut maturity assessment and harvest decision-making. This review examines traditional destructive techniques such as the hull scrape method and pod blasting, followed by emerging non-invasive methods employing proximal and remote sensing platforms. Applications of vegetation indices, multispectral and hyperspectral imaging, and AI-based data analytics are discussed in the context of maturity prediction. Additionally, the potential of multimodal remote sensing data fusion and digital frameworks integrating spatial big data analytics, centralized data management, and cloud-based graphical interfaces is explored as a pathway toward end-to-end decision-support systems. Recent advances in non-invasive sensing and AI-assisted modeling have demonstrated significant improvements in scalability, precision, and automation compared with traditional manual approaches. However, their effectiveness remains constrained by the limited inclusion of agroclimatic, phenological, and cultivar-specific variables. Furthermore, the translation of model outputs into actionable, field-level harvest decisions is still underdeveloped, underscoring the need for integrated, user-centric digital infrastructure. Achieving a robust and transferable digital peanut maturity estimation system will require comprehensive ground-truth data across cultivars, regions, and growing seasons. Multidisciplinary collaborations among agronomists, data scientists, growers, and technology providers will be essential for developing practical, field-ready solutions. Integrating AI, multimodal sensing, and geospatial analytics holds immense potential to transform peanut maturity estimation. Such innovations promise to enhance harvest precision, economic returns, and sustainability while reducing manual effort and uncertainty, ultimately improving the efficiency and quality of life for peanut producers worldwide.
Why it matches plant phenotyping methodsピーナッツ莢の成熟度という植物状態を対象に、従来法と非侵襲センシング、画像解析、AIによる推定手法を体系的にレビューしており、フェノタイピング手法が中心である。
abstractThis review synthesizes the current understanding of peanut pod maturity and evaluates existing traditional and non-invasive approaches for maturity estimation.
Background: This review study examines the transformative potential of machine learning (ML) methods for real-time and continuous evaluation of legume crop development. It provides a structured and comprehensive synthesis of current ML applications, highlighting their potential to improve legume crop management in terms of accuracy, efficiency, scalability and sustainability. Unlike existing reviews, this study specifically emphasizes real-time monitoring frameworks that integrate multi-source data (satellite, UAV, IoT and sensors) for legume crops. Methods: Various machine learning methods, including supervised, unsupervised and deep learning paradigms, are reviewed with respect to their applications in crop health prediction, disease detection and yield estimation. The review further analyzes the integration of ML models with Internet of Things (IoT), edge computing and sensor-based systems to address challenges related to data quality, model interpretability, computational efficiency and real-time decision-making. Result: While challenges remain, such as data heterogeneity, limited model generalization and the integration of ML with traditional agronomic practices, recent technological advancements demonstrate promising solutions. Key trends include the development of robust and transferable models, improved human–machine interfaces and decision-support tools for farmers. These advances have the potential to enhance precision, resilience and sustainability in legume crop monitoring, thereby contributing to global food security and climate-smart agriculture.
Why it matches plant phenotyping methodsマメ科作物の生育・健康・病害・収量を対象に、機械学習と衛星・UAV・IoT・センサーを統合したモニタリング手法をレビューしており、植物形質・状態の取得および推定方法が中心である。
abstractThis review study examines the transformative potential of machine learning (ML) methods for real-time and continuous evaluation of legume crop development.
Abstract Plant diseases are a major threat to the global agricultural productivity causing considerable yield losses and economic damage. Recent developments in Artificial Intelligence (AI) and specifically in Deep Learning has led to a revolution in the diagnosis of plant diseases with automated and scalable analysis of the crop images. This review offers an extensive synthesis of Convolution Neural Network (CNN) architectures engineered in precision phytopathology and mainly aimed at disease detection, classification, localization, and severity quantification. Following a systematic literature review using PRISMA methodology, this paper reports a structured taxonomy of CNN-based methods including classical classification networks, object detection networks and semantic segmentation models from 131 peer-reviewed articles. The review compares popular architectures like ResNet, EfficientNet, Yolo and U-net, highlighting their performance characteristics, accuracy-efficiency trade-offs, as well as suitability to real-world deployment. Findings show that although CNN based systems hold a high diagnostic accuracy in controlled settings, there are still issues especially related to generalization, dataset availability, and field level robustness. Emerging directions such as hybrid CNN-Transformer models, multimodal sensing and edge deployment are found as critical enablers for next-generation precision phytopathology systems for sustainable and data-driven crop disease management.
Why it matches plant phenotyping methods植物病害の画像から病徴の検出・分類・局在化・重症度を定量化するCNN手法を体系的に比較・整理した方法論レビューであり、植物表現型取得が中心です。
abstractThis review offers an extensive synthesis of Convolution Neural Network (CNN) architectures engineered in precision phytopathology and mainly aimed at disease detection, classification, localization, and severity quantification.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 5 Sept 2026
Plant diseases remain a major threat to global food production, causing significant yield losses and economic impact worldwide. Early and precise disease detection is crucial for effective crop management, yet conventional diagnostic approaches are often slow, labor-intensive, and rely on specialized expertise that may not be widely accessible. Recent advances in artificial intelligence (AI), particularly deep learning–based image analysis, offer scalable and automated solutions for plant disease recognition. This review critically examines forty-one peer-reviewed studies published between 2008 and 2025, selected following PRISMA guidelines from major scientific databases. We summarize key methodological developments, including convolutional neural networks, vision transformers, transfer and few-shot learning, and multimodal sensing approaches, highlighting their reported performance and limitations. Although many models achieve high accuracy in controlled datasets, their effectiveness often decreases under real-field conditions due to environmental variability, limited training data, and practical deployment constraints. We discuss existing challenges and propose future research directions, emphasizing improved robustness in field environments, development of lightweight and explainable models suitable for edge deployment, and integration with precision agriculture systems. This review aims to guide the design of reliable, practical, and scalable AI-driven plant disease detection strategies.
Why it matches plant phenotyping methods植物病害の画像認識・マルチモーダルセンシング手法を体系的にレビューしており、病害状態の表現型推定法が中心である。
abstractThis review critically examines forty-one peer-reviewed studies published between 2008 and 2025, selected following PRISMA guidelines from major scientific databases.
Abstract This study presents a systematic review of artificial intelligence applications, particularly machine learning and deep learning models, for okra leaf disease detection and diagnosis. Due to the limited number of okra-specific studies, a related study on leaf diseases of other crops was included for comparative analysis. Following the PRISMA framework, 28 peer-reviewed articles published between 2015 and 2025 were examined. The results show that convolutional neural networks dominate the current study, accounting for nearly 70% of all reviewed models. Architectures such as MobileNet, ResNet, and InceptionV3 consistently achieved accuracies above 90%. Okra-focused studies reported performance ranging from 87% to 98.63% (mean = 94.5%) but were constrained by small or imbalanced datasets. In contrast, studies on other crops achieved accuracies between 77% and 99.84% (mean = 96%), supported by substantially larger datasets. The review further identifies limited adoption of explainable AI, vision transformers, and federated learning approaches. Key study gaps include dataset scale, environmental integration, real-world validation, and reproducibility. The study recommends developing large-scale okra-specific datasets, integrating agronomic variables, deploying lightweight, mobile-ready architectures, and strengthening the adoption of explainable and federated learning frameworks to enable scalable, field-deployable diagnostic systems.
Why it matches plant phenotyping methods植物病害の症状を画像から検出・診断するAI手法を体系的にレビューしており、植物の病態を直接推定する方法論が中心です。
abstractThis study presents a systematic review of artificial intelligence applications, particularly machine learning and deep learning models, for okra leaf disease detection and diagnosis.
Abstract has not been obtained from indexed metadata or an accessible article page.
Why it matches plant phenotyping methods植物の病害・ストレス状態をVIS/NIR分光で検出する手法のレビューであり、植物フェノタイピング手法が中心です。
titleUnlocking the potential of 1D to 2D transformation in visible and near-infrared (VIS/NIR) spectroscopy for improved plant disease and stress detection: A review
Crop diseases continue to pose a serious challenge to global agricultural productivity, leading to substantial yield losses, economic instability, and threats to food security. Conventional crop disease detection methods rely heavily on manual visual inspection by farmers or experts, which is time-consuming, subjective, and impractical for large-scale and continuous monitoring. In response to these limitations, recent advancements in precision agriculture have encouraged the adoption of intelligent and automated techniques for crop health assessment. This review paper critically examines a dissertation that presents a deep learning-based framework for crop disease detection using convolutional neural networks (CNNs). The reviewed study employs image-based analysis of crop leaf images and formulates the problem as a binary classification task, distinguishing between healthy and diseased crops. The proposed system integrates image preprocessing techniques with hierarchical feature extraction through CNN architectures, eliminating the need for handcrafted features. Model performance is evaluated using standard classification metrics, including accuracy, precision, recall, F1-score, and confusion matrix analysis. Experimental findings demonstrate an overall classification accuracy of 93.75 percent, accompanied by balanced precision and recall values across both classes, indicating strong generalization and reliable disease detection capability. This review synthesizes the methodology, experimental outcomes, and significance of the study, while also highlighting existing limitations and potential directions for future research in intelligent precision agriculture systems
Why it matches plant phenotyping methods植物葉画像から健全・罹病状態を推定する画像ベース手法を中心に扱うレビューであり、植物病害状態のフェノタイピング手法に該当する。
abstractThis review paper critically examines a dissertation that presents a deep learning-based framework for crop disease detection using convolutional neural networks (CNNs).
Image / point-cloud registrationGrowth / development / phenology
The increasing complexity and volume of plant phenotypic data have driven the emergence of new computational and standardization frameworks to enable data integration, reproducibility, and reuse. This systematic literature review examines the current state of software tools, data models, and interoperability standards in plant phenomics, focusing on the implementation of the FAIR (Findable, Accessible, Interoperable, Reusable) principles. Using a structured PRISMA-based methodology, we analyze two major community driven initiatives MIAPPE and BrAPI as representative solutions for standardized data description and exchange. Furthermore, the study evaluates the role of High-Performance Computing (HPC) and deep learning in addressing computational challenges associated with large-scale datasets, including multi-sensor and 3D capture technologies. Special consideration is given to data governance, encompassing secure access, ethical use, and GDPR compliance within expanding phenomics ecosystems. The synthesis identifies persistent gaps in data harmonization and semantic alignment, proposing future research directions toward more integrated, secure, and scalable infrastructures. This review emphasizes that the success of plant phenomics depends on bridging the gap between standard definitions and their practical implementation within high-performance workflows.
Why it matches plant phenotyping methods植物フェノミクスのデータ標準、ソフトウェア、相互運用性を扱う方法論的レビューであり、MIAPPE・BrAPIや大規模フェノタイピング基盤が中心です。
abstractThis systematic literature review examines the current state of software tools, data models, and interoperability standards in plant phenomics
Abstract Water stress is a major limiting factor for crop productivity worldwide, and its impacts are intensifying due to climate variability and increasing water scarcity. This review focuses on the spatial and temporal scales in plant phenotyping as a critical approach to improving crop water‐stress assessment and supporting precision water management. We reviewed over 200 research articles and discussed the tools, techniques, and challenges associated with spatial and temporal phenotyping for assessing crop water stress, highlighting recent advances and emerging technologies. Emerging technologies such as artificial intelligence (AI) and Internet of Things systems are transforming crop water‐stress phenotyping by enabling real‐time monitoring and robust predictive models. Despite these advancements, challenges persist, including data gaps, platform limitations, and the need for scalable integration frameworks. The review examines key physiological and spectral indicators of crop water stress across multiple spatial and temporal scales using ground‐based sensors, unmanned aerial vehicles, and satellites. It further discusses multiscale phenotyping approaches and data fusion techniques to improve spatial resolution and prediction accuracy. Challenges in harmonizing spatial and temporal data are discussed, along with the need for interdisciplinary collaboration among the phenotyping, modeling, and agronomy domains. The review concludes by identifying future directions, including edge computing, high‐resolution imaging, and robust spatiotemporal phenotyping frameworks to enhance crop water‐stress assessment. By leveraging remote sensing, modeling, and AI, future phenotyping systems can improve water‐stress assessment, advance precision agriculture, and ensure resilience in water‐limited agroecosystems.
Why it matches plant phenotyping methods植物の水ストレス表現型評価に用いる空間・時間スケール、センサー、UAV、衛星、データ融合などの手法を中心に扱うレビューであり、対象範囲に明確に該当する。
abstractThis review focuses on the spatial and temporal scales in plant phenotyping as a critical approach to improving crop water‐stress assessment
Abstract Plant diseases are a major challenge in agriculture, leading to reduced crop yield and economic losses. Traditional methods of disease detection rely on manual inspection, which is time-consuming and less accurate. With the advancement of Deep Learning, Computer Vision, and Internet of Things, automated plant disease detection systems have been developed to improve accuracy and efficiency. Recent research shows that deep learning models, especially Convolutional Neural Networks (CNNs), are widely used for plant disease classification due to their ability to automatically extract features from images and achieve high accuracy [3], [34] . Transfer learning techniques using models such as ResNet and VGG further enhance performance, particularly when datasets are limited [9], [41] . In addition, lightweight models like MobileNet and ShuffleNet are being developed for deployment on mobile and IoT devices [2], [12] . Many studies use benchmark datasets such as PlantVillage, which provide high accuracy under controlled conditions. However, real-world applications face challenges such as varying lighting conditions, complex backgrounds, and limited dataset diversity [13], [15] . To address these issues, researchers are exploring advanced techniques such as data augmentation, object detection models like YOLO, and multimodal approaches that combine image data with environmental sensor data [5], [10] . IoT-based systems are also gaining importance as they enable real-time monitoring of crop conditions using sensors and smart devices [21], [26] . Furthermore, Explainable AI techniques such as Grad-CAM are being used to improve model transparency and help users understand the prediction results [25] . Despite significant progress, challenges remain in terms of model generalization, computational complexity, and real-time deployment. Future research should focus on developing lightweight, efficient, and scalable models, along with the use of large real-field datasets and edge computing technologies. Keywords Plant Disease Detection; Leaf Image Analysis; Convolutional Neural Network (CNN); Deep Learning; Transfer Learning; Computer Vision Internet of Things; Lightweight Models; Object Detection (YOLO); Multimodal Data Fusion; Explainable Artificial Intelligence (XAI)
Why it matches plant phenotyping methods植物病害を葉画像から推定するCNN・画像解析手法を体系的に扱うレビューであり、植物の病態を観測・推定するフェノタイピング手法が中心です。
titleHybrid CNN-Based Plant Disease Detection for Smart Agriculture: A Review
Plant diseases remain a big menace to agricultural productivity in the world, resulting into massive loss of produce, and compromised food security especially in areas experiencing resource shortages. Traditional methods of disease detection that are mostly reliant on expert visual evaluation are slow, subjective, and lack scalability. Over the past few years, the advent of the artificial intelligence (AI) and in particular, machine learning and deep learning algorithms have revolutionized the diagnostics of plant diseases by allowing the detection of the diseases through automated image-based methods at a high accuracy. Convolutional neural networks and computer vision technologies have demonstrated good potential to detect intricate patterns of diseases and facilitate precision farming. This review will critically analyze the advances in AI-driven plant disease detection to date, including the leading models, datasets, and performance trends. It was systematically and interpretively based on the methodological approach relying on the peer-reviewed literature of significant academic databases. It is emphasized in the analysis that deep learning models, and CNN-based architectures, in particular, and transfer learning training, in particular, are prevalent in the field and often achieve high accuracy when trained in controlled settings on benchmark datasets. Nevertheless, the review also notes the major limitations, such as the bias of the data set, low generalizability to real-life scenarios, high computational costs, and the absence of interpretability of the so-called black-box models. Such obstacles limit the applicability and adoption scale of AI solutions, particularly among the smallholder farmers. Moving forward, the evolution of multiple, field based datasets, explainable AI integration to enhance greater transparency, and edge computing to implement real time, on field diagnosis should be the focus of future research. It will also be necessary to strengthen the institutional support and digital infrastructure to close the technology development and practical application to achieve sustainable and inclusive agricultural transformation.
Why it matches plant phenotyping methods植物病害を画像から自動検出するAI手法を対象としたレビューであり、病害状態という植物表現型の取得・推定方法が中心です。
abstractThis review will critically analyze the advances in AI-driven plant disease detection to date, including the leading models, datasets, and performance trends.
Global food security faces unprecedented pressure from crop diseases, which are responsible for annual yield losses estimated at 20–40% of all food production. The application of deep learning methodologies, particularly convolutional neural network (CNN) architectures, to the automated detection and classification of crop diseases has emerged as a transformative paradigm within the domain of smart agriculture. A structured literature search was conducted using the academic databases Web of Science, Scopus, Google Scholar, and PubMed, covering the publication period from January 1996 to March 2026. The search strategy employed a combination of controlled vocabulary and free text search strings, including but not limited to the following terms and their Boolean combinations. The review examining the theoretical underpinnings and empirical performance of diverse CNN architectures including VGGNet, ResNet, Inception, DenseNet, EfficientNet, and Vision Transformers as applied to plant pathology. Special attention is directed towards the role of multispectral and hyperspectral imaging modalities, which extend disease detection capabilities beyond the visible spectrum and enable the identification of latent biochemical stress signatures before visible symptom onset. The review further explores the critical contribution of transfer learning in addressing the perennial challenge of limited annotated agricultural datasets, demonstrating how pre trained models can be fine tuned to achieve high diagnostic accuracy across diverse crop pathogen combinations. A dedicated section examines the rapidly maturing field of Explainable AI (XAI), with particular focus on gradient weighted class activation mapping (Grad CAM), integrated gradients, and SHAP based methods, which are essential for building agronomist trust and regulatory acceptability. The synthesis identifies persistent challenges including domain shift, class imbalance, computational constraints in field deployable systems, and the scarcity of standardised benchmark datasets. The review concludes with a forward looking perspective on federated learning, multimodal fusion architectures, and the integration of UAV based sensing with edge computing as the frontier of next generation agricultural AI systems.
Why it matches plant phenotyping methods植物病害の画像ベース検出・分類手法を中心に、CNN、マルチスペクトル／ハイパースペクトル画像、説明可能AIなどをレビューしており、植物状態（病害）の取得・推定方法が主題である。
abstractThe review examining the theoretical underpinnings and empirical performance of diverse CNN architectures including VGGNet, ResNet, Inception, DenseNet, EfficientNet, and Vision Transformers as applied to plant pathology.
The problems of plant leaf disease are rather serious in the world agricultural industry, leading to a significant decrease in crop quantity and quality, consequently, resulting in a huge loss in the economy and food insecurity. Detection and successful classification of plant diseases at the initial stage is essential to further agricultural output and the quality production of food. The recent improvements in the field of artificial intelligence (AI), specifically, machine learning (ML) and deep learning (DL), have shown significant prospects in automating and enhancing methods of diagnosing plant leaf diseases by using a wide variety of ML and DL algorithms. This review article presents an in-depth analysis of thirty novel methods created by researchers to diagnose and classify plant leaf diseases. They are such conventional classifiers as Support Vector Machines (SVM), Random Forests (RF), and K-Nearest Neighbors (KNN), along with some advanced DL architectures, such as Convolutional Neural Networks (CNN), VGG16, ResNet50, InceptionResNetV2, EfficientNet, and various hybrids. The review analysis takes into consideration the methodologies applied, performance metrics, and insights in practice, as well as the strengths and weaknesses of both. The most crucial findings of the review show that deep learning models, and CNNs in particular, tend to be more accurate, robust, and feature extractors than traditional models of MLs. The performance of classification is also enhanced by numerous hybrid models that will use ML together with DL, and transfer learning has been an effective method to enhance the generalization using small datasets. Nevertheless, with all this progress, the issues of diversity of datasets, computational resource requirements and model interpretability are still to be explored in the future.
Why it matches plant phenotyping methods植物葉の病徴を画像から検出・分類する機械学習手法を体系的に比較するレビューであり、植物状態の取得・推定手法が中心である。
abstractThis review article presents an in-depth analysis of thirty novel methods created by researchers to diagnose and classify plant leaf diseases.
Rice is one of the simple food crops that has been cultivated in the majority of countries. Rice leaf diseases (RLDs) are a major problem in crop production since they may result in low productivity and economic losses. Traditional ways of detecting an illness may be time-consuming and even labor-intensive, and at times may need specialized skills. The popularity of preceding works on detecting RLDs has relied on machine learning (ML) and image processing approaches. On the other hand, deep learning (DL) methodologies are more applicable in disease detection problems because they can learn stipulated patterns on big data without using feature extraction methods. This systematic review explores various ML and DL methods used in the literature for RLD detection, which includes survey articles based on convolutional neural network (CNN), transfer learning, and advanced AI approaches. The review of existing open-source datasets is also discussed in this survey. In addition, it examines limitations of current models related to practical implementation, data diversity, domain adaptation, and hardware limitations. Lastly, this survey identifies future research directions to improve the strength and usage of DL models in real-world agriculture settings. This survey comprehensively reviews more than 70 peer-reviewed publications (2019–2025) sourced from IEEE, Elsevier, Springer, ACM, and MDPI digital libraries.
Why it matches plant phenotyping methodsイネ葉の病害を画像から検出する機械学習・深層学習手法を体系的にレビューしており、植物の病害状態を推定するフェノタイピング手法が中心である。
abstractThis systematic review explores various ML and DL methods used in the literature for RLD detection
Background/Objectives: Downy mildew, caused by Peronosclerospora and Sclerophthora species, is a major constraint to maize production in tropical and subtropical regions, with yield losses of 30-100%. This systematic review synthesised evidence on methods used to screen maize for downy mildew resistance and assessed their effectiveness, reliability, and associated markers. Methods: PubMed, Google Scholar, ScienceDirect, and CAB Abstracts were searched (last searched 22 October 2025) for English-language studies (1990-2025) evaluating phenotypic or molecular screening methods. Risk of bias was assessed using the RoB 2 framework. Narrative synthesis was conducted following a protocol registered on the Open Science Framework. Results: Twelve studies met the inclusion criteria, predominantly from India and Cambodia. Spreader row systems (seven studies) and conidial spray inoculation (six studies) were the most common field methods, while the glasshouse sandwich technique generated the highest disease pressure. Cross-method correlations were strong (r = 0.92-0.99), and heritability estimates ranged from 0.50 to 0.97. QTL mapping identified resistance loci on chromosomes 2, 3, and 6, with chromosome 6 stable across multiple pathogen species. Evidence certainty was moderate for method effectiveness and low for molecular markers. Conclusions: Established phenotypic screening methods reliably discriminate resistant germplasm; however, standardised protocols, broader geographic validation, and independent molecular marker confirmation are needed.
Why it matches plant phenotyping methodsトウモロコシのべと病抵抗性という植物状態を評価する表現型スクリーニング法を体系的にレビューし、方法の有効性・信頼性を比較しているため、手法レビューとして収載する。
titleScreening Methods for Downy Mildew Resistance in Maize: A Systematic Review.
Advancements in agricultural technologies have increasingly emphasized technical innovations aimed at improving the predictability and reliability of agricultural outputs. These aspects encompass developments in agricultural machinery, automation technologies, biotechnology, and controlled environment farming systems. This article focuses on Remote Sensing (RS)-based approaches applied to agricultural yield estimation for both crops and plants. RS technologies offer enhanced precision and scalability, making them particularly effective for large-scale agricultural monitoring and analysis. A systematic classification of RS-based methodologies employed for crop yield estimation is presented in this study. These methodologies are categorized into: (i) Sensor-Based approaches, (ii) Platform-Based approaches, (iii) Analytical and Modeling-based methods, and (iv) Machine Learning (ML)-driven models. Based on findings reported across multiple studies, it is observed that Deep Learning (DL)-based architectures consistently achieve superior performance across key evaluation metrics, including accuracy, precision, recall, and F1-score. This performance advantage stems from their capacity to learn hierarchical representations, capture complex non-linear relationships, scale efficiently with large datasets, and reduce reliance on manual feature engineering. Following this classification, our article presents a comprehensive discussion of the limitations associated with these methodologies. These challenges are organized into four major categories: (i) Environmental, (ii) Algorithmic, (iii) Hardware and Operational, and (iv) Wireless Sensor Networks (WSNs) related limitations. The adopted classification framework helps readers identify and address the key challenges associated with effective yield estimation in crops and plants. Moreover, the article concludes by outlining several future research directions intended to support and guide both early-career and experienced researchers in this domain.
Why it matches plant phenotyping methods作物収量という植物形質のリモートセンシング推定法を体系的に分類・比較し、環境・アルゴリズム・ハードウェア上の限界を論じる方法論レビューであり、フェノタイピング手法が中心である。
titleA review of remote sensing-based crop yield estimation: machine learning techniques and environmental, algorithmic, and hardware limitations
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · Crossref · checked 15 Sept 2026
High-throughput plant phenotyping is increasingly constrained by the mismatch between the demand for field-relevant, fine-grained phenotypic data and the limited capability of conventional observation platforms under complex agricultural conditions. In this context, mobile phenotyping systems, particularly ground robots, are emerging as a key technological pathway for bridging macro-scale monitoring and organ-level trait analysis. This review examines the development of mobile phenotyping platforms for high-throughput plant phenotyping, with emphasis on the evolving role of ground robots in field-based sensing, decision-making, and active interaction. We first compare the functional characteristics of unmanned aerial vehicles and unmanned ground vehicles and discuss their complementarity in multiscale phenotypic data acquisition. We then summarize recent advances in the core technical framework of mobile phenotyping robots, including multimodal perception, localization and mapping, motion planning, deep-learning-based phenotypic analysis, active observation, robotic intervention, and edge deployment. Major challenges are further discussed, particularly those related to environmental generalization, data annotation, standardization, reproducibility, and long-term field reliability. Finally, future directions are outlined from the perspectives of air–ground collaboration, multi-robot systems, foundation models, and embodied intelligence. This review highlights ground robots as a central carrier for advancing mobile phenotyping toward autonomous, fine-grained, and field-deployable systems.
Why it matches plant phenotyping methods植物フェノタイピング用の移動ロボットプラットフォームと、マルチモーダルセンシング・表現型解析などの技術を中心に扱うレビューであり、対象分野の方法論的レビューに該当する。
abstractThis review examines the development of mobile phenotyping platforms for high-throughput plant phenotyping
This study presents a comparative evaluation of manual inspection, ground-based sensors, and UAV-based remote sensing for detecting crop stress in paddy, maize, and coconut fields across Malaysia and China. Although sensing technologies have advanced considerably, cross-country comparisons between regions with differing levels of technological maturity remain limited. China, recognised for its advanced adoption of UAV and sensor-based agriculture, provides a benchmark against Malaysia’s developing digital agriculture landscape. Each method was assessed based on accuracy, responsiveness, scalability, and cost-effectiveness under field conditions. UAV-based remote sensing achieved the highest overall accuracy (mean 92%) and demonstrated superior scalability, enabling rapid large-area monitoring using vegetation indices such as NDVI and NDRE. Ground-based sensors, including soil moisture probes and chlorophyll meters, showed moderate accuracy (mean 81%) and were suitable for plot-level monitoring with real-time feedback. Manual inspection recorded the lowest accuracy (mean 68%) and limited scalability due to labour dependency and subjective assessment. UAV methods were particularly effective in early stress detection, with thermal imaging identifying canopy temperature anomalies 3–5 days before visible symptoms, especially in maize and coconut fields. Integrating UAV and ground-based sensing provided more comprehensive and timely assessments than individual approaches. These findings support the development of scalable precision agriculture frameworks tailored to tropical and subtropical systems.
Why it matches plant phenotyping methods作物ストレスという植物状態を対象に、手動観察・地上センサー・UAVリモートセンシングを精度、応答性、拡張性、費用で比較評価しており、センシング手法の技術評価が中心である。
abstractThis study presents a comparative evaluation of manual inspection, ground-based sensors, and UAV-based remote sensing for detecting crop stress in paddy, maize, and coconut fields across Malaysia and China.
Crop diseases caused by diverse pathogens, including fungi, bacteria, and viruses, lead to result in global yield losses of nearly 20–40% each year, posing a major significant threat to food security and agricultural sustainability. Traditional detection methods, relying on visual inspection and routine laboratory assays, are often slow, labour-intensive, and prone to inaccuracies, resulting in delayed disease management. By enabling quick, precise, and scalable detection systems, recent advancements in molecular biology, digital technologies, and remote sensing have completely transformed the field of crop disease diagnostics. Molecular techniques such as real-time PCR, loop-mediated isothermal amplification (LAMP), and CRISPR-based assays (e.g., SHERLOCK) offer high sensitivity and specificity, allowing early on-site pathogen identification. Digital technologies driven by artificial intelligence, including smartphone-based diagnostic tools and convolutional neural networks (CNNs), now achieve over 95% accuracy in image-based disease recognition, making advanced diagnostics more accessible to farmers. Remote sensing approaches particularly drone-assisted hyperspectral and multispectral imaging facilitate non-invasive, large-scale monitoring and early detection of disease outbreaks across agricultural landscapes. Additionally, metagenomics and next-generation sequencing (NGS) enable the discovery of novel pathogens and support resistance-breeding programs through comprehensive genomic insights. Collectively, these innovative technologies enhance the speed, precision, and cost-effectiveness of crop disease detection, potentially reducing yield losses by up to 30% and promoting sustainable agriculture. This review highlights the principles, recent advancements, advantages, limitations, and prospects of integrating molecular, digital, and remote sensing tools to strengthen global crop health management systems.
Why it matches plant phenotyping methods植物病害の画像認識、ドローン搭載ハイパースペクトル・マルチスペクトルセンシングを用いた病害状態の取得・検出技術を体系的に扱うレビューであり、植物フェノタイピング手法が中心的です。分子診断も含みますが、デジタル・リモートセンシングによる植物病害表現型の推定が明示されています。
abstractThis review highlights the principles, recent advancements, advantages, limitations, and prospects of integrating molecular, digital, and remote sensing tools to strengthen global crop health management systems.
A dynamic analysis of plant ion homeostasis is imperative for elucidating the mechanisms underlying stress resistance and enabling precision agriculture. However, conventional detection methods face challenges in simultaneously meeting the synergistic demands of in situ , real-time, minimally invasive, and high-resolution monitoring, which severely restricts advancements in this field. Microneedle sensing technology, with a focus on the "microneedle body-sensing unit-signal transmission" architecture, represents a significant paradigm shift from ex vivo destructive detection to in vivo minimally invasive dynamic monitoring. This article employs a systematic approach to elucidate the scientific implications and implementation challenges associated with in situ decoding of plant ionic signals. The proposed framework traces the technological evolution of microneedle sensing across the sensing, detection, and system layers, elucidating how it progressively overcomes key bottlenecks, including minimally invasive adaptation, specific recognition, and long-term, stable monitoring. Furthermore, typical applications of this technology in signal transduction analysis, stress-resistant variety screening, and precision field management are reviewed. It analyzes core challenges from two perspectives: fundamental research and industrialization. Ongoing advancements in material intelligence and system integration will position MN sensing technology as an indispensable tool in smart agriculture and plant physiology research. This technology provides critical support for addressing global food security challenges.
Why it matches plant phenotyping methods植物イオン状態を対象とするマイクロニードルセンシングの原理・実装・応用・課題を体系的にレビューしており、植物の生理状態を非侵襲・リアルタイムに取得するセンシング手法が中心である。
abstractMicroneedle sensing technology, with a focus on the "microneedle body-sensing unit-signal transmission" architecture, represents a significant paradigm shift from ex vivo destructive detection to in vivo minimally invasive dynamic monitoring.
Agriculture currently faces the dual pressures of ensuring global food security and adapting to rapid climate change. To cope with these challenges, researchers have introduced several modern mechanization technologies, including advanced farm machinery, autonomous navigation systems, artificial intelligence, sensing technologies, and communication tools, to enhance productivity and sustainability (Syed et al., 2025a). These technologies enable data-driven decision-making by allowing continuous, large-scale acquisition and analysis of crop and environmental information. Consequently, accurately predicting crop yields and monitoring plant health in real time have become critical prerequisites for precision agricultural management (Syed et al., 2025). Traditional measurement methods-often labor-intensive, destructive, and spatially limited-are increasingly unable to meet the demands of modern large-scale farming. In this context, the integration of Remote Together, these ten contributions illustrate the maturation of agricultural remote sensing, moving towards models that are not only more accurate but also lighter, more interpretable, and more resilient to environmental noise. By combining satellite and UAV data with advanced computational models, these innovative approaches are paving the way for a more resilient and productive global food system. Future research will increasingly focus on improving the precision of crop yield estimation models through multi-dimensional analyses. As agricultural environments grow more complex, integrating AI-powered models with multi-sensor fusion technologies will be essential. Innovations such as lightweight neural networks and multimodal cross-attention frameworks will enable the detection of small, occluded, and densely packed targets with greater accuracy, thereby refining crop-specific metrics such as photosynthetically active radiation (FPAR) and nitrogen content. This, in turn, will enhance crop health monitoring and yield predictions.Additionally, UAV-based remote sensing, combined with multitier feature selection, will improve nitrogen content analysis in crops such as cotton, while image dehazing models and light-use efficiency frameworks will bolster biomass estimation.Emerging technologies such as the Ta-YOLO framework will further optimize small fruit detection in dense canopies, advancing overall crop detection accuracy.A key challenge lies in adapting these models to handle real-world complexities, such as variable environmental conditions. Future work will focus on improving the robustness of these models through dynamic coding networks and performance optimization, ensuring they can operate in heterogeneous agricultural environments.Interdisciplinary collaboration between agriculture, AI, and remote sensing experts will accelerate the development and deployment of these approaches, paving the way for more efficient crop yield estimation systems that are critical for ensuring food security and sustainable agricultural practices.
Why it matches plant phenotyping methods作物収量・健康・バイオマス・窒素含量などの植物形質を、衛星・UAVリモートセンシングと計算モデルで推定する手法群を中心に扱う編集レビューであり、方法論的役割が明確。
titleInnovative approaches in remote sensing for precise crop yield estimation: advancements, applications, and future directions
LeafPhysiological trait estimationGrowth / development / phenology
Purpose This paper aims to explore the role of plant growth monitoring in precision agriculture, ecological environment protection and urban greening, this study analyzes the applications, challenges and future development directions of wearable flexible sensors for monitoring plant physiology and growth environments. Design/methodology/approach This review focuses on wearable flexible sensor technologies for plant physiology and environmental monitoring: optical sensors, flexible electronic sensors and chemical/biological sensors. The data were collected through Web of Science search, and then carefully manually organized, analyzed, and summarized. Findings Current challenges for wearable sensors in plant growth monitoring include insufficient long-term stability, environmental interference suppression and multi-sensor collaborative optimization. Originality/value Propose future development directions such as the development of new flexible materials, design of self-powered systems, solar energy harvesting sensors integrated with leaf veins to avoid shading critical photosynthetic tissues and AI-driven data intelligent analysis. These innovations, based on interdisciplinary integration, are expected to promote the development of precision agriculture and intelligent ecosystems.
Why it matches plant phenotyping methods植物生理・生育状態を測定するウェアラブル柔軟センサー技術を中心に整理したレビューであり、環境モニタリングも扱うが植物フェノタイピング手法のレビューとして中心性が明確。
abstractThis review focuses on wearable flexible sensor technologies for plant physiology and environmental monitoring: optical sensors, flexible electronic sensors and chemical/biological sensors.
Abstract The Affordable Phenomics special topic in The Plant Phenome Journal showcased recent advances that expand the accessibility, cost‐effectiveness, and scalability of plant phenotyping technologies. This collection of 15 articles presented innovative approaches, ranging from low‐cost sensors and open‐source analytical pipelines to artificial intelligence–driven image analysis and spectroscopy, that address the financial and technical barriers limiting widespread adoption of plant phenomics. In this foreword, we highlight the contributions featured in the special topic. The foreword also serves as an overview of the state of the art in affordable phenomics by summarizing the vision and perspectives presented in the invited review “Affordable phenomics: Expanding access to enhancing genetic gain in plant breeding.”
Why it matches plant phenotyping methods植物フェノタイピング技術に関する特集の進展と手法を概観するフォワードであり、フェノタイピング方法論のレビューとして中心的です。
abstractshowcased recent advances that expand the accessibility, cost‐effectiveness, and scalability of plant phenotyping technologies
Fruits are a critical component of the human diet, as they provide essential dietary nutrients that play an important role in the functioning of the human body and maintaining health. It is well-known that consuming fruits has various benefits, including the prevention of chronic diseases, cancer, and cardiovascular disorders. Thus, wider availability and maintaining the quality of fruits are highly required. Around 25% of global crop losses reported annually are attributed to disease and pest infestations, as per the Food and Agriculture Organization. Fungal pathogens are a major cause of post-harvest diseases, which significantly affect production and lead to economic losses. To address this, disease diagnosis at an early stage is crucial to enable timely monitoring, implementation of prevention techniques, and minimizing storage-related losses. Various methods are available for early pathogen detection; spectroscopic and imaging techniques have been widely applied as they offer cost-effectiveness, potential for real-time analysis, and a non-destructive nature of analysis. When integrated with advanced decision-support tools, these instrumental techniques can enable rapid and accurate detection of fungal diseases in fruits. In recent years, nanotechnology has emerged as a promising approach, with a wide range of nanoparticles being utilized to develop nanobiosensors for various applications. This review also highlights recent advancements in the use of nanomaterials and nanoparticle-based sensing systems for the detection of pathogens, providing an overview of their potential role in improving post-harvest disease diagnostics.
Why it matches plant phenotyping methods果実の真菌病という植物器官の病状態を対象に、分光・画像診断ツールを中心としてレビューしており、病害状態の取得・検出手法が主題である。
abstractThis review also highlights recent advancements in the use of nanomaterials and nanoparticle-based sensing systems for the detection of pathogens
Charcoal rot, caused by Macrophomina phaseolina, is a destructive soil-borne disease that threatens several oilseed crops. Its persistence in the soil through microsclerotia, wide host range, and strong association with drought and heat stress makes it a formidable challenge for sustainable production. Breeding for resistance is widely recognized as the most effective and environmentally sound management strategy. This review synthesizes current knowledge on the biology and economic impact of charcoal rot in oilseed crops, with a focus on screening methodologies, genetic resistance, and breeding interventions. Field-based techniques such as root and stem severity scoring and colony-forming unit indices remain central to resistance evaluation, although challenges of standardization and reproducibility persist. Advances in molecular and genomic tools, including QTL mapping, genome-wide association studies (GWASs), marker-assisted selection (MAS), and genomic selection (GS), have begun to strengthen the identification and deployment of resistance loci. In addition, speed breeding, high-throughput phenotyping, and gene-editing platforms such as CRISPR/Cas offer novel opportunities to accelerate cultivar development. Integration of these approaches, along with the exploration of wild relatives and pre-breeding materials, is essential for broadening the genetic base of resistance and achieving durable, climate-resilient oilseed production. By linking pathogen biology, screening methods, and advanced genetic strategies, this review provides a comprehensive framework for future breeding programs aimed at mitigating the impact of charcoal rot in oilseed crops.
Why it matches plant phenotyping methods耐病性評価に用いる根・茎の病徴重症度スコアリングやCFU指標などのスクリーニング方法を明示的に扱い、標準化・再現性の課題も論じるレビューであり、植物病害表現型の取得法が主要な内容に含まれる。
abstractThis review synthesizes current knowledge on the biology and economic impact of charcoal rot in oilseed crops, with a focus on screening methodologies, genetic resistance, and breeding interventions.
Abstract Plant diseases are a serious issue that cause food shortages and financial losses. In large-scale farming, traditional disease detection techniques that primarily rely on expert inspection are frequently unfeasible. Deep learning and super-resolution methods for plant disease detection are thoroughly reviewed in this study, with an emphasis on their use in leaf-level imaging and UAV-based monitoring. This thorough review was carried out using the PRISMA framework, looking at peer-reviewed publications from important databases like Google Scholar, ScienceDirect, Web of Science, and Scopus. According to the review, low spatial resolution, environmental variability, occlusion, and domain shift cause convolutional and transformer-based models to perform poorly at canopy and field scales, despite achieving high accuracy on leaf-level datasets. Despite improving the perceptual quality of aerial imagery, super-resolution techniques are still difficult to incorporate into disease detection pipelines because of their high computational overhead, lack of task-aware training, scarcity of annotated UAV datasets, and poor generalization in real-world scenarios. There are few actual architectural implementations of cross-scale integration strategies currently in use; most of them are conceptual. Deep learning for plant disease detection has come a long way, but reliably deploying this technology outside of controlled environments remains challenging due to scale differences and data availability constraints. Coordinated developments in cross-scale learning approaches, data collection, and model design are needed to address these issues. The results also emphasize the significance of multimodal data fusion, super-resolution-assisted domain adaptation, and hierarchical transfer learning as viable approaches to enhancing the scalability and dependability of plant health monitoring systems. This review highlights useful research directions and provides a critical overview of current methods. It encourages the development of AI-powered solutions for better crop management, early disease detection, and sustainable farming methods.
Why it matches plant phenotyping methods植物病害の葉・キャノピー画像から病害状態を検出する深層学習および超解像手法を対象とした体系的レビューであり、植物状態の取得・推定手法が中心です。
titleA systematic review of deep learning and super resolution techniques for leaf level and canopy level plant disease detection
Understanding how plants respond to dynamic and spatially variable stimuli is a key goal in plant sciences. Traditional imaging methods often involve a trade-off between environmental control and spatial resolution, limiting their ability to capture real-time responses in high resolution. Microfluidic technology overcomes these limitations by facilitating precise control of environmental conditions and high-resolution live imaging. In the past two decades, microfluidic technology has increasingly been applied in plant sciences research. This review summarises current applications of microfluidic technology in plant sciences, including studies of root-rhizosphere interactions, tip-growing plant cells, plant protoplasts, and plant phenotyping. Emerging trends are explored, and key research gaps are highlighted.
Why it matches plant phenotyping methods植物科学におけるマイクロ流体技術の応用を総説し、植物フェノタイピングを明示的な対象として含むため、フェノタイピング手法レビューとして収録する。
abstractThis review summarises current applications of microfluidic technology in plant sciences, including studies of root-rhizosphere interactions, tip-growing plant cells, plant protoplasts, and plant phenotyping.
Charcoal rot, caused by Macrophomina phaseolina, is a destructive soil-borne disease that threatens several oilseed crops. Its persistence in the soil through microsclerotia, wide host range, and strong association with drought and heat stress makes it a formidable challenge for sustainable production. Breeding for resistance is widely recognized as the most effective and environmentally sound management strategy. This review synthesizes current knowledge on the biology and economic impact of charcoal rot in oilseed crops, with a focus on screening methodologies, genetic resistance, and breeding interventions. Field-based techniques such as root and stem severity scoring and colony-forming unit indices remain central to resistance evaluation, although challenges of standardization and reproducibility persist. Advances in molecular and genomic tools, including QTL mapping, genome-wide association studies (GWASs), marker-assisted selection (MAS), and genomic selection (GS), have begun to strengthen the identification and deployment of resistance loci. In addition, speed breeding, high-throughput phenotyping, and gene-editing platforms such as CRISPR/Cas offer novel opportunities to accelerate cultivar development. Integration of these approaches, along with the exploration of wild relatives and pre-breeding materials, is essential for broadening the genetic base of resistance and achieving durable, climate-resilient oilseed production. By linking pathogen biology, screening methods, and advanced genetic strategies, this review provides a comprehensive framework for future breeding programs aimed at mitigating the impact of charcoal rot in oilseed crops.
Why it matches plant phenotyping methods油糧作物の炭腐病抵抗性評価に用いる症状重症度スコアやCFU指標などのスクリーニング方法を中心に整理したレビューであり、植物病害状態の表現型測定法が実質的な主題である。
abstractThis review synthesizes current knowledge on the biology and economic impact of charcoal rot in oilseed crops, with a focus on screening methodologies, genetic resistance, and breeding interventions.
Unmanned aerial vehicle (UAV) remote sensing has evolved from experimental imaging into an operational diagnostic infrastructure supporting climate-smart agriculture through high-resolution, flexible, and timely crop observation. This review synthesizes advances in UAV platforms, multisensor payloads, artificial intelligence (AI) analytics, and multisource data fusion to evaluate their combined potential for monitoring heterogeneous smallholder systems. A PRISMA-guided analysis of 59 studies (2013–2024) classified sensing architectures, analytical approaches, and application domains across diverse agroecological contexts. Integrated UAV–AI frameworks improve detection of crop stress, yield variability, biomass distribution, and phenological dynamics compared with conventional monitoring, particularly when multimodal sensor data are fused with satellite and ground observations. Predictive performance and diagnostic reliability increase when spectral, thermal, and structural datasets are analyzed jointly using machine-learning or deep-learning models. However, scalability remains constrained by operational, infra-structural, and regulatory factors, especially in resource-limited systems. These findings demonstrate that integrated sensing–analytics systems form a critical foundation for scalable climate-smart agricultural transformation and data-driven decision support across farm, landscape, and institutional scales.
Why it matches plant phenotyping methodsUAVセンシングとAIによる作物ストレス、収量変動、バイオマス、フェノロジーの観測・推定技術を体系的にレビューしており、植物形質・状態の取得方法が中心である。
abstractThis review synthesizes advances in UAV platforms, multisensor payloads, artificial intelligence (AI) analytics, and multisource data fusion
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 5 Sept 2026
The last decade has marked a period of rapid innovation in high-throughput phenotyping (HTP) of plants. This includes the establishment of robotic phenotyping infrastructure, development of new sensors, and improvements in computation for downstream analysis. While HTP approaches have revolutionized data collection, meaningful insights into plant function require a yet deeper connection between resultant HTP-based information and biological responses. We suggest that dynamic process-based plant models, which simulate growth and physiology in a time-explicit manner, can serve as a functional link between high-throughput methods and whole-plant mechanisms of growth. Using this framework, we review recent research that has leveraged HTP approaches for estimation of plant traits that are commonly used as process-based model (PBM) variables. Through this analysis, we review successes and identify emerging directions for future research. Finally, we highlight the varied ways that HTP can be used in conjunction with PBMs as a tool to advance discovery and improve prediction of plant growth.
Why it matches plant phenotyping methodsHTP基盤、センサー、計算解析、および植物形質推定を対象としたレビューであり、植物フェノタイピング手法が中心的に扱われている。
abstractThe last decade has marked a period of rapid innovation in high-throughput phenotyping (HTP) of plants.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 15 Sept 2026
Plants are essential for global food security and ecosystem stability, exhibiting high sensitivity to environmental fluctuations and both biotic and abiotic stressors. Consequently, monitoring plant health is critical for advancing sustainable agriculture and optimizing resource management. However, traditional methods often rely on destructive sampling or intermittent measurements, failing to capture dynamic physiological processes. Recent developments in flexible wearable sensors enable real-time, in-situ, and non-invasive monitoring of key plant physiological parameters, offering new opportunities for plant phenotyping and precision agriculture. This review summarizes recent advances in material design and interface engineering of plant wearable sensors, focusing on their role in establishing biotic-abiotic interfaces for reliable signal acquisition and their applications in monitoring plant physiological signals and stress responses. Finally, we outline key challenges related to field stability and data integration, envisioning these sensors as pivotal components of intelligent environmental monitoring networks that promote sustainable agriculture and safeguard ecosystem health.
Why it matches plant phenotyping methods植物の生理状態・ストレス応答を取得するウェアラブルセンサー技術を中心に扱う、植物フェノタイピング手法のレビューである。
abstractRecent developments in flexible wearable sensors enable real-time, in-situ, and non-invasive monitoring of key plant physiological parameters, offering new opportunities for plant phenotyping and precision agriculture.
Field / plotLaboratory / benchtopNeRF / 3D Gaussian SplattingPhotogrammetry / SfM / MVSLiDAR / point cloudRGB-D / ToFWhole plant / canopy / plot / field2D/3D reconstruction
Three-dimensional point cloud (3DPC) data capture detailed geometric and structural plant traits beyond the capability of 2D imaging. When combined with artificial intelligence (AI), it offers a powerful, non-invasive tool for plant phenotyping, which is crucial for driving advancements in plant breeding and agriculture. However, challenges related to data complexity, limited datasets, and model generalization hinder 3DPC’s widespread adoption. To provide a comprehensive overview and guide future research in this area, we conducted a systematic literature review (SLR) following Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines by analysing 381 papers published between January 2017 and October 2025 from major databases. Our review examines the advantages, current status, limitations, and future directions of AI applications in 3DPC-based plant phenotyping. Our findings indicate a rapid increase in publications since 2022, with deep learning (DL) methods, especially pointwise MLP-based networks, driving much of this growth, with a notable recent surge in Transformer-based, Graph-based, and particularly Hybrid models that combine their strengths. Furthermore, novel methods like Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) are emerging as powerful tools for 3D reconstruction and scene synthesis. Time-of-Flight (ToF) and Structure from Motion and Multi-View Stereo (SfM-MVS) technologies remain the predominant 3DPC data acquisition techniques. Research in this area focuses on trees/shrubs and cereals, typically involving single-species studies. Although the overall use of public datasets remains low (18.9%), their adoption has significantly increased since 2020. Key limitations identified include: (1) a lack of standardized data collection and formats, (2) insufficient model robustness and generalization, especially from lab to field, (3) high computational demands, and (4) a reliance on species-specific models. The future of AI-driven 3DPC phenotyping hinges on overcoming these bottlenecks. Priority should be given to: developing field-deployable, computationally efficient models; exploring the potential of the foundation model; establishing diverse and standardized public datasets; and strengthening the integration of 3D phenomics with genomics to bridge the genotype-to-phenotype gap. This review provides a foundational roadmap to guide research in plant phenomics, crop breeding, and plant science.
Why it matches plant phenotyping methods3D点群とAIによる植物形質取得・解析を中心に扱う体系的レビューであり、植物フェノタイピング手法のレビューとして明確に適格。
titleAI-driven 3D point cloud analysis in plant phenotyping: A Systematic Review
Abiotic and biotic stress factors pose a significant threat to plant productivity and global food security. This review uses bibliometric analysis and literature synthesis to comprehensively examine the role of artificial intelligence (AI) and machine learning (ML) techniques in plant stress management. A total of 5369 publications retrieved from the Web of Science database between 2010 and 2024 were analysed using VOSviewer to evaluate publication trends, countries, institutions, and keywords. China, the US, and India were identified as the leading countries, with deep learning, convolutional neural networks, and image-based diagnostic methods emerging as key areas. The second phase revealed that DL architectures such as YOLO, EfficientNet, and Transformer, as well as methods like remote sensing and hyperspectral imaging, can accurately detect abiotic (drought, salinity, water, and heavy metals) and biotic (fungal, bacterial, and viral) stress. Machine learning (ML) algorithms such as support vector machine (SVM), random forest (RF), and artificial neural network (ANN) have also been found to be effective in stress prediction. However, challenges such as data imbalance, model interpretability, and high computational requirements persist. To address these issues, open-access datasets, low-cost and transparent models, multimodal sensing systems, and ethical AI approaches are recommended. This review contributes to the field by highlighting strategic and technical gaps in the development of scalable and sustainable AI-supported plant stress management systems.
Why it matches plant phenotyping methods植物ストレスの画像・リモートセンシング・ハイパースペクトル等による検出と、AI/ML手法の技術的レビューが中心であり、植物の状態・症状を推定するフェノタイピング手法レビューに該当する。
abstractThis review uses bibliometric analysis and literature synthesis to comprehensively examine the role of artificial intelligence (AI) and machine learning (ML) techniques in plant stress management.
Agriculture serves as a major source of food and plays a key function as the backbone of most countries’ economies. However, farmers are encountering many challenges in this sector, such as drought, flooding, diseases, nutrient deficiency, and so on. The technological advancements in the field of agriculture, also called smart agriculture, are necessary to address the requirements of the expanding population and manage the associated challenges. Among those, plant leaf diseases are the primary concern that severely impacts crop yield and economic stability. This technical review examines various Machine Learning (ML) and Deep Learning (DL) approaches used to identify and classify different plant leaf diseases. This review gives an overview of the current state-of-the-art ML, DL, and IoT-enabled disease prediction systems and their recent advances in developing an intelligent system in smart agriculture. It provides insights into the various technological developments and discusses the benefits and opportunities of AI-based models in plant disease management.
Why it matches plant phenotyping methods植物葉の病徴を画像・機械学習で検出・分類する手法を中心に扱うレビューであり、植物の疾病状態を推定するフェノタイピング手法レビューに該当する。
abstractThis technical review examines various Machine Learning (ML) and Deep Learning (DL) approaches used to identify and classify different plant leaf diseases.
Efficient management and precise monitoring are essential for the sustainable control of crop diseases and pests. Traditional unimodal methods exhibit reduced reliability due to data gaps and environmental fluctuations. Multimodal artificial intelligence (AI) offers a promising alternative by integrating complementary data sources and enhancing robustness and adaptability. However, a comprehensive synthesis connecting multimodal AI with multi-scale disease and pest management is still lacking. Based on 950 publications from the past decade reflecting a 31.7% annual growth rate over the past five years, this review examines the evolution of AI-driven research and compares unimodal and multimodal approaches by summarizing major data modalities, fusion strategies, and modeling techniques. Deep learning emerges as the most widely used class of AI methods, and quantitative evidence indicates that multimodal systems achieve approximately 3–48.9% higher diagnostic accuracy than unimodal models. Evidence from 27 studies demonstrates the effectiveness of multimodal fusion across imaging, spectral, environmental, and sensor-based datasets. Building upon these findings, we propose a novel three-level management framework comprising point-level diagnosis, area-scale monitoring, and spatiotemporal forecasting, clarifying how multimodal AI strengthens each task. We further highlight the role of Plant Electronic Medical Records (PEMRs) and outline a conceptual virtual plant clinic to support continuous, data-driven crop health services. Finally, this review identifies key directions including advanced fusion strategies, lightweight and interpretable models, digital twin integration, and scalable decision-support systems, which are essential for intelligent and sustainable crop disease and pest management.
Why it matches plant phenotyping methods植物病害の診断・モニタリングを対象に、画像・スペクトル・環境・センサーデータを統合するAI手法とその性能を体系的にレビューしており、植物の病害状態推定が中心的な方法論的貢献である。
abstractthis review examines the evolution of AI-driven research and compares unimodal and multimodal approaches by summarizing major data modalities, fusion strategies, and modeling techniques.
Robotic pollination represents a pivotal component of smart agriculture, with foundational architectures for target recognition, path planning, and motion control having been progressively established. However, developing an efficient and robust pollination system that integrates perception, decision-making, and execution within real-world scenarios remains confronted with complex challenges. This study systematically reviews recent advancements in the field and distills the core technical issues of greenhouse robotic pollination into three primary domains: target detection and pose estimation, end-effector design, and pollination strategies combined with motion control. Focusing on the visual perception of flowers, actuator architecture, and operational tactics, this review synthesizes existing academic findings to evaluate the state-of-the-art in flower detection and pose estimation, characterize diverse end-effector designs, and analyze the evolutionary trajectory of motion control techniques. Specifically, the analysis encompasses the impact of detection algorithms on recognition accuracy and robustness, the structural classification and performance attributes of pollination mechanisms, and the optimization of control strategies. Furthermore, the study categorizes global research backgrounds, technical methodologies, and paradigmatic system cases, offering a critical evaluation of experiences in constructing automated pollination systems. Despite these advances, current robotic pollination technologies for peppers (chili) face significant bottlenecks characterized by immature methods for precise flower detection and pose estimation, the need for optimized specialized end-effector designs, and insufficient robustness in decision-making systems under dynamic environmental conditions. To address these issues, future development should prioritize constructing diverse, large-scale flower image and pose datasets while developing detection algorithms adaptable to complex environments to achieve high-precision identification. Additionally, implementing this system requires a hierarchical architecture where perception drives adaptive actuation. Deep learning models must localize flower targets and assess maturity in real-time, feeding coordinates to path planners that generate collision-free trajectories through foliage. These trajectories are executed via multimodal motion control, synchronizing the rigid manipulator with soft end-effectors. By embedding tactile feedback into the machine learning loop, the system creates a unified sensorimotor framework. This enables dynamic force modulation based on physical resistance, ensuring precise, non-destructive pollination tailored to chili plants.
Why it matches plant phenotyping methods温室コショウの花の検出・姿勢推定など、植物器官の観測・形質抽出を中核とするロボット受粉技術のレビューであり、方法論的貢献が中心。
abstractThis study systematically reviews recent advancements in the field and distills the core technical issues of greenhouse robotic pollination into three primary domains: target detection and pose estimation, end-effector design, and pollination strategies combined with motion control.
Background: Plant diseases are a major challenge for global food production. They lead to significant reductions in crop yield and quality. Fungi, bacteria, viruses and nematodes are common pathogens that attack plants. These diseases not only affect food security but also cause economic losses worldwide. Estimates show that 20-30% of global crop yields are lost annually due to plant diseases. Early detection is necessary to minimize losses and protect crops. Traditional detection methods rely on field observation and laboratory tests. These techniques are time-consuming, labor-intensive and may not be practical for large-scale monitoring. Modern tools, including imaging technologies and machine learning, are emerging as effective solutions. They offer rapid, accurate detection and classification of plant diseases. Methods: This paper reviews plant disease detection techniques with a focus on classification systems and diagnostic tools. The classification is based on disease incidence, mode of spread, symptoms, host parts affected and causative agents. A literature search was performed using databases such as Scopus, Web of Science and Google Scholar. Keywords included “plant disease detection,” “machine learning,” “AI in agriculture,” and “disease management.” Studies from 2005 to 2024 were considered. Priority was given to research discussing image-based diagnosis, hyperspectral imaging and machine learning models. Relevant articles were analyzed for methods, performance and limitations. Result: Machine learning-based models show strong potential for disease detection. Convolutional neural networks (CNNs) are widely used for image classification tasks. Hyperspectral imaging and sensor-based systems improve accuracy. However, limitations exist. Models struggle with dataset imbalance, varying environmental conditions and real-field application. More diverse datasets and field validation are needed. Explainable AI models are also lacking.
Why it matches plant phenotyping methods植物病害の画像・ハイパースペクトル・センサーによる症状検出と機械学習手法を中心に扱うレビューであり、植物状態（病害）の取得・推定手法が主題。
abstractThis paper reviews plant disease detection techniques with a focus on classification systems and diagnostic tools.
Confronted with the severe imperatives to food security posed by a growing population and the urgent need for sustainable development amid climate change, traditional agricultural models face significant resource-intensive efficiency bottlenecks. Deep learning-based image recognition is driving a future-oriented intelligent agricultural revolution by enabling high-throughput phenotyping and autonomous decision-making across the production chain. This paper systematically reviews key advancements in image recognition within modern agriculture, mapping the fundamental paradigm shift from traditional hand-crafted feature engineering to adaptive deep feature learning. We critically analyze technological implementation and performance across five core application scenarios: high-precision pest and disease diagnosis, spatio-temporal growth monitoring and yield prediction through multi-source image fusion, agricultural robots for automated harvesting, non-destructive quality inspection of products, and intelligent precision management of farmland. The review further identifies critical challenges hindering large-scale technology adoption, primarily centered on the high costs of constructing high-quality agricultural datasets and model robustness in complex field environments. Consequently, this study provides a comprehensive and forward-looking reference for advancing the deep integration of vision technology, thereby offering a strategic path toward achieving more intelligent, efficient, and sustainable global agricultural production systems in the digital era.
Why it matches plant phenotyping methods画像認識による高スループット表現型解析を含む農業画像技術を、実装・性能・課題の観点から体系的にレビューしており、植物フェノタイピング手法のレビューが中心です。
abstractThis paper systematically reviews key advancements in image recognition within modern agriculture
Drone-based phenotyping using unmanned aerial vehicles (UAVs) has emerged as a revolutionary approach for high-throughput, precise, and scalable measurement of plant traits critical to crop improvement. This technology integrates advanced imaging sensors—including RGB, multispectral, hyperspectral, and thermal cameras—with sophisticated image processing and artificial intelligence algorithms to non-destructively capture key phenotypic data such as plant height, biomass, canopy temperature, maturity timing, and disease symptoms under natural field conditions. Compared with traditional manual phenotyping and satellite-based remote sensing, UAV phenotyping offers superior spatial and temporal resolution, enabling dynamic monitoring of complex traits such as drought tolerance and disease resistance. Applications span early stress detection, quantitative trait assessment, yield prediction, and accelerating breeding cycles by facilitating objective, rapid selection of superior genotypes across multiple crop species. Despite its transformative potential, challenges remain in standardizing protocols, managing large-scale complex datasets, integrating phenotypic with genomic and environmental data, and providing training resources for widespread adoption. Ongoing advancements in sensor technology, data analytics, open-source tools, and capacity building are poised to cement drone-based phenotyping as a cornerstone technology for sustainable, climate-resilient crop breeding and global food security.
Why it matches plant phenotyping methodsUAV画像・センサーによる植物形質計測を中心に扱う明示的なフェノタイピングレビューであり、手法の応用、技術、課題を総合的に論じている。
abstractDrone-based phenotyping using unmanned aerial vehicles (UAVs) has emerged as a revolutionary approach for high-throughput, precise, and scalable measurement of plant traits critical to crop improvement.
Understanding plant functional diversity across scales requires integrating field-based ecology and remote sensing, yet these disciplines differ in how traits are studied. We evaluated the conceptual and methodological convergence between these disciplines. Our results reveal that field-based ecology has undergone longer conceptual development and covers a broader range of traits, while remote sensing has experienced rapid growth driven by technological advances. Both disciplines are increasingly converging on similar concepts. However, major gaps in empirical coverage persist across biomes in both disciplines. Although plant-dominated ecosystems have been extensively studied, extreme ecosystems remain undersampled. While there is considerable diversity in the definition “functional traits”, both disciplines converge on using a similar set of traits, reflecting their central role in plant strategies and spectral detectability. Our synthesis underscores the potential for methodological synergy. Harmonizing trait definitions, scaling assumptions, and computational steps involved in estimating plant functional diversity are crucial for building a unified, multiscale framework for biodiversity monitoring in ecosystems undergoing biodiversity loss and climate change. Teaser A synthesis of how field ecology and remote sensing can be aligned to monitor plant functional diversity across scales.
Why it matches plant phenotyping methods植物機能形質・機能多様性をリモートセンシングで推定する方法論の系統的レビューであり、形質定義、スケーリング、計算手順の統合が中心である。
titleBridging the gaps between field-based ecology and remote sensing to estimate plant functional diversity: a systematic review
Plant diseases continue to pose a serious challenge to agriculture, leading to substantial yield losses and posing a threat to global food security. Accurate and early identification of plant diseases is crucial for effective crop management. However, traditional manual inspection methods are time-consuming, subjective, and heavily dependent on expert knowledge. With recent advances in artificial intelligence and computer vision, automated plant disease detection systems have emerged as a reliable alternative. These systems depend strongly on large, well-annotated image datasets for training and evaluation. Among publicly available resources, the PlantVillage dataset is one of the most widely used benchmarks for plant disease research. It contains over 50,000 high-resolution RGB leaf images captured under controlled conditions and covers 14 crop species, including tomato, potato, and bell pepper, along with multiple other plants. The dataset represents 38 distinct classes encompassing both healthy and diseased leaf categories. All images are collected against uniform backgrounds, providing visual consistency and making the dataset suitable for benchmarking machine learning and deep learning–based plant disease classification models. This survey provides a comprehensive review of the PlantVillage dataset and its contribution to the advancement of automated plant disease detection. It traces the progression from traditional handcrafted feature–based classifiers to convolutional neural networks, transfer learning approaches, and recent transformer-based architectures. Various methods are compared in terms of classification accuracy, generalization ability, computational efficiency, and robustness. In the survey we have identified that Transfer Learning model showed 99.75% accuracy. The survey also discusses key limitations of the dataset, particularly its controlled imaging conditions and challenges related to real-field deployment. Finally, future research directions are highlighted, including domain adaptation, explainable artificial intelligence, multi-disease recognition, and real-world agricultural applications. This work aims to offer researchers a structured understanding of the PlantVillage dataset and support the development of next-generation intelligent crop disease diagnostic systems.
Why it matches plant phenotyping methodsPlantVillage画像を用いた植物病害状態の画像ベース推定手法とデータセットを中心に、複数の機械学習手法を比較・レビューしているため、植物フェノタイピング方法論のレビューとして含める。
abstractThis survey provides a comprehensive review of the PlantVillage dataset and its contribution to the advancement of automated plant disease detection.
Plant sensors have witnessed remarkable advancements, enabling precise and real-time monitoring of diverse plant parameters. Plant sensors empowered by artificial intelligence, Internet of Things, and cloud-based analytics are able to monitor and increase the crop yield and productivity. The smart sensors encompass a wide range of functionalities, including but not limited to measuring soil moisture, nutrient levels, environmental conditions, plant health, and physiological responses. This article has given detailed elaboration of literature and patent status on sensors for plant phenotyping, plant biochemistry, plant physiology, and plant health assessment. It has also covered global patent player countries, major International Patent Classification class, and top economy drivers in the key areas. Plant sensors were aligned to achieve sustainable development goals such as 2, 6, 7, 12, and 13. As per our knowledge, this is the first time we are discussing plant sensors focusing on patent landscapes. This study will act as a guide for researchers and economists, helping them navigate the complex field of sensor-enabled plant analysis and promoting sustainable agricultural practices.
Why it matches plant phenotyping methods植物フェノタイピング用センサーに関する文献・特許レビューであり、センサー技術と植物形質・健康状態の測定を主題としているため、方法レビューとして含める。
titleSensors for Phenotyping and Health Assessment in Plants: A Literature and Patent Review
Tomato ( Solanum lycopersicum ) is a globally cultivated horticultural crop, yet its productivity is severely constrained by foliar and insect-vectored diseases that reduce its quality and production. Early and accurate diagnosis of these diseases, along with sustainable biocontrol strategies, is essential for improving crop health and reducing economic losses. This review synthesizes and evaluates the recent progress in lightweight deep learning models and edge AI for tomato disease detection, highlighting their potential for practical deployment in precision agriculture. A comprehensive survey of recent literature was conducted, which covers convolutional neural networks, transformer-based models, optimization techniques including pruning, quantization, and knowledge distillation, and use of explainable AI tools to enhance transparency and trust. In addition, experimental validation was performed by utilizing MobileNetV2 and EfficientNetB0 on a subset of tomato diseases that are most common and prevalent in Tamil Nadu. The test performance of both the models resulted in an overall accuracy of 99.9% and macro-F1 nearly 0.99. Further, a unique framework that combines AI-powered diagnosis with microbial biocontrol recommendations is proposed offering a solution to manage diseases in both eco-friendly and region-specific way. Overall, this work provides a roadmap for combining sustainable methods with AI-driven diagnosis, promoting resilient, scalable, and farmer-friendly agricultural systems.
Why it matches plant phenotyping methodsトマト葉の病害状態を画像から推定する深層学習手法をレビューし、モデル性能も実験検証しているため、植物フェノタイピング手法が中心です。
abstractThis review synthesizes and evaluates the recent progress in lightweight deep learning models and edge AI for tomato disease detection
Global agriculture is facing significant threat from climate-driven abiotic stress, which endangers global food security by impacting crop performance and adaptation. However, traditional abiotic stress detection methods are often labor-intensive and lack precision and scalability. Efficient and reliable solutions are needed to meet rising global food demand. Recent advances in artificial intelligence (AI) offer highly accurate, non-invasive, and sustainable approaches for abiotic stress detection. This paper reviews the impact of AI, and specifically Machine and Deep Learning algorithms, coupled with synergistic technologies and diverse datasets (imaging techniques and Internet of Things (IoT) infrastructures), to identify unique signatures of abiotic stress, and assess its impact on growth and physiological performance. It contrasts with other reviews that address individual technologies and algorithms, while presenting abiotic stress detection as a secondary objective. We examined peer-reviewed journal articles on the use of AI in detecting abiotic stress. The reviewed literature was chosen based on the stress category, sensing mode, and AI technologies employed. A comparative analysis was performed to explore potential advancements of AI-based abiotic stress detection methods over traditional approaches and also challenges lied to the adoption of AI in agriculture for abiotic stress detection.
Why it matches plant phenotyping methods植物の非生物的ストレス状態をAI・画像・IoT等で検出する手法を主題としたレビューであり、植物フェノタイピング手法のレビューに該当する。
abstractThis paper reviews the impact of AI, and specifically Machine and Deep Learning algorithms, coupled with synergistic technologies and diverse datasets (imaging techniques and Internet of Things (IoT) infrastructures), to identify unique signatures of abiotic stress, and assess its impact on growth and physiological performance.
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 5 Sept 2026
3D phenotyping refers to the quantitative characterization of a plant's structural and morphological traits in three-dimensional space, allowing for a detailed analysis of plant architecture and growth patterns. In recent years, rapid advancements in non-destructive, high-throughput 3D imaging technologies have enabled the precise measurement of these traits. Initially focused on single-plant traits under controlled conditions, the field has now expanded towards robust applications in real-world field environments, enabling large-scale analyses of plant canopies and complex structures. This study focuses on the recent advancements in 3D crop phenotyping using point cloud technologies. It compares sensor technology and its application in controlled environments (Chamber-Crop Phenotyping, CCP) and field conditions (Field-Crop Phenotyping, FCP). Technologies such as Multiview stereo (MVS) reconstruction, LiDAR, and laser triangulation have enhanced plant phenomics by enabling high-throughput, non-destructive measurements of key traits such as canopy structure, leaf area, and stem diameter. This review highlights the strengths of the CCP, where environmental variables and flexibility are tightly controlled, facilitating precise trait measurement, and contrasts it with the challenges of the FCP, where unpredictable factors, such as occlusion, wind, light variability, and terrain complexity, complicate data acquisition. Various sensor platforms, including ground-based robotic systems and unmanned aerial vehicles (UAVs), have been discussed regarding their ability to overcome occlusion and limited sensor range in real-world conditions. The need to transition these technologies from laboratory environments to real-world agricultural applications is emphasized, highlighting their potential to improve crop management and plant breeding through accurate phenotypic trait extraction. Finally, current research gaps and future directions for integrating advanced sensor platforms and analytical techniques in both CCP and FCP settings are identified, emphasizing the need to enhance the scalability and robustness of 3D phenotyping for field applications.
Why it matches plant phenotyping methods3D作物フェノタイピングのセンサー技術、点群処理、対象形質、検証上の課題を中心に扱う方法論レビューであり、植物形質の取得手法が明確に中心である。
abstractThis study focuses on the recent advancements in 3D crop phenotyping using point cloud technologies.
The agricultural sector has increasingly recognized the significance of integrating computer vision and machine learning in recent years. Computer vision (CV) technology has transformed farming through the development of autonomous, scalable sensor systems . These technologies, which use remote cameras and advanced CV algorithms, have several uses, from lowering production costs through intelligent automation to improving overall efficiency. In agriculture, one of the most significant challenges is accurately detecting plant leaf diseases, which can significantly affect crop quality and yield. One significant advancement in this area is the You Only Look Once (YOLO) framework, a state-of-the-art object identification method that formulates detection as a single regression problem. YOLO can recognize many disease types in a single image with speed and accuracy. This study presents a thorough analysis of plant disease detection methods based on multiple YOLO versions. It explains and evaluates enhancements made to the original YOLO design, summarizes the findings of earlier studies where constructively looks at performance metrics, and discusses potential directions for future development.
Why it matches plant phenotyping methods植物葉の病害状態を画像から検出するYOLO手法を比較・評価するレビューであり、病害表現型の取得・推定手法が中心である。
abstractThis study presents a thorough analysis of plant disease detection methods based on multiple YOLO versions.
Major crops worldwide are affected by various diseases yearly, leading to crop losses in different regions. The primary methods for addressing crop disease losses include manual inspection and chemical control. However, traditional manual inspection methods are time-consuming, labor-intensive, and require specialized knowledge. The preemptive use of chemicals also poses a risk of soil pollution, which may cause irreversible damage. With the advancement of computer hardware, photographic technology, and artificial intelligence, crop disease recognition methods based on spectral and red-green-blue (RGB) images not only recognize diseases without damaging the crops but also offer high accuracy and speed of recognition, essentially solving the problems associated with manual inspection and chemical control. This paper summarizes the research on disease recognition methods based on spectral and RGB images, with the literature spanning from 2020 through early 2025. Unlike previous surveys, this paper reviews recent advances involving emerging paradigms such as State Space Models (e.g., Mamba) and Generative AI in the context of crop disease recognition. In addition, it introduces public datasets and commonly used evaluation metrics for crop disease identification. Finally, the paper discusses potential issues and solutions encountered during research, including the use of diffusion models for data augmentation. Hopefully, this survey will help readers understand the current methods and effectiveness of crop disease detection, inspiring the development of more effective methods to assist farmers in identifying crop diseases.
Why it matches plant phenotyping methods作物病害をRGB・スペクトル画像から認識する手法を中心に、評価指標や公開データセットを含めて体系的にレビューしており、植物の病害状態を画像から推定するフェノタイピング手法レビューに該当する。
abstractThis paper summarizes the research on disease recognition methods based on spectral and RGB images
Against the backdrop of global food security concerns and the impending threat of phytopathogens, precision plant pathology technology has emerged as a key tool in ensuring the optimisation of agricultural sustainability. The conventional methods adopted in crop disease diagnosis, based on visual examination and laboratory analysis, are found to be lacking in terms of providing timely, geographically precise and scalable solutions. With recent advances in Unmanned Aerial Vehicle (UAV), or drone, technology, there is a paradigm shift in meeting such challenges. This review discusses in depth the synergistic integration of UAVs with multispectral, hyperspectral, thermal, and RGB imaging modalities in conjunction with artificial intelligence (AI) and deep learning approaches for the detection, classification, and quantification of diseases in plants at an early stage. Machine learning algorithms and optical sensors on unmanned aerial vehicles (UAVs) enable real-time high-resolution monitoring of disease signs on large crop fields. Vegetation indices, thermal stress maps, and spectral signatures are used by these systems to detect subtle physiological changes in crops before any visible sign of the disease. Their uses include disease detection, irrigation optimization, nutrient mapping, aerial sowing, yield prediction and precision pesticide application. Deep learning models, particularly CNNs and U-Net architectures, show the high accuracy of disease diagnosis and the estimation of their severity in field scenarios. In addition, UAV-based systems are fully compatible with Geographic Information Systems (GIS), IoTs, and cloud platforms, which facilitate data-driven decisionmaking for crop management. Nevertheless, there are obstacles in the shape of high data acquisition costs, model generalizability, regulatory restrictions, and low dataset diversity. The current article is concerned with recent developments, field-scale case studies, and existing challenges and discusses future directions for drone-based plant disease monitoring. The integration of UAV technologies with AI is highly promising to change the face of plant pathology and render disease monitoring more accurate, proactive, and sustainable.
Why it matches plant phenotyping methodsUAV画像・分光/熱センシングとAIによる植物病徴の検出・重症度推定を中心に扱うレビューであり、植物状態の表現型取得手法が主題である。
abstractThis review discusses in depth the synergistic integration of UAVs with multispectral, hyperspectral, thermal, and RGB imaging modalities in conjunction with artificial intelligence (AI) and deep learning approaches for the detection, classification, and quantification of diseases in plants at an early stage.
AI-driven imaging is becoming central to crop monitoring, with proximal and unmanned aerial vehicle (UAV) platforms now routinely used for disease and stress detection, yield estimation, canopy structure, and fruit counting. Yet, as these models move from plots to farms, the main bottleneck is no longer raw accuracy but robustness under distribution shift. Systems trained in one field, season, cultivar, or sensor often fail when the scene, sensor, protocol, or timing changes in realistic ways. This review synthesizes recent advances on robustness and transferability in proximal and UAV imaging, drawing on a corpus of 42 core studies across field crops, orchards, greenhouse environments, and multi-platform phenotyping. Shift types are organized into four axes, namely scene, sensor, protocol, and time. The article also maps the empirical evidence on when RGB imaging alone is sufficient and when multispectral, hyperspectral, or thermal modalities can potentially improve robustness. This serves as a basis to synthesize acquisition and evaluation practices that often matter more than architectural tweaks, which include phenology-aware flight planning, radiometric standardization, metadata logging, and leave-one-field/season-out splits. Adaptation options are consolidated into a practical symptom/remedy roadmap, ranging from lightweight normalization and small target-set fine-tuning to feature alignment, unsupervised domain adaptation, style translation, and test-time updates. Finally, a benchmark and dataset agenda are outlined with emphasis on object-oriented splits, cross-sensor and cross-scale collections, and longitudinal datasets where the same fields are followed across seasons under different management regimes. The goal is to outline practices and evaluation protocols that support progress toward deployable and auditable systems, noting that such claims require standardized out-of-distribution testing and transparent reporting as emphasized in the benchmark specification and experiment suite proposed here.
Why it matches plant phenotyping methods植物の近接・UAV画像による病害・ストレス・収量・キャノピー構造・果実数の推定について、頑健性、転移性、取得・評価プロトコル、ベンチマークを体系化する方法論レビューであり、フェノタイピング手法が中心です。
abstractThis review synthesizes recent advances on robustness and transferability in proximal and UAV imaging, drawing on a corpus of 42 core studies across field crops, orchards, greenhouse environments, and multi-platform phenotyping.
Recent developments in machine learning (ML) and deep learning (DL) algorithms have introduced a new approach to the automatic detection of plant diseases. However, existing reviews of this field tend to be broader than maize-focused and do not offer a comprehensive synthesis of how ML and DL methods have been applied to image-based detection of maize leaf disease. Following the PRISMA guidelines, this systematic review of 102 peer-reviewed papers published between 2017 and 2025 examined methods and approaches used to classify leaf images for detecting disease in maize plants. The 102 papers were categorized by disease type, dataset, task, learning approach, architecture, and metrics used to evaluate performance. The analysis results indicate that traditional ML methods, when combined with effective feature engineering, can achieve classification accuracies of approximately 79–100%, while DL, especially CNNs, provide consistent, superior classification performance on controlled benchmark datasets (up to 99.9%). Yet in “real field” conditions, many of these improvements typically decrease or disappear due to dataset bias, environmental factors, and limited evaluation. The review provides a comprehensive overview of emerging trends, performance trade-offs, and ongoing gaps in developing field-ready, explainable, reliable, and scalable maize leaf disease detection systems.
Why it matches plant phenotyping methodsトウモロコシ葉の病害を画像から分類・検出する機械学習手法を体系的にレビューしており、植物の病害状態を推定するフェノタイピング手法が中心である。
abstractThe review provides a comprehensive overview of emerging trends, performance trade-offs, and ongoing gaps in developing field-ready, explainable, reliable, and scalable maize leaf disease detection systems.
Nitrogen (N) is an essential macronutrient that plays a central role in photosynthesis, metabolism, and crop productivity. Accurate and non-destructive evaluation of plant N status is essential for improving N use efficiency and sustainable fertilization. Bioimpedance spectroscopy (BIS) has emerged as a promising tool for in vivo assessment of plant physiological state; however, its application to nutrient monitoring remains limited. Previous studies show that N deficiency significantly alters extracellular and intracellular fluid resistances and reduces cell membrane capacitance, reflecting impaired ion conductivity, loss of membrane integrity, and changes in vacuole storage. These alterations can be detected in vivo within specific frequency ranges and often correlate with leaf N content, but most studies considered only total N and did not account for inorganic nitrate (NO 3 ⁻) forms or water-related effects. Future research should combine BIS with direct apoplastic NO 3 ⁻ measurements and factorial N and water experiments to distinguish nutrient-specific responses from drought-induced changes. Applying advanced equivalent circuit models, such as the Double-Shell (DBS) model, could strengthen physiological interpretation and associate impedance parameters with cellular functions. Addressing these issues will enable BIS to become a reliable, non-destructive diagnostic method for N monitoring.
Why it matches plant phenotyping methods植物の窒素状態を非破壊的に測定するバイオインピーダンス分光法を中心に、既存知見と今後の診断手法をレビューしており、植物フェノタイピング手法が中核です。
titleAdvancing nitrogen diagnostics in plants through bioimpedance spectroscopy: current evidence and future perspectives-a review.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · OpenAlex · checked 15 Sept 2026
Hyperspectral imaging (HSI) has emerged as a powerful tool for precision agriculture, enabling the non-destructive monitoring of crop biochemical and physiological traits. However, HSI alone lacks structural context, which limits its ability to accurately capture complex canopy architectures and organ-level traits. Integrating HSI with depth-sensing modalities such as Light Detection and Ranging (LiDAR), Red, Green, Blue, and Depth (RGB-D) cameras, and computational reconstruction technique such as photogrammetry enables the generation of three-dimensional hyperspectral point clouds, combining spectral richness with geometric fidelity. This multi-modal fusion enhances crop trait estimation, including biomass, leaf chlorophyll content, canopy height, leaf area, and stress indicators, while improving the robustness of phenotyping under occlusions, shadows, and varying illumination. Dimensionality reduction, feature selection, and machine learning approaches, including deep learning and explainable AI, are useful for handling high-dimensional hyperspectral data and extracting actionable agronomic insights. Moreover, the integration of thermal, radar, and Global Navigation Satellite System (GNSS) data further expands the capabilities of multi-modal sensing, enabling continuous, all-weather crop monitoring and accurate spatial referencing. Despite these advances, most studies to date focus on controlled environments, highlighting the need for field-based validation to ensure the reliability and scalability of HSI-depth fusion techniques. This review consolidates current knowledge on multi-modal hyperspectral and 3D crop reconstruction, highlighting methods, applications, and challenges, and outlines future directions for implementing high-throughput, real-time phenotyping and precision agriculture solutions.
Why it matches plant phenotyping methods植物形質推定のためのハイパースペクトル・深度センシング融合と3D再構成を中心に扱うレビューであり、フェノタイピング手法の方法論的整理が主題。
abstractThis review consolidates current knowledge on multi-modal hyperspectral and 3D crop reconstruction, highlighting methods, applications, and challenges
Deep learning has achieved promising performance for fruit and vegetable image analysis, by possessing strong representation power, and providing resilient generalization and broad transferability on large-scale data for classification, detection, and segmentation tasks, which is indispensable role in optimizing agricultural practices. This comprehensive survey reviews over 270 recent studies, offering a deep exploration of the key techniques and strategies, fundamental properties, and advancements and future directions according to different categories of deep learning methods for fruit and vegetable image analysis. Furthermore, this paper outlines the novelty and concept of fruit and vegetable image analysis, summarizes publicly available datasets, evaluation metrics, and discusses successful applications in disease detection, quality grading, yield estimation, localization, and multiple application integration. The survey emphasizes the need for processing large-scale datasets and exploring the potential of efficient deep learning for enhancing real-time applications and specific tasks. By comprehensively comparing and analyzing the fundamental attributes of the fruit and vegetable image analysis methods from a fresh perspective, this survey reveals the commonalities and disparities of divert techniques and guides researchers and practitioners toward developing more efficient and accurate solutions.
Why it matches plant phenotyping methods果実・野菜画像解析の深層学習手法を包括的にレビューし、疾患検出や収量推定など植物の状態・形質推定、データセット、評価指標を扱うため、フェノタイピング手法レビューとして中心的です。
abstractThis comprehensive survey reviews over 270 recent studies
Hyperspectral imaging (HSI) has emerged as a powerful tool for precision agriculture, enabling the non-destructive monitoring of crop biochemical and physiological traits. However, HSI alone lacks structural context, which limits its ability to accurately capture complex canopy architectures and organ-level traits. Integrating HSI with depth-sensing modalities such as Light Detection and Ranging (LiDAR), Red, Green, Blue, and Depth (RGB-D) cameras, and computational reconstruction technique such as photogrammetry enables the generation of three-dimensional hyperspectral point clouds, combining spectral richness with geometric fidelity. This multi-modal fusion enhances crop trait estimation, including biomass, leaf chlorophyll content, canopy height, leaf area, and stress indicators, while improving the robustness of phenotyping under occlusions, shadows, and varying illumination. Dimensionality reduction, feature selection, and machine learning approaches, including deep learning and explainable AI, are useful for handling high-dimensional hyperspectral data and extracting actionable agronomic insights. Moreover, the integration of thermal, radar, and Global Navigation Satellite System (GNSS) data further expands the capabilities of multi-modal sensing, enabling continuous, all-weather crop monitoring and accurate spatial referencing. Despite these advances, most studies to date focus on controlled environments, highlighting the need for field-based validation to ensure the reliability and scalability of HSI-depth fusion techniques. This review consolidates current knowledge on multi-modal hyperspectral and 3D crop reconstruction, highlighting methods, applications, and challenges, and outlines future directions for implementing high-throughput, real-time phenotyping and precision agriculture solutions.
Why it matches plant phenotyping methods植物形質推定のためのハイパースペクトル・深度センシング・3D再構成手法を中心に扱うレビューであり、フェノタイピング手法レビューに該当する。
abstractThis review consolidates current knowledge on multi-modal hyperspectral and 3D crop reconstruction, highlighting methods, applications, and challenges
The study of annual growth rings in Vitis vinifera has recently emerged as a promising framework to explore long-term vine responses to climate and management. This review synthesizes current knowledge on grapevine wood anatomy, xylem functionality, and isotopic signatures, highlighting their role as archives of environmental and agronomic information. Grapevine growth rings provide high-resolution records of climate signals, including drought and heat stress, and reveal cultivar-specific hydraulic strategies shaped by soil conditions and management practices. Stable isotope analyses further complement anatomical chronologies by integrating physiological responses to water availability. Together, these approaches offer valuable insights into the structural memory and plasticity of grapevine xylem, with direct implications for vineyard sustainability and climate adaptation. We also examine the impact of viticultural practices such as irrigation, pruning, grafting, and rootstock choice on xylem architecture, emphasizing how agronomic decisions leave long-lasting anatomical imprints in wood. Finally, we outline future research perspectives, including the integration of dendrochronological, isotopic, and high-resolution imaging techniques, to fully exploit grapevine chronologies as tools for understanding vine resilience and for guiding varietal selection, breeding, and precision viticulture under changing environmental conditions.
Why it matches plant phenotyping methodsブドウの年輪解剖、安定同位体、画像解析を用いて環境応答や木部機能などの植物形質・状態を評価する方法群をレビューしており、測定・解析手法が中心的である。
abstractGrapevine growth rings provide high-resolution records of climate signals, including drought and heat stress, and reveal cultivar-specific hydraulic strategies shaped by soil conditions and management practices.
Crop yield prediction (CYP) along with crop growth parameter estimation (CGPE) recently gained prominence as essential means for optimizing agricultural resource use and addressing global food security challenges, particularly in regions with vulnerable climates and diverse agricultural systems, such as the Mediterranean one. Artificial intelligence (AI) and remote sensing (RS) play an important role in achieving such objectives. To identify present methodologies and frameworks, emerging trends, research gaps and future directions in the integrated use of AI and RS in the Mediterranean area for CYP and CGPE. We systematically reviewed the published scientific literature on the topic (106 studies) by means of the PRISMA methodology. We found that integration of AI, particularly machine learning methods such as Random Forest, Support Vector Machine, and Artificial Neural Networks, along with satellite-based RS platforms such as Sentinel-2, Sentinel-1, MODIS, and Landsat-8, demonstrated strong potential to enhance monitoring and support adaptive agricultural decision-making. Deep learning models, such as Convolutional Neural Networks and Long Short Term Memories, are emerging tools for spatio-temporal modelling, although their use is limited, likely due to data and computational constraints. Wheat is the most frequently analyzed crop, alongside high-value perennial crops like olives and vineyards. Data acquisition relies predominantly on satellite imagery, though hybrid approaches incorporating unmanned aerial vehicle and ground-based data are promising in improving prediction accuracy. Despite these advancements, significant challenges persist, including uneven geographical research coverage, limited model transferability, and insufficient consideration of crop phenology. A critical lack of standardized validation datasets and the underrepresentation of North African and Middle Eastern countries further constrain progress. To fully harness AI-RS integration for sustainable agriculture and food security in the Mediterranean area, and similar agroecosystems, future efforts should aim at i) prioritizing cross-regional collaboration, ii) focusing on hybrid AI-RS methods, iii) developing phenology-aware models, and iv) widening access to data.
Why it matches plant phenotyping methodsAI・リモートセンシングによる作物生育パラメータ推定を中心に、手法群・データ取得・検証課題を体系的にレビューしており、植物形質推定手法の方法論的レビューに該当する。
titleIntegration of artificial intelligence and remote sensing for crop yield prediction and crop growth parameter estimation in Mediterranean agroecosystems: Methodologies, emerging technologies, research gaps, and future directions
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 7 Sept 2026
MRI / PETX-ray / CTRootMorphology / geometry measurementRoot system architectureStress response / toleranceWater status / transpiration
Strategic optimisation of Root System Architecture (RSA) represents a critical frontier for stabilising crop productivity amid increasingly unpredictable moisture-deficit regimes. Understanding key root traits underlying effective drought response is necessary to harness the genetic diversity associated with root growth patterns and environmental adaptations. Many functionally significant root architectural traits have been reported, and the mechanistic importance of some of the anatomical ideotypes, such as the increased metaxylem vessel diameter to reduce axial hydraulic resistance to maintain leaf water potential and change in root growth angle to promote geotropic deep-soil moisture foraging, are discussed in this review. Despite the identification of these characteristics, the knowledge gap in their integration into predictive breeding frameworks remains. This review addresses this fragmentation by critically evaluating how the bottleneck of the ‘phenotyping’ process is being broken down through non-invasive high-throughput phenotyping modalities. Dynamic root-soil interfaces can be spatio-temporally quantified in situ using non-destructive technologies such as X-ray computed tomography and MRI, which can detect developmental plasticity masked by destructive sampling. Artificial Intelligence (AI), especially Convolutional Neural Networks, enables automated extraction of high-dimensional topological parameters from complex digital rhizograms. Present review integrates recent advances in phenotyping with molecular regulatory mechanisms, bridging two traditionally disparate fields. By focusing on the DRO1/qSOR1 loci and ABA-auxin crosstalk, we establish critical connections between molecular regulation and field-scale architectural performance. The resulting multi-scale roadmap may help in targeted selection of climate-resilient cultivars to maximize resource use efficiency.
Why it matches plant phenotyping methods根系構造の非破壊・ハイスループット表現型解析技術を中心に、X線CT、MRI、AIによる根系形質抽出をレビューしており、植物フェノタイピング手法が中核です。
abstractThis review addresses this fragmentation by critically evaluating how the bottleneck of the ‘phenotyping’ process is being broken down through non-invasive high-throughput phenotyping modalities.
Multimodal approaches for crop disease detection have gained significant attention due to their ability to integrate diverse data sources for improved accuracy. This review categorizes recent studies into five areas: multimodal deep learning and vision transformers, hyperspectral and remote sensing, thermal imaging and UAV applications, CNN–Transformer hybrids and ensemble methods, and comprehensive reviews. Results indicate that frameworks combining RGB, hyperspectral, and thermal imaging achieve accuracies up to 97.8%, while hybrid CNN–Transformer architectures reach 99.7% on benchmark datasets. Despite these advances, challenges remain in scalability, computational cost, and real-world deployment, highlighting the need for lightweight, explainable, and field-validated models.
Why it matches plant phenotyping methods植物病害を画像・リモートセンシングから推定する方法を体系的にレビューしており、病害状態という植物表現型の取得・推定が中心です。
abstractMultimodal approaches for crop disease detection have gained significant attention due to their ability to integrate diverse data sources for improved accuracy.
Crop production is often affected by the co-occurrence of heat and drought, which significantly impacts physiology, growth, development, and yield. Leaf wilting is a phenotype that can provide important insights into how plants respond to combined stressors, linking visible morphological changes to internal physiological changes and water transport. This review emphasizes the importance of leaf wilting as a visual indicator of stress under water-limited conditions. It discusses (i) the water transport processes within plants, (ii) canopy responses to heat and drought stress such as paraheliotropism, leaf rolling, and leaf wilting, (iii) wilting dynamics in plants, in response to heat and drought stress, and (iv) highlights the importance, opportunities, and challenges of emerging technologies, i.e., the potential of unmanned aerial vehicles and machine learning, to enable efficient and large-scale high-throughput phenotyping of heat and drought stress-induced leaf wilting in crop production. A deeper understanding of leaf wilting mechanisms under water-limited conditions is essential for optimizing the use of advanced technologies for crop stress monitoring, thereby improving crop resilience and global food security.
Why it matches plant phenotyping methods葉の萎れという植物形質を対象に、UAVや機械学習による大規模ハイスループット表現型計測の可能性と課題をレビューしており、フェノタイピング手法が中心的に扱われている。
abstractThis review emphasizes the importance of leaf wilting as a visual indicator of stress under water-limited conditions.
With rapid advancements in breeding technologies, phenomics, and artificial intelligence, crop breeding is progressively entering an era of greater precision and efficiency. In this context, three-dimensional (3D) phenotyping techniques-leveraging multidimensional spatial resolution capabilities-have overcome the limitations of two-dimensional (2D) phenotyping in breeding analyses, enabling precise characterization of crop spatial interactions, spatial distribution of plant architecture, and complex 3D structural traits. Recent breakthroughs in computer technology for 3D reconstruction and 3D segmentation have provided robust technical support for crop 3D phenotypic analysis. Furthermore, effective integration of extracted 3D phenotypic data with genotypic data serves as a powerful tool for future research on crop gene function and genomics-assisted breeding. This review systematically examines major advances in 3D phenotyping techniques and their representative applications, with particular emphasis on innovations in 3D phenotyping and analytical methodologies. In parallel, we describe the latest interdisciplinary advances in 3D phenotyping within crop functional genomics research and genomics-assisted breeding. We objectively evaluate the advantages and limitations of 3D phenotyping compared with 2D approaches to assist breeders in selecting appropriate technologies. Finally, we propose future perspectives to promote deeper integration of phenomics and breeding technologies. Despite existing conceptual and technical challenges, it is foreseeable that cross-disciplinary integration of phenomics and genomics will offer promising prospects for crop breeding.
Why it matches plant phenotyping methods3D植物フェノタイピング技術と解析手法の進展を体系的にレビューしており、植物形態・構造形質の取得方法が中心である。
abstractThis review systematically examines major advances in 3D phenotyping techniques and their representative applications, with particular emphasis on innovations in 3D phenotyping and analytical methodologies.
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 5 Sept 2026
With the development of artificial intelligence (AI) in complicated imaging and remote sensing technologies, plant research is transitioning from manual measurements to automated data collecting. High-throughput image-based phenotyping enables the precise and automated acquisition of traits across various spatial and temporal scales, ranging from controlled laboratory settings to intricate field. Furthermore, AI facilitates the combination of satellite observations, unmanned aerial vehicle (UAV) imaging, soil and climate data, and spatiotemporal information to enhance the precision of trait monitoring and yield prediction. These advances enhance the ability to evaluate and predict crop performance under variable environmental conditions. This paper offers a cross-disciplinary paradigm for accurate and sustainable modern agriculture by merging AI methodologies with plant phenotyping and yield forecasting.
Why it matches plant phenotyping methods画像ベース・リモートセンシングによる植物形質取得とAI解析を中心に扱う方法論的レビューであり、植物フェノタイピング手法が中心的である。
abstractThis paper offers a cross-disciplinary paradigm for accurate and sustainable modern agriculture by merging AI methodologies with plant phenotyping and yield forecasting.
Abstract Sucrose is the central unit of carbon and energy in plants. As the product of photosynthesis, it is transported from source–to–sink tissues across both short and long distances. Subcellular sucrose concentrations strongly influence rates of transport within cells, tissues, and organs. Moreover, as a central metabolite, its concentration influences the rates of many enzymatic reactions. Measuring sucrose concentration with subcellular resolution remains challenging, especially for the cytosol, which hosts many critical enzymatic reactions and, in many cells, occupies only a thin layer between the vacuole and the plasma membrane. Here, we review the methods that have been utilized to measure subcellular sucrose concentrations in plant cells. The approaches covered include microautoradiography, non-aqueous fractionation, Fourier transform infrared (FTIR) microspectroscopy, Raman microspectroscopy, mass spectrometry imaging, Förster resonance energy transfer (FRET) nanosensors, direct sampling, and theoretical modelling. We provide perspectives on the use cases for these methods and discuss developments towards resolving subcellular sugar concentrations in live tissues.
Why it matches plant phenotyping methods植物組織内の細胞内ショ糖濃度という生理形質を測定する手法群をレビューし、各手法の利用場面と発展を論じているため、植物フェノタイピング手法レビューに該当する。
abstractHere, we review the methods that have been utilized to measure subcellular sucrose concentrations in plant cells.
Genebanks serve as critical repositories for preserving the genetic diversity of plant species, including crops, forages, and their wild relatives, which is essential for adapting to climate change, enhancing food security, and improving agricultural sustainability. Seed phenotyping, the process of evaluating observable seed traits influenced by genetics and environmental factors, plays a pivotal role in characterizing and utilizing this diversity. Traditional phenotyping methods, however, are labor-intensive and inadequate for the vast collections housed in genebanks. This paper explores the transformative potential of high-throughput phenomics technologies, leveraging the electromagnetic spectrum—from gamma rays to radio waves—to enable rapid, precise, and non-invasive assessment of seed traits such as size, shape, biochemical composition, and vigor. We highlight the integration of advanced imaging systems (e.g., hyperspectral, X-ray, and thermal imaging) to enrich genebank datasets, facilitating trait discovery and crop improvement. Despite challenges like cost, scalability, and data standardization, opportunities arise from collaborative initiatives between genebanks and phenomics facilities through organizations such as International Plant Phenotyping Network. Our conclusions underscore how phenomics can revolutionize genebank operations, ensuring the efficient conservation and deployment of genetic resources to address global agricultural demands.
Why it matches plant phenotyping methods種子形質の高スループット取得に用いるセンサー・イメージング技術を中心に整理したフェノタイピングレビューであり、方法論的役割が明確です。
abstractThis paper explores the transformative potential of high-throughput phenomics technologies, leveraging the electromagnetic spectrum—from gamma rays to radio waves—to enable rapid, precise, and non-invasive assessment of seed traits such as size, shape, biochemical composition, and vigor.
Genebanks serve as critical repositories for preserving the genetic diversity of plant species, including crops, forages, and their wild relatives, which is essential for adapting to climate change, enhancing food security, and improving agricultural sustainability. Seed phenotyping, the process of evaluating observable seed traits influenced by genetics and environmental factors, plays a pivotal role in characterizing and utilizing this diversity. Traditional phenotyping methods, however, are labor-intensive and inadequate for the vast collections housed in genebanks. This paper explores the transformative potential of high-throughput phenomics technologies, leveraging the electromagnetic spectrum—from gamma rays to radio waves—to enable rapid, precise, and non-invasive assessment of seed traits such as size, shape, biochemical composition, and vigor. We highlight the integration of advanced imaging systems (e.g., hyperspectral, X-ray, and thermal imaging) to enrich genebank datasets, facilitating trait discovery and crop improvement. Despite challenges like cost, scalability, and data standardization, opportunities arise from collaborative initiatives between genebanks and phenomics facilities through organizations such as International Plant Phenotyping Network. Our conclusions underscore how phenomics can revolutionize genebank operations, ensuring the efficient conservation and deployment of genetic resources to address global agricultural demands.
Why it matches plant phenotyping methods種子形質を対象とする高スループット画像・センサー型フェノタイピング技術を中心に扱うレビューであり、方法論的役割が明確。
abstractThis paper explores the transformative potential of high-throughput phenomics technologies, leveraging the electromagnetic spectrum—from gamma rays to radio waves—to enable rapid, precise, and non-invasive assessment of seed traits such as size, shape, biochemical composition, and vigor.
Adlay ( Coix lacryma-jobi L.) stands out as a vital health-promoting cereal due to its dual nutritional and medicinal properties; however, it remains significantly underdeveloped compared to major crops. The lack of mechanistic understanding of its caryopsis development and trait formation severely constrains targeted genetic improvement. While transformative technologies, specifically micro-computed tomography (micro-CT) imaging combined with AI-assisted analysis (e.g., Segment Anything Model (SAM)) and multi-omics approaches, have been successfully applied to unravel the structural and physiological complexities of model cereals, their systematic adoption in adlay research remains fragmented. Going beyond a traditional synthesis of these methodologies, this article proposes a novel, multidimensional framework specifically designed for adlay. This forward-looking strategy integrates high-resolution 3D phenotyping with spatial multi-omics data to bridge the gap between macroscopic caryopsis architecture and microscopic metabolic accumulation. By offering a precise digital solution to elucidate adlay's unique developmental mechanisms, the proposed framework aims to accelerate precision breeding and advance the scientific modernization of this promising underutilized crop.
Why it matches plant phenotyping methods穀粒の3DフェノタイピングとAI画像解析を中核に据えた、方法論的な枠組みを提案するレビュー／展望論文である。
abstractThis forward-looking strategy integrates high-resolution 3D phenotyping with spatial multi-omics data
Accurate estimation of tree biomass and volume is essential for sustainable forest management, climate change mitigation, and ecosystem service assessment. Recent advances in unmanned aerial vehicle (UAV) technology enable the acquisition of ultra-high-resolution optical and three-dimensional data, providing a resource-efficient alternative to traditional field-based inventories. This review synthesizes 181 peer-reviewed studies on UAV-based estimation of tree biomass and volume across forestry, agricultural, and urban ecosystems, integrating bibliometric analysis with qualitative literature review. The results reveal a clear methodological shift from early structure-from-motion photogrammetry toward integrated frameworks combining three-dimensional canopy metrics, multispectral or LiDAR data, and machine learning or deep learning models. Across applications, tree height, crown geometry, and canopy volume consistently emerge as the most robust predictors of biomass and volume, enabling accurate individual-tree and plot-level estimates while substantially reducing field effort and ecological disturbance. UAV-based approaches demonstrate particularly strong performance in orchards, plantation forests, and urban environments, and increasing applicability in complex systems such as mangroves and mixed forests. Despite significant progress, key challenges remain, including limited methodological standardization, insufficient uncertainty quantification, scaling constraints beyond local extents, and the underrepresentation of biodiversity-rich and structurally complex ecosystems. Addressing these gaps is critical for the operational integration of UAV-derived biomass and volume estimates into sustainable land management, carbon accounting, and climate-resilient monitoring frameworks.
Why it matches plant phenotyping methodsUAV画像・3Dデータによる樹木のバイオマス、体積、樹高、樹冠形状などの植物形質推定手法を181研究から体系的にレビューしており、フェノタイピング手法が中心です。
abstractThis review synthesizes 181 peer-reviewed studies on UAV-based estimation of tree biomass and volume across forestry, agricultural, and urban ecosystems, integrating bibliometric analysis with qualitative literature review.
Abstract Reliable forest biomass assessments are becoming increasingly important, as Parties to the Climate Convention are required to report changes in multiple carbon pools, including both above- and belowground biomass. In some regions, use of remote sensing is the only viable option for obtaining such estimates, whereas in other regions it bears potential to improve the accuracy of ground inventory-based biomass estimates. However, statistically rigorous estimation through remote sensing poses several challenges. This study systematically and comprehensively reviews the methodological quality of large-area biomass assessment studies from 1992 to 2022, based on core survey elements for successful biomass surveying assisted by remote sensing. For each element, we reviewed the studies in relation to “ideal standards” derived from the literature, which served as evaluation criteria. Our review revealed an increasing trend in use of remote sensing for biomass surveys, coupled with gradual improvements in methodological quality for all survey elements evaluated. For example, advances in remote sensing techniques, particularly the increased use of Light Detection and Ranging, Radio Detection and Ranging, and digital aerial photogrammetry, all technologies able to capture information on forest structure, have enhanced the reliability of biomass estimates. However, several problems remain, such as field data scarcity for model calibration, signal saturation in high-biomass regions, and misconceptions about the use of statistical methods. We identified five remaining key challenges for improving remote sensing assisted large-area biomass assessments. These include (i) obtaining sensor data that correlate stronger with biomass, (ii) acquiring larger sets of harmonized field data at the level of trees and plots for calibrating models, (iii) adequate use of statistical principles, (iv) developing methods for domain estimation, and (v) improved quality assurance and quality control. While upcoming new airborne technologies and satellite missions may mitigate some challenges, continued methodological innovation and further enhancement of the rigor of statistical and other procedures will remain essential for advancing remote sensing-based biomass assessments.
Why it matches plant phenotyping methods森林の植物バイオマスという明示的な形質を対象に、リモートセンシングによる推定手法の方法論的品質、校正、統計、精度向上を体系的に評価しており、単なるバイオマス測定の報告ではない。
abstractThis study systematically and comprehensively reviews the methodological quality of large-area biomass assessment studies from 1992 to 2022, based on core survey elements for successful biomass surveying assisted by remote sensing.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 5 Sept 2026
Low-temperature stress compromises the integrity of plant cell membranes, leading to lipid phase transitions and increased membrane permeability, which subsequently induce physiological damage. However, conventional methods for assessing cold resistance, such as relative electrolyte leakage measurement, growth recovery tests, and LT50 determination, are limited by their highly destructive nature, time-consuming procedures, or insufficient sensitivity. Electrical impedance spectroscopy (EIS), a non-destructive and efficient electrophysiological technique, has emerged as a valuable tool for evaluating cold resistance and screening cold-tolerant plant varieties. By applying multi-frequency alternating current to plant tissues and measuring the resulting impedance responses, EIS enables the extraction of key parameters such as extracellular resistance, intracellular resistance, and cell membrane capacitance. These parameters collectively reflect the structural integrity and physiological condition of cells from multiple perspectives. Notably, under low-temperature stress, plant genotypes with varying degrees of cold resistance exhibit distinct impedance spectral characteristics, allowing EIS to efficiently discriminate cold tolerance among different varieties or treatments. This review summarizes recent advances in EIS-based research on plant cold resistance, covering its underlying electrical principles, equivalent circuit models, and biophysical mechanisms. It also outlines practical applications, including the screening of cold-tolerant woody and herbaceous plants, as well as integration with traditional assessment methods, while highlighting the advantages of EIS in terms of accuracy, universality, and real-time monitoring. Furthermore, the review addresses key challenges such as species specificity, model standardization, and data analysis, and proposes future research directions, including integration with artificial intelligence, development of portable devices, and establishment of standardized stress resistance databases.
Why it matches plant phenotyping methods植物の低温耐性をEISで非破壊評価・識別する方法を中心に、原理、モデル、検証課題、実用化をレビューしており、植物フェノタイピング手法のレビューに該当する。
abstractElectrical impedance spectroscopy (EIS), a non-destructive and efficient electrophysiological technique, has emerged as a valuable tool for evaluating cold resistance and screening cold-tolerant plant varieties.
Plant diseases significantly affect global agricultural productivity and food security. Conventional disease detection techniques rely heavily on manual inspection, which is labor-intensive, time-consuming, and prone to subjectivity. The emergence of the Internet of Things (IoT) has enabled real-time monitoring of plant health and automated disease detection using interconnected sensors, imaging devices, and intelligent data processing frameworks. This paper presents a systematic review of current IoT techniques used in plant disease detection, focusing on sensor technologies, communication protocols, data processing platforms, and machine learning integration. A structured review methodology is adopted to analyze recent literature, and comparative tables are provided to highlight the strengths and limitations of existing systems. The study demonstrates that integrating IoT with artificial intelligence significantly improves detection accuracy, response time, and sustainability in precision agriculture.
Why it matches plant phenotyping methods植物病害検出に用いるIoTセンサー、画像、データ処理、機械学習を体系的にレビューしており、植物の病害状態を観測・推定するフェノタイピング手法が中心です。
abstractThis paper presents a systematic review of current IoT techniques used in plant disease detection, focusing on sensor technologies, communication protocols, data processing platforms, and machine learning integration.
• Very-high-resolution UAVs dominate row/plant analyses; Sentinel-2 underpins regional monitoring. • Multi-sensor fusion (UAV/satellite) and 3D bring robustness to vine identification. • Deep Learning enables detection of plots and accurate row delineation in complex terrains. • Deep Learning models requires vast annotated data and high computational cost limits routine use. • Validation and model portability remain the weakest methodological areas. Sustainable vineyard management and planning require reliable methods for identification and monitoring. This systematic review synthesises and appraises the literature on automatic vineyard identification using remote sensing (RS), from classical techniques to artificial intelligence (AI), describing the state of the art, patterns, challenges, and gaps. Guided by PRISMA and informed by selected SWiM reporting items, we conducted a systematic search across multiple databases, gathering all relevant records up to 13 July 2025, and included 108 sources, of which 80 empirical studies contributed to the synthesis. The risk of bias was assessed by adapting the principles of PROBAST-AI and QUADAS-2 to the agricultural context, covering data representativeness, sensors/pre-processing, ground-truth, validation, and portability; its application also guided the selection and organisation of the synthesis. The analysis was narrative and structured by scale and application objective (regional, parcel, row, and plant). The most common tasks were classification (28%), detection (26%), and segmentation (24%), with multitask pipelines being frequent. We observe a clear transition from pixel-based approaches using satellite imagery to methodologies that integrate very-high - resolution UAV imagery, 3D reconstruction, and Deep Learning (DL). UAVs dominate row and plant-level analyses, whereas Sentinel-2 has become the main tool for multitemporal regional monitoring. DL models, such as CNNs and Vision Transformers (ViTs), tend to deliver superior performance in canopy segmentation and parcel classification. The assessment identified model validation as the weakest methodological domain across studies. The main limitations lie in weak spatiotemporal portability of models and high computational costs, aggravated by reliance on large volumes of annotated data. Promising directions include multisensory fusion (UAV + satellite) and the integration of 3D information into DL pipelines, which increase robustness and operational applicability. These advances are enabling high-value, specialised objectives such as mapping in complex terrain, detecting abandoned vineyards, and identifying missing plants.
Why it matches plant phenotyping methodsブドウ園・列・植物レベルの自動識別とモニタリングに用いるリモートセンシング手法を体系的にレビューし、センサー、3D再構成、深層学習、検証性、可搬性を評価しており、植物状態・構造の取得手法が中心である。
abstractThis systematic review synthesises and appraises the literature on automatic vineyard identification using remote sensing (RS), from classical techniques to artificial intelligence (AI), describing the state of the art, patterns, challenges, and gaps.
Abscisic acid (ABA) is a key phytohormone that regulates plant responses to abiotic stresses such as drought, salinity, and cold, serving as an important biomarker for plant health. Traditional ABA detection methods, primarily chromatographic and immunoassay-based, are invasive, labor-intensive, and unsuitable for continuous monitoring in natural growth conditions. Wearable sensors offer a promising solution for in situ, non-destructive, and real-time monitoring of plant stress responses. This manuscript highlights the advantages of electrochemical sensing platforms over physical and electrophysiological modalities for direct hormone detection. Moreover, this manuscript discusses material considerations, including biocompatibility, molecular specificity, mechanical flexibility, and environmental resilience, which are critical for reliable field deployment. Recent advances in molecularly imprinted polymers, hydrogel-based interfaces, and nanomaterial composites such as graphene and carbon nanotubes are evaluated for their potential to enhance sensitivity and selectivity. Challenges, including sensor stability, interference from complex plant matrices, and integration with low-power electronics, are also addressed. Continuous, real-time data from wearable sensors provides a dynamic view of plant stress, surpassing conventional snapshot measurements. Furthermore, advances in flexible electronics and miniaturization enable seamless integration with plant tissues without causing damage. Finally, this manuscript focuses on future research directions on hybrid sensor design, wireless communication, and AI-driven analytics to enable high-resolution monitoring of plant stress (ABA). Wearable electrochemical sensors thus hold transformative potential for precision agriculture, supporting proactive crop management and sustainable farming practices.
Why it matches plant phenotyping methods植物のABA濃度とストレス状態をリアルタイムに測定するウェアラブル電気化学センサーを中心に、材料、性能、課題、統合をレビューしており、植物フェノタイピング手法が中核です。
abstractWearable sensors offer a promising solution for in situ, non-destructive, and real-time monitoring of plant stress responses.
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 5 Sept 2026
Genebanks serve as critical repositories for preserving the genetic diversity of plant species, including crops, forages, and their wild relatives, which is essential for adapting to climate change, enhancing food security, and improving agricultural sustainability. Seed phenotyping, the process of evaluating observable seed traits influenced by genetics and environmental factors, plays a pivotal role in characterizing and utilizing this diversity. Traditional phenotyping methods, however, are labor-intensive and inadequate for the vast collections housed in genebanks. This paper explores the transformative potential of high-throughput phenomics technologies, leveraging the electromagnetic spectrum-from gamma rays to radio waves-to enable rapid, precise, and non-invasive assessment of seed traits such as size, shape, biochemical composition, and vigor. We highlight the integration of advanced imaging systems (e.g., hyperspectral, X-ray, and thermal imaging) to enrich genebank datasets, facilitating trait discovery and crop improvement. Despite challenges like cost, scalability, and data standardization, opportunities arise from collaborative initiatives between genebanks and phenomics facilities through organizations such as International Plant Phenotyping Network. Our conclusions underscore how phenomics can revolutionize genebank operations, ensuring the efficient conservation and deployment of genetic resources to address global agricultural demands.
Why it matches plant phenotyping methods種子形質を対象とする高スループットセンサー・画像フェノタイピング技術を総説しており、フェノタイピング手法が中心である。
abstractThis paper explores the transformative potential of high-throughput phenomics technologies, leveraging the electromagnetic spectrum-from gamma rays to radio waves-to enable rapid, precise, and non-invasive assessment of seed traits such as size, shape, biochemical composition, and vigor.
Cassava remains a critical food-security crop across Africa and Southeast Asia but is highly vulnerable to diseases such as cassava mosaic disease (CMD) and cassava brown streak disease (CBSD). Traditional diagnostic approaches are slow, labor-intensive, and inconsistent under field conditions. This review synthesizes current advances in combining unmanned aerial vehicles (UAVs) with deep learning (DL) to enable scalable, data-driven cassava disease detection. It examines UAV platforms, sensor technologies, flight protocols, image preprocessing pipelines, DL architectures, and existing datasets, and it evaluates how these components interact within UAV–DL disease-monitoring frameworks. The review also compares model performance across convolutional neural network-based and Transformer-based architectures, highlighting metrics such as accuracy, recall, F1-score, inference speed, and deployment feasibility. Persistent challenges—such as limited UAV-acquired datasets, annotation inconsistencies, geographic model bias, and inadequate real-time deployment—are identified and discussed. Finally, the paper proposes a structured research agenda including lightweight edge-deployable models, UAV-ready benchmarking protocols, and multimodal data fusion. This review provides a consolidated reference for researchers and practitioners seeking to develop practical and scalable cassava-disease detection systems.
Why it matches plant phenotyping methodsUAV画像と深層学習によるカッサバ病害の検出手法を中心に、センサー、撮影プロトコル、画像処理、モデル、データセット、性能指標を体系的にレビューしているため、植物の病害状態を対象とするフェノタイピング手法レビューに該当する。
abstractThis review synthesizes current advances in combining unmanned aerial vehicles (UAVs) with deep learning (DL) to enable scalable, data-driven cassava disease detection.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 5 Sept 2026
The apple (Malus × domestica), a globally significant perennial fruit crop, faces immense pressure from climate change, evolving pathogens, and consumer demand for novel traits. Also, remains constrained by slow trait selection despite technological advances. Further, the traditional breeding methods are slow and resource-intensive, hampered by the apple's long juvenile period and high heterozygosity. This systematic literature review (SLR) synthesizes the state of the art in advanced data-driven technologies for accelerating apple breeding and genetic modification. Following the PRISMA-EcoEvo protocol, 47 selected studies were analyzed from databases including Web of Science, Scopus, and PubMed. Our thematic synthesis reveals a paradigm shift towards a "digital breeding" model, characterized by the convergence of three core technological pillars. First, high-throughput phenotyping (HTP), which leverages sensor modalities such as RGB-D, hyperspectral imaging, and LiDAR, is automating the collection of trait data at an unprecedented scale. Second, machine learning (ML) and deep learning (DL) algorithms are being deployed for diverse applications, including cultivar identification with over 96% accuracy, non-destructive quality prediction, and genomic selection, thereby boosting predictive ability for key traits by up to 18%. Third, precise and efficient genome editing, predominantly using Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR)/CRISPR-associated protein 9 (Cas9), is enabling the rapid introduction of desirable traits, such as disease resistance, enhanced shelf life, and improved nutrient uptake. Demonstrated transgene-free editing protocols are accelerating the path to commercialization. We further explore the integration of these pillars through the agricultural internet of things (AIoT) and discuss emerging frontiers, including federated learning for data privacy, explainable AI (XAI) for model transparency, and the implications of recent regulatory frameworks. This review identifies critical research gaps, including the need for standardized open-access datasets and integrated end-to-end system validation. It concludes that the synergistic application of these technologies is poised to revolutionize the speed, precision, and resilience of apple improvement programs worldwide.
Why it matches plant phenotyping methodsリンゴ育種におけるデータ駆動技術の系統的レビューであり、高スループット表現型解析のセンサー技術と技術統合・検証課題を主要に扱っている。
abstractThis systematic literature review (SLR) synthesizes the state of the art in advanced data-driven technologies for accelerating apple breeding and genetic modification.
Abstract - The rapid advancement of unmanned aerial vehicles (UAVs) and deep learning techniques has significantly transformed crop monitoring and precision agriculture. Among various crops, soybean plays a crucial role in global food and oilseed production, making timely and accurate crop health assessment essential. This review presents a comprehensive analysis of UAV-based soybean crop health evaluation methods, with a particular focus on image-based disease detection and stress monitoring using deep learning models. Recent progress in convolutional neural networks, patch-level image analysis, attention mechanisms, and lightweight architectures is systematically examined. The paper discusses commonly used UAV imaging modalities, preprocessing strategies, model architectures, and evaluation practices reported in the literature. Furthermore, existing challenges such as environmental variability, computational complexity, data imbalance, and real-world deployment constraints are critically analyzed. Based on the reviewed studies, potential research directions are identified, emphasizing efficient patch-level learning, interpretable health mapping, and scalable field-level assessment. This review aims to provide researchers and practitioners with a clear understanding of current trends, limitations, and future opportunities in UAV-assisted soybean crop health monitoring. Key Words: - Unmanned Aerial Vehicles (UAVs), Soybean Crop Health Monitoring, Precision Agriculture, Deep Learning
Why it matches plant phenotyping methodsUAV画像と深層学習によるダイズの病害・ストレス評価手法を体系的にレビューしており、植物状態の画像ベース取得・推定方法が中心である。
abstractThis review presents a comprehensive analysis of UAV-based soybean crop health evaluation methods, with a particular focus on image-based disease detection and stress monitoring using deep learning models.
Detecting plant diseases is a crucial component of precision agriculture, necessary for maintaining economic viability, sustainable farming practices, food security, and preventing economic losses. Deep learning models such as Capsule Attention Networks, DenseNets, and Convolutional Neural Networks have demonstrated state-of-the-art performance in leaf-image-based disease classification. However, large-scale practical implementation in resource-constrained environments remains challenging due to overfitting, environmental insensitivity, extended training times, and high computational cost, along with the absence of a sustainable framework for real-world deployment. Emerging quantum neural networks (QNNs), integrated with quantum-influenced optimization algorithms, offer promising avenues to enhance practical applicability. Their capabilities for high-dimensional feature mapping, entanglement, and superposition improve generalization and convergence in hybrid models that combine quantum layers with classical architectures. Incorporating quantum modules into DenseNets, attention mechanisms, capsule networks, and other hybrid systems may further enhance accuracy, enable robust disease segmentation, and reduce training time. Nonetheless, challenges remain regarding real-time deployment on edge devices, efficient data encoding, limited explainability of quantum-driven features, and hardware constraints. This survey reviews classical, hybrid, and quantum-enhanced approaches, provides comparative insights, and identifies research gaps toward developing scalable, interpretable, and dependable frameworks for plant disease detection and diagnosis.
Why it matches plant phenotyping methods植物病害を葉画像から検出・分類する画像ベースの表現型取得手法を対象としたサーベイであり、手法レビューが中心です。
abstractThis survey reviews classical, hybrid, and quantum-enhanced approaches, provides comparative insights, and identifies research gaps toward developing scalable, interpretable, and dependable frameworks for plant disease detection and diagnosis.
The agricultural sector is rapidly evolving through digital technologies, creating significant opportunities to apply Artificial Intelligence (AI) for improving crop productivity, reducing losses, and optimizing resource utilization. This review specifically examines two key challenges in modern agriculture: the timely and accurate detection of crop diseases and the generation of precise fertilizer recommendations. We present a structured analysis of recent deep learning advancements, focusing on computer vision techniques such as Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and Generative Adversarial Networks (GANs) for image-based disease diagnosis, as well as NLP and knowledge-graph approaches for integrating agronomic information. Additionally, we evaluate data-driven fertilizer recommendation frameworks that incorporate soil characteristics, climatic factors, and crop growth patterns using hybrid deep learning and ensemble models. The review also explores the role of multimodal learning, IoT-based sensing, and cloud–edge computing in enabling real-time agricultural decision-making. Finally, we highlight current limitations—including dataset scarcity, generalization issues, explainability gaps, and scalability concerns—and outline future research directions for building intelligent, interpretable, and adaptive AI systems for sustainable agriculture.
Why it matches plant phenotyping methods作物病害を画像から検出する深層学習手法をレビューしており、植物の病徴・病害状態を推定するフェノタイピング手法が主要対象です。肥料推薦も扱いますが、病害検出の方法論的レビューとして適格です。
abstractThis review specifically examines two key challenges in modern agriculture: the timely and accurate detection of crop diseases and the generation of precise fertilizer recommendations.
Recent advances in high-throughput sequencing, imaging, and phenotyping have carried plant science into the era of 'big data.' Complex, multi-scale datasets provide new opportunities to uncover plant molecular mechanisms with a level of detail previously unachievable. Fully exploiting this complexity requires integrating advanced statistics, computational modeling, and artificial intelligence (AI). This minireview offers guidance on how the combination of AI and mechanistic models is transforming temporal, image-based, and spatial omics data into detailed predictions of robust plant traits. In addition, embedding physical principles into AI models can enhance interpretability and strengthen their biological grounding, leading to more realistic representations of plant inner workings. Together, these advances are reshaping plant science by turning 'big data' into deep insights, thus greatly enriching our understanding of plant growth, adaptation, and environmental responses.
Why it matches plant phenotyping methods植物フェノタイピング、画像データ、AI・機械論的モデルによる植物形質予測を扱うレビューであり、計算的な形質推定が中心的テーマです。
abstractThis minireview offers guidance on how the combination of AI and mechanistic models is transforming temporal, image-based, and spatial omics data into detailed predictions of robust plant traits.
Seed phenomics is a critical research field for understanding seed germination mechanisms. Metasurfaces, composed of subwavelength nanostructures, offer a promising pathway to achieve both dispersion control and imaging functionalities within an ultra-compact form factor. Recent advances in micro–nano-optics and computational imaging have opened new avenues for high-dimensional, multimodal imaging. However, conventional hyperspectral and light-field systems still face limitations in compactness, depth resolution, and spectral–spatial integration. This review summarizes recent progress in metalens and metasurface lens array-based light-field systems for hyperspectral imaging and 3D reconstruction, with a focus on the underlying principles, design strategies, and reconstruction algorithms that enable single-shot 3D hyperspectral acquisition. We further present a forward-looking roadmap toward the realization of a revolutionized imaging paradigm: a metasurface-based light-field platform that fully integrates 3D and hyperspectral imaging capabilities. In particular, we examine how dispersive metasurfaces serve as core optical elements for precise dispersion control in hyperspectral imaging systems, while metalens arrays enable accurate modulation of spatial–angular distributions in light-field configurations. We systematically review both 3D and spectral reconstruction algorithms, highlighting their roles in decoding complex optical encodings. The application of these integrated systems in seed phenotyping is emphasized, demonstrating their capability to capture 3D spatial–spectral distributions in a single exposure. This approach facilitates high-throughput analysis of morphological traits, germination potential, and internal biochemical composition, offering a comprehensive solution for advanced seed characterization. Finally, we outline a practical roadmap for implementing a metasurface-based light-field platform that integrates hyperspectral imaging and computational 3D reconstruction. This review offers a comprehensive overview of the state of the art in compact 3D light-field systems and multimodal hyperspectral imaging platforms, while providing forward-looking insights aimed at advancing smart seed phenotyping, precision agriculture, and next-generation optical imaging technologies.
Why it matches plant phenotyping methods種子フェノミクス向けの3D・ハイパースペクトル画像取得および再構成プラットフォームを中心にレビューし、形態形質や発芽能の解析への適用を扱うため、方法論が中心です。
abstractThis review summarizes recent progress in metalens and metasurface lens array-based light-field systems for hyperspectral imaging and 3D reconstruction
Plant diseases significantly impact agriculture by reducing crop yield, causing financial losses, and increasing food insecurity.Therefore, accurate and early detection of plant leaf diseases is crucial to prevent disease spread and support effective treatment strategies.Traditional diagnosis based on visual inspection by experts is time-consuming, labor-intensive, and prone to human errors.Recent advancements in digital imaging and machine learning have enabled automated plant disease identification systems with higher accuracy and efficiency.However, both ML and DL models still face challenges such as limited datasets, image noise, and model generalization.This study analyzes existing ML and DL approaches, identifies their limitations, and highlights research gaps to guide the development of an improved framework for plant leaf disease detection.
Why it matches plant phenotyping methods植物葉の画像に基づく病害識別手法を分析するレビューであり、病害状態という植物表現型の取得・推定方法が中心です。
abstractThis study analyzes existing ML and DL approaches, identifies their limitations, and highlights research gaps to guide the development of an improved framework for plant leaf disease detection.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 15 Sept 2026
Pathogenic plant diseases pose a serious risk to global food supplies and to the sustainable development of agriculture and forestry. Conventional control strategies, which rely heavily on chemical treatments, can disrupt ecological balance and may also affect human health. There is therefore a strong need for environmentally benign and efficient technologies that can detect disease at an early stage. This review surveys recent advances and remaining challenges in sensor based early detection of plant diseases, following the path from basic concepts to practical deployment. It first considers the biological traits and infection processes of major pathogens and identifies characteristic signaling molecules released by infected plants, which serve as design cues for sensing platforms. Existing detection strategies are then grouped into two broad categories. Direct approaches aim at the pathogen itself and use optical or electrochemical biosensors that incorporate antibodies or DNA probes. Indirect approaches focus on plant responses to stress and monitor indicators such as trace volatile organic compounds (VOCs), low frequency acoustic signals and changes in plant phenotype. Finally, the review summarizes the main classes of sensors, discusses their current limitations and outlines possible routes for technological translation and future development. Grounded in plant pathology and early disease monitoring, the review aims to provide researchers and practitioners with both an overview of the field and practical guidance for further work.
Why it matches plant phenotyping methods植物病害の早期検出に用いるセンサー技術を体系的にレビューし、感染植物の揮発性物質、音響信号、表現型変化などを測定する手法とセンサープラットフォームを中心に扱っているため、病害状態のフェノタイピング方法レビューに該当する。
abstractThis review surveys recent advances and remaining challenges in sensor based early detection of plant diseases, following the path from basic concepts to practical deployment.
Plants play a vital role in living organisms. However, daily changes in the environment can significantly impact plant growth with respect to their surroundings. Exposure to pathogens, environmental disturbances, or unfavorable conditions make plants vulnerable to diseases. The rapid spread of diseases affects the healthy growth of plants, resulting in the reduction of products quality and quantity. To mitigate these issues, it is necessary to monitor the plant growth and to identify the plant diseases at an earlier stage. However, the manual detection of plant diseases is an unreliable method as it is a time-consuming and error-prone process. Analyzing the subjected plant leaves through the advancements in image processing has paved the way to engage the researchers in the development of automated solutions for disease identification. In addition, image acquisition, data collection, and the development of advanced state-of-the-art approaches are the major research tools contributed by various researchers. Therefore, this paper delves into the latest methodologies by concentrating on these research contributions. In this regards, the available research papers published from 2018 to 2024 are considered. This study also incorporates some of the challenges and research topics for future plant leaf disease analysis by emphasizing the critical role of high-performance computing. Moreover, it offers valuable insights for researchers and practitioners, providing a wide-ranging understanding of the current state-of-the art approaches in the field of plant leaf disease analysis by highlighting their pros and cons.
Why it matches plant phenotyping methods植物葉の病害状態を画像処理で識別する手法を対象としたレビューであり、画像取得・データ収集・解析手法が中心的に扱われているため含める。
abstractAnalyzing the subjected plant leaves through the advancements in image processing has paved the way to engage the researchers in the development of automated solutions for disease identification.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 5 Sept 2026
Plant leaf spectrophotometry has been used successfully as a means to detect stress, and it has been complemented by fluorescence analysis. This identification can be achieved in the ultraviolet (UV), visible (red, green, blue; RGB), near-infrared (NIR), and infrared (IR) spectral regions. Hyperspectral (measuring continuous wavelength bands) and multispectral (measuring discrete wavelength bands) imaging modalities can provide detailed information concerning the physiological well-being of plants, often diagnosing them at an earlier stage than visual or other more traditional biochemical assays. Because hyperspectral methods are highly sensitive and accurate, they cost a lot and produce vast quantities of data, which demand sophisticated computing software, and compared to multimedia, multispectral, and RGB cameras, they are less expensive and easier to carry but have reduced spectral resolution. Such methods are justified by thermal and fluorescence images revealing variations in the temperature and efficiency of photosynthesis of the leaves in response to stress. New digital imaging, thermal imaging, and optical filter technologies, and advancements in smartphone cameras have rendered low-cost, field-deployable platforms to monitor plant stress in real time feasible. Machine learning also supports these techniques by automating feature extraction, classification, and prediction to reduce the use of expensive instrumentation and human skill. But also problems like sensor calibration in a changing field, low model generalization across species and environments, and large, annotated datasets are needed. Beyond highlighting the relative strengths of the conventional and contemporary sensing approaches, the paper also examines the possibility of applying machine learning to multimodal images, as well as the growing impact of smartphone- based solutions in supplying inexpensive agricultural diagnostics. It concludes by overviewing the current limitations and limits to future research into scalable, cost-effective, and generalizable plant stress models.
Why it matches plant phenotyping methods植物ストレスを対象としたマルチモーダル画像・分光・熱・蛍光センシングと機械学習による表現型抽出を中心に扱う方法レビューであり、植物フェノタイピング手法の範囲に明確に該当する。
titlePlant stress detection using multimodal imaging and machine learning: from leaf spectra to smartphone applications.
Highlights This study presents a seven-year operational review of a large-scale cable-suspended phenotyping system. Standardized operation and data protocols enable the delivery of high-resolution, high-frequency phenotypic datasets. The platform supports a wide range of phenotyping applications, from morphological to physiological trait analysis. The system plays a critical role in developing advanced sensing technology for phenotyping and precision agriculture. ABSTRACT. High-throughput plant phenotyping (HTPP) significantly improves plant phenotyping efficiency by integrating advanced sensing technologies, data processing, and modeling techniques. Over the last two decades, field-based HTPP systems have evolved from handheld sensors to sophisticated robotic platforms. Large-scale, ground-based phenotyping facilities have made significant contributions to advancing technology through their high sensor payloads, proximal measurement capabilities, and unmatched spatial and temporal resolution. This review paper presents a detailed and quantitative analysis of the operational performance of the cable-suspended NU-Spidercam phenotyping facility at the University of Nebraska–Lincoln from 2017 to 2023, focusing on daily operations, data management strategies, and system maintenance. Additionally, the paper systematically summarizes representative studies performed at the facility across morphological, spectral, and physiological phenotyping domains. Finally, the discussion highlights future directions, emphasizing the NU-Spidercam’s role in validating mobile phenotyping platforms, enabling precision agriculture research, supporting fundamental remote sensing studies, and facilitating the transfer of advanced sensing techniques to affordable, mobile platforms such as drones. Keywords: Artificial intelligence, Computer vision, Deep learning, Field plant phenotyping, Large-scale facility, Machine learning, Operational review, Physiological phenotyping.
Why it matches plant phenotyping methods大規模なケーブル懸架型植物フェノタイピング施設の運用性能、データ管理、保守、および形態・スペクトル・生理形質測定を体系的にレビューしており、フェノタイピング基盤が中心である。
abstractThis review paper presents a detailed and quantitative analysis of the operational performance of the cable-suspended NU-Spidercam phenotyping facility at the University of Nebraska–Lincoln from 2017 to 2023, focusing on daily operations, data management strategies, and system maintenance.
Microfluidics has emerged as a powerful enabling technology in plant science, offering unprecedented control over microscale environments for the cultivation, manipulation, and analysis of plant cells, tissues, and organs. This review provides a comprehensive overview of the development and application of microfluidic systems in plant physiology and development studies. We categorize the platforms based on their structural designs and biological targets—from single-cell trapping devices and droplet-based screening systems to organ-on-a-chip and root–microbe interaction modules. Key applications include live-cell imaging, real-time monitoring of stress responses, microenvironment simulation, and high-throughput phenotyping. Particular attention is given to microfluidic investigations of plant mechanobiology, chemotropism, and cell-to-cell communication, as well as their integration with biosensors, electrophysiological tools, and environmental control systems. We also examine current limitations related to material compatibility, device scalability, and biological complexity, and highlight emerging solutions such as modular design, interdisciplinary integration, and soil-on-a-chip systems. By addressing both fundamental research needs and practical agricultural challenges, microfluidic technologies offer a transformative path toward precision plant science and sustainable crop innovation.
Why it matches plant phenotyping methods植物研究向けマイクロ流体プラットフォームを体系的にレビューし、高スループット表現型解析やストレス応答のリアルタイム測定を中心的に扱っているため、方法レビューとして採用。
abstractThis review provides a comprehensive overview of the development and application of microfluidic systems in plant physiology and development studies.
This systematic literature review investigates the development of a Ground-Penetrating Radar (GPR)-based object detection system tailored for under-ground garlic crop monitoring. While garlic-specific GPR applications re-main limited, studies on structurally similar root crops such as potatoes and carrots provide a valuable reference framework. Using a PRISMA-guided methodology, 16 relevant studies were analysed and synthesized, highlighting advancements in GPR signal processing, object reconstruction, and machine learning integration. Results show that mid- frequency GPR (500–800 MHz), especially when paired with deep learning models such as 3D Convolutional Neural Networks (CNNs), offers high accuracy in detecting root structures. Key challenges such as signal attenuation in clay-rich and tropical soils are addressed through electromagnetic induction (EMI) hybridization and antenna optimization. A comparative matrix summarizes the most relevant findings, and actionable recommendations are proposed to guide future research. These include the development of garlic-specific datasets, localized field testing, and AI- enhanced signal classification. GPR, when effectively configured and paired with machine learning, presents a viable solution for real-time, non-invasive garlic crop monitoring in tropical agriculture.
Why it matches plant phenotyping methods地下作物の成長・根構造をGPRで検出する手法の開発に焦点を当てた系統的レビューであり、植物形態の非破壊取得・抽出方法が中心です。
titleA Systematic Literature Review for the Development of an Object Detection System for Monitoring Underground Crop (Garlic) Growth Using GPR
This study explores the conceptual framework and evaluation methods of grape berry uniformity, elucidating its multidimensional nature arising from the coordinated contributions of berry size, shape, and cluster structure. Quantitative evaluation approaches based on the coefficient of variation, composite multi-trait indices, and high-throughput phenotyping technologies are systematically summarized. On this basis, key factors influencing berry uniformity are further analyzed, including genetic background, pollination and fertilization processes, berry developmental dynamics, plant growth regulator treatments, and water-nutrient environmental conditions. Integrating breeding strategies with production practices, a framework for improving berry uniformity is proposed, centered on “multi-trait selection, marker-assisted selection, and cultivation regulation.” Meanwhile, with the advancement of machine vision, high-throughput phenotyping, and multi-source data integration technologies, the evaluation of berry uniformity is shifting toward automation, precision, and intelligence. However, challenges remain in the standardization of evaluation systems, elucidation of molecular mechanisms, and integration of multi-source data. Future research directions toward data-driven precision improvement are discussed. This study aims to provide theoretical foundations and technical support for enhancing the quality and standardized production of table grapes.
Why it matches plant phenotyping methodsブドウ果実の均一性を対象に、評価指標、高スループットフェノタイピング、機械ビジョンによる自動評価を体系的に扱うレビューであり、フェノタイピング手法が中心です。
abstractQuantitative evaluation approaches based on the coefficient of variation, composite multi-trait indices, and high-throughput phenotyping technologies are systematically summarized.
Agricultural systems are entering an era defined not just by mechanization but by real-time, spatially aware, data driven production practices. This shift which has rapidly evolved from novelty to necessity in precision agriculture. At the center of this shift Unoccupied Aerial Vehicles (UAV) or drones have operationalized high-resolution aerial data into sustainable agricultural outcomes. This chapter provides an application-focused roadmap for integrating UAV into modern agronomic workflows as pre, during, and post flight operations for agronomic flight planning. It bridges the engineering of flight platforms and sensors with the applications in crop stress detection, variable-rate input application, and predictive yield modeling. We explore UAV architecture and their implications for data resolution, field scale, and operational complexity. Sensor systems use the portions of electromagnetic spectrum (RGB, multispectral, hyperspectral, thermal, LiDAR) and are examined through their applications for plant physiology and soil interactions. Ground sampling distance, spectral calibration, geospatial accuracy and photogrammetry are not treated as ancillary steps, but as critical determinants of agronomic utility. We describe the full data pipeline from FAA (Federal Aviation Administration) regulations to machine learning-driven analytics, acquisition, orthomosaic generation, digital surface modeling, vegetation index extraction, and the development of actionable prescription maps. In the context of AI evolution, we emphasize how AI-ML methods classification, regression, clustering, and dimensionality reduction help with integrating complex patterns in time-series UAV imagery, enabling early and precise management of nutrients, water, weeds, and disease. By synthesizing global regulatory frameworks and field-based use cases, the chapter concludes UAV as tools that transforms data into agronomic decisions.
Why it matches plant phenotyping methodsUAVセンサー、校正、フォトグラメトリ、オルソモザイク、植生指数抽出、機械学習解析を含む一連の植物状態・ストレス推定ワークフローをレビューしており、単なる生物学的実験の測定ではなく、取得・解析手法とプラットフォームが中心です。
abstractThis chapter provides an application-focused roadmap for integrating UAV into modern agronomic workflows as pre, during, and post flight operations for agronomic flight planning.
Global demographic expansion and accelerating climate change are heightening the need for sustainable enhancement of crop productivity and resilience to environmental stresses. As conventional breeding approaches based on empirical selection approach their limits, digital breeding is emerging as an integrated framework that combines high-throughput imaging, multi-source data, and artificial intelligence (AI). Although next-generation sequencing (NGS) and smart-farming systems have enabled large-scale accumulation of genomic and environmental datasets, the phenotypic dimension remains a critical bottleneck in predictive breeding. To overcome this limitation, Korea has established six large-scale national phenotyping platforms equipped with advanced RGB, hyperspectral, and thermal imaging systems for high-throughput, precision phenotypic data acquisition. These platforms support quantitative and non-destructive monitoring of plant morphology, stress responses, and developmental dynamics and employ AI-driven classification and predictive modeling to derive biologically relevant traits. The integration of genomic, phenomic, and environmental datasets through AI-based analytical pipelines is expected to accelerate digital breeding, facilitating the development of climate-resilient and consumer-oriented cultivars within a data-driven agricultural paradigm. Collectively, plant phenomics research is evolving beyond image-based observation toward a comprehensive, predictive framework that provides the technological basis for next-generation precision agriculture.
Why it matches plant phenotyping methods植物フェノミクスとデジタル育種に関するレビューであり、RGB・ハイパースペクトル・熱画像を用いた大規模表現型プラットフォーム、形態・ストレス応答・発達動態の定量化、AI解析を中心的に扱っている。
abstractKorea has established six large-scale national phenotyping platforms equipped with advanced RGB, hyperspectral, and thermal imaging systems for high-throughput, precision phenotypic data acquisition.
Imaging technologies have become indispensable tools in modern plant phenotyping, transforming visual information into measurable traits essential for analyzing morphology, physiology, biochemistry, and micro- to nanoscale structures. This concise review summarizes recent advances by dividing plant imaging into two major categories: (1) physiological and biochemical, which includes hyperspectral, multispectral, and fluorescence hyperspectral imaging, as well as terahertz imaging, surface-enhanced Raman scattering, and carbon dot-based techniques; and (2) structural and morphological, encompassing RGB, thermal, light detection and ranging (LiDAR), confocal microscopy, and optical coherence tomography. Together, these modalities deliver insights from the canopy to the molecular level, enabling precise monitoring of plant stress, disease, and developmental traits. By integrating these multimodal imaging techniques with artificial intelligence, the review highlights key developments, current challenges, and future perspectives in plant measurement and analysis.
Why it matches plant phenotyping methods植物フェノタイピングに用いる画像技術を体系的にレビューし、植物形質の測定・解析手法と課題を扱うことが中心である。
abstractThis concise review summarizes recent advances by dividing plant imaging into two major categories
Digital phenotyping has evolved from simple imaging-based trait measurement to a core technology enabling large-scale analysis of genotype × environment × management (G × E × M) interactions. This review highlights the manner in which digital phenotyping simultaneously supports two major research trajectories in modern agro-ecosystems. In engineering-driven approaches, imaging and sensor data are increasingly used to enhance the physical control of climate, irrigation, and crop protection through model-based and AI-assisted decision systems. In life science-centered approaches, high-throughput phenotyping and multi-omics integration provide mechanistic insights into plant stress responses, developmental plasticity, and complex trait regulation. Despite significant progress, both pathways face limitations in addressing the biological complexity and climatic unpredictability of crop systems. We discuss the emerging opportunities to integrate these domains through a two-layer AI framework that combines real-time sensing and actuation (“Physical AI”) with ontology- and LLM-based reasoning systems capable of synthesizing biological knowledge and generating strategic policies. Together, these developments position digital phenotyping as a bridging technology and a foundation for adaptive, resilient, and knowledge-driven agro-ecosystem management.
Why it matches plant phenotyping methods植物デジタルフェノタイピングを中心に、画像・センサーデータによる形質測定と高スループット解析の発展・応用をレビューしており、方法論レビューとして中心的である。
abstractDigital phenotyping has evolved from simple imaging-based trait measurement to a core technology enabling large-scale analysis of genotype × environment × management (G × E × M) interactions.
Accurate measurement of plant phenotypic data can provide a comprehensive understanding of plant physiology and help to study the relationship between plant genes and the environment. The application of visible light and other multi-source and multi-dimensional imaging sensing technology can provide a rich data source for plant phenotype identification and monitoring. With the continuous development and application of computer technology in the field of plant phenotype analysis, deep learning technology has made remarkable achievements in plant phenotype identification and monitoring. On the basis of reviewing the relevant research results at home and abroad at this stage,this paper firstly describes the common ways of plant phenotype image acquisition; then it discusses in detail the current status of the application of deep learning technology in the fields of classification, detection and segmentation of plant phenotypes, crop development and yield prediction, as well as plant drought and pest stress, etc.; and finally it discusses the challenges and future development goals of the deep learning method in the monitoring and recognition of plant phenotypes.This paper aims to provide theoretical support and technical reference for the development and application of deep learning technology in the field of agricultural plant phenotyping.
Why it matches plant phenotyping methods植物フェノタイピングにおける画像取得と深層学習による分類・検出・セグメンテーション、成長・収量予測などを体系的にレビューしており、方法論が中心です。
titleREVIEW OF RESEARCH ON RECOGNITION AND MONITORING OF PLANT GROWTH PHENOTYPE BASED ON DEEP LEARNING
Plant image science is a new multidisciplinary science that involves imaging techniques and image analysis methods to capture, process, and analyze plant images for understanding plant status and responses to environmental perturbations across various plant types and ecosystems. Plant image science encompasses a broader range of concept and scope than plant phenomics making it differentiable and widely appreciable. It covers plant phenotyping and the diagnosis and remote sensing of individual plants, plant communities, vegetation, and living organisms (for example, microorganisms and insects). Relevant applications include but not limited to plant phenomics, plant breeding and genomic research, crop management, crop protection, agricultural machinery, and postharvest processes. Its conceptual flexibility and multidisciplinary nature suggest that it has virtually no limitations in its applications, making it an essential domain and tool for the future of plant-based sciences and industries including agriculture, forestry and environment.
Why it matches plant phenotyping methods植物画像科学と植物フェノタイピングを含む画像取得・解析分野の概念的レビューであり、方法領域の整理が中心です。
abstractPlant image science is a new multidisciplinary science that involves imaging techniques and image analysis methods to capture, process, and analyze plant images
Crop phenomics has emerged as a transformative discipline that bridges genomics and agronomy by enabling precise, high-throughput, and non-destructive measurement of plant traits. Over the past decade, more than 50 advanced phenotyping platforms have been established globally, ranging from controlled-environment facilities to field-based systems, underscoring the momentum of this technological revolution. With increasing demands for sustainable food production under climate change, phenomics offers unprecedented opportunities to accelerate genetic gains and optimize crop management. Recent advances in imaging technologies, sensor integration, and computational tools have expanded the scope of trait dissection in field crops. Ground-based systems, unmanned aerial vehicles (UAVs), and satellite-based remote sensing now provide scalable and high-resolution field phenotyping, while controlled-environment platforms deliver mechanistic insights into plant physiology and stress responses. The integration of hyperspectral, thermal, and 3D imaging with machine learning algorithms has enhanced trait extraction and predictive accuracy. Applications span diverse domains, including identification of stress-resilient genotypes, improvement of nutrient and water use efficiency, early disease detection, and precision breeding strategies. Despite these advances, challenges persist in data standardization, cost-effectiveness, and translating controlled-environment findings to field conditions. Adherence to FAIR (Findable, Accessible, Interoperable, and Reusable) data principles remains critical to ensure harmonized and comparable datasets across platforms. In future, the convergence of phenomics with genomics, enviromics, and artificial intelligence is poised to redefine crop improvement pipelines, enabling the development of resilient, high-yielding, and resource-efficient cultivars. This review synthesizes current tools and applications, highlighting the pivotal role of crop phenomics in advancing global food and nutritional security.
Why it matches plant phenotyping methods植物フェノミクスのツール、プラットフォーム、画像・センサー・計算手法を体系的に扱う方法論レビューであり、スコープの中心に該当する。
abstractThis review synthesizes current tools and applications, highlighting the pivotal role of crop phenomics
Abstract Artificial intelligence (AI), a key driver of the Fourth Industrial Revolution, is being rapidly integrated into plant phenomics to automate sensing, accelerate data analysis, and support decision‐making in phenomic prediction and genomic selection. This perspective paper synthesizes current advances, identifies major barriers, and proposes future directions to realize the transformative potential of AI‐enabled plant phenomics. We first provide an overview of AI technologies with the potential to address key challenges in phenomics, from data collection to phenotypic trait extraction and environmental sensing. We then present three case studies focusing on specialty crops (blueberry [ Vaccinium corymbosum L.] mechanical harvestability traits, strawberry [ Fragaria × ananassa (Duchesne ex Weston)] production, and citrus [ Citrus L.] disease) to illustrate practical applications of AI‐driven phenomics. Moreover, we highlight future perspectives and opportunities for further research and innovation. These include large foundation models, real‐time inference on edge devices, explainable AI, generative AI and digital twins, AI‐enhanced multi‐omics, agentic AI, and knowledge‐guided and data‐driven hybrid approaches. Finally, we discuss key challenges and limitations of applying AI to plant phenomics, including data curation, model generalization and bias, and ethical considerations related to equitable access to AI tools.
Why it matches plant phenotyping methods植物フェノミクスにおけるAIセンシング・形質抽出を主題とする展望論文であり、方法論のレビューとして中心的に扱っている。
abstractWe first provide an overview of AI technologies with the potential to address key challenges in phenomics, from data collection to phenotypic trait extraction and environmental sensing.
The integration of Large Language Models (LLMs) with Vision-Language Models (VLMs) holds transformative potential for plant stress phenotyping, enhancing high-throughput crop monitoring, trait identification, and decision support. Traditional phenotyping methods, often reliant on manual assessments and task-specific Machine Learning (ML) models, face persistent limitations in scalability, adaptability, and contextual interpretation, especially under complex and overlapping stress conditions. VLMs address these challenges by combining deep visual recognition with contextual reasoning, enabling real-time analysis of multimodal inputs such as high-resolution imagery, agronomic text data, and environmental sensor readings. Complementarily, LLMs contribute to text mining, semantic annotation of trait descriptors, and the integration of external knowledge via Retrieval-Augmented Generation (RAG), thereby enhancing the interpretability and adaptability of phenotyping workflows. This review critically evaluates the emerging role of integrating LLMs with VLMs in plant stress phenotyping, highlighting their applications in visual trait recognition, knowledge extraction, and autonomous decision-making. We synthesize current advances and identify key challenges, including data quality, domain-specific generalization, model transparency, and equitable access to AI technologies. As one of the first comprehensive reviews on this topic, we propose a forward-looking framework that integrates LLMs, VLMs, and RAG systems to enable scalable, explainable, and user-centric phenotyping solutions. This interdisciplinary convergence offers a promising pathway toward sustainable and resilient AI-driven agriculture.
Why it matches plant phenotyping methods植物ストレス・形質認識のためのLLM/VLM統合を批判的に評価するレビューであり、植物フェノタイピング手法が中心です。
abstractThis review critically evaluates the emerging role of integrating LLMs with VLMs in plant stress phenotyping
ABSTRACT Agriculture is essential for sustaining life, providing nutrition and contributing trillions of dollars to the global economy. However, increasing global populations and limited natural resources are placing unprecedented pressure on food production systems. These challenges are further exacerbated by plant diseases, environmental pollution and extreme weather events, all of which can significantly reduce crop yields and undermine socioeconomic stability. To ensure food security, there is an urgent need to develop early‐stage plant disease detection systems, optimise resource efficiency and minimise dependence on chemical inputs. Traditional crop inspection methods, which rely heavily on visual assessment and farmer expertise, face significant limitations in accuracy and scalability. In contrast, advanced optical‐based techniques—such as Raman spectroscopy and nanopore sequencing—offer promising alternatives by enabling non‐invasive, highly sensitive and real‐time disease detection. This review explores diagnostic approaches leveraging nanotechnology, as well as emerging advancements in information and communication technology for agriculture. By integrating these cutting‐edge solutions we can revolutionise the global fight against plant pathogens and secure sustainable food production for the future.
Why it matches plant phenotyping methods植物病害の非侵襲・リアルタイム検出に用いる光学的センシング手法を中心に扱うレビューであり、病害状態という植物表現型の取得方法が主題である。
abstractThis review explores diagnostic approaches leveraging nanotechnology, as well as emerging advancements in information and communication technology for agriculture.
Wheat rusts are the most important diseases leading to substantial yield losses. Early and precise detection of wheat rusts for early mitigation and disease control is imperative. This review summarizes the advances in high-throughput phenotyping (HTP) approaches for rust detection. Additionally, various genomic interventions leading to the development of rust resistance in wheat are discussed in detail. High-throughput phenotyping (HTP) approaches enable early, non-destructive, and repeatable detection of wheat diseases. However, they need initial investment, expertise, and computational resources. RGB imaging achieves ~80% accuracy by capturing infected leaf coloration, while hyperspectral and fluorescence imaging can predict rust with over 90% accuracy, 3–8 days before visible symptoms. LiDAR, UAVs, and robotic platforms automate large-scale field phenotyping, and spectral indices (NDVI, PRI), thermal, and chlorophyll sensors detect early physiological changes. AI and machine learning models, including CNNs and SVMs, enhance diagnostic precision and reduce bias, while mobile apps, lateral flow devices, and IoT-based systems facilitate affordable, real-time rust detection and forecasting. Genomic interventions complement phenotyping, with marker-assisted selection (MAS) enabling precise tracing of rust resistance genes, and genomic selection (GS) allowing early multi-trait prediction. QTL mapping and GWAS identify major and minor resistance loci, while introgression from wild relatives and MAS reduce linkage drag and introduce novel alleles. Transgenic approaches, RNA interference (RNAi), and CRISPR/Cas9 gene editing enhance resistance through targeted gene modification, and gene pyramiding combines multiple loci for durable protection. Wheat pan-genome resources further support precise trait targeting, and speed breeding integrated with MAS, GS, or gene editing accelerates rust-resistant line development. Efficient seed system pathways ensure rapid dissemination, adoption, and resilience. The development and commercialization of rust-resistant wheat varieties under harsh climatic conditions are crucial for mitigating yield losses, reducing fungicide use, safeguarding farmer livelihoods, and ensuring sustainable food security.
Why it matches plant phenotyping methodsコムギさび病の高スループット表現型解析手法を中心にレビューしており、画像・分光・熱・LiDAR・AIなどによる植物病徴の検出方法を扱うため。
abstractThis review summarizes the advances in high-throughput phenotyping (HTP) approaches for rust detection.
Summary The intricate architecture of plant metabolic networks and the dynamic fluxes of elements through these networks are fundamental determinants of how carbon (C) is partitioned among growth, reproduction, storage, respiration and the synthesis of secondary metabolites. While these C fluxes are critical to cellular function and plant life, their routine measurement remains a significant challenge. This review aimed to highlight the substantial potential of hydrogen (H) isotopes of plant carbohydrates to bridge this methodological gap by serving as a flux‐based proxy for primary C metabolism. This potential is demonstrated from both a theoretical perspective and by summarising available evidence at the whole‐molecule and position‐specific levels. The utility of this proxy is significant for understanding species' metabolic plasticity, assessing plant responses to environmental change and selecting superior metabolic phenotypes in agriculture and forestry. However, for this proxy to be fully realised, several fundamental questions remain. This includes the identification of specific metabolic reactions associated with isotopic variation and their relationship to plant performance. We outline several approaches to advance the development of an H‐isotope based plant metabolic proxy for plant performance.
Why it matches plant phenotyping methods植物炭水化物のH同位体を炭素代謝フラックスと植物パフォーマンスの代理指標として発展させる方法論レビューであり、植物の代謝表現型評価が中心です。
abstractThis review aimed to highlight the substantial potential of hydrogen (H) isotopes of plant carbohydrates to bridge this methodological gap by serving as a flux‐based proxy for primary C metabolism.
Plant health is a fundamental aspect of agricultural production, intimately linked to crop yield and quality. The precise acquisition of plant physiological information is vital for modern farmland management. This information encompasses plant biomarker information and details about the plant's growth environment. Traditional detection methods are limited by lengthy intervals between measurements and time-consuming detection processes. Wearable sensors, attached to the surface of plants, transform plant physiological environment information into photoelectric signals. This enables continuous, real-time in-situ monitoring of plant physiological information, opening up new avenues for plant health management and variety improvement. This article reviews the latest advancements in wearable sensors for plant health, classifies the sensors based on the types of plant physiological information they measure, and provides a detailed overview of their applications, including plant biomarker sensors and plant growth environment sensors. Furthermore, the challenges and future directions in this field are discussed, highlighting the potential of wearable sensors in precision agriculture and proposing a multidisciplinary approach to harness the full potential of wearable sensors in ensuring food security.
Why it matches plant phenotyping methods植物の生理情報を連続測定するウェアラブルセンサー技術を中心に整理したレビューであり、植物フェノタイピング手法レビューに該当する。
abstractThis article reviews the latest advancements in wearable sensors for plant health, classifies the sensors based on the types of plant physiological information they measure
Plant diseases pose a significant threat to global agricultural productivity, making early and accurate detection critical for yield protection and food security. This study evaluates the evolution, effectiveness, and practical applicability of Machine Learning (ML) and Deep Learning (DL) models for plant disease detection while analyzing research trends to identify leading models, data limitations, and implementation challenges. A systematic literature review and bibliometric analysis were conducted using the PRISMA framework, examining 625 peer-reviewed articles published between 2017 and 2025 from major databases. The analysis highlights the most influential studies, commonly used datasets, and top-performing ML/DL models, assessed in terms of accuracy, methodology, dataset type, and real-time deployment potential. Results show that models such as YOLOv4, VGG19, ResNet50, and MobileNetV2 achieved accuracy levels between 98% and 99.99%, with most trained on the PlantVillage dataset or custom annotated datasets. Several studies demonstrated successful real-time deployment via mobile and edge-device applications. However, key challenges remain, including limited dataset diversity, poor model generalization across environments, and reduced performance under real-field conditions. This study provides a comprehensive overview of progress in AI-based plant disease detection, emphasizing the need for lightweight, adaptable, and field-ready models to support scalable real-world deployment.
Why it matches plant phenotyping methods植物病害状態の画像ベース検出手法を対象とした系統的レビューであり、モデル、データセット、精度、実運用性を方法論的に評価しているため、植物フェノタイピング手法レビューとして含める。
abstractThis study evaluates the evolution, effectiveness, and practical applicability of Machine Learning (ML) and Deep Learning (DL) models for plant disease detection
Plant diseases are estimated to cause a reduction of 20–40% in worldwide crop yields leading to over USD 220 billion in lost productivity and food security each year. Detecting these diseases early is essential for sustainable management, however traditional methods like scouting and laboratory diagnostics are often slow and impractical for large-scale or pre-symptomatic monitoring. This review looks at recent developments in using Unmanned Aerial Vehicles (UAVs) combined with Artificial Intelligence (AI) for overseeing crop health. It compares different sensor types such as RGB, multispectral, hyperspectral, thermal and LiDAR and explains the process from data collection to AI-driven classification. A particular focus is on machine learning (ML) and deep learning (DL) including Convolutional Neural Network (CNN) architectures, which have achieved 90–98% accuracy in identifying diseases in crops like wheat, potatoes, citrus and grapevines. The review further explores exciting new directions like data fusion, edge computing and autonomous scouting, pointing towards a future of more proactive, scalable and precise disease management. Keywords: Climate change, hi-tech agriculture, remote sensing, pre-symptomatic, autonomous scouting, machine learning.
Why it matches plant phenotyping methodsUAVセンサーとAIによる作物病害状態の観測・分類手法を中心に比較・レビューしており、植物フェノタイピング手法のレビューに該当する。
abstractThis review looks at recent developments in using Unmanned Aerial Vehicles (UAVs) combined with Artificial Intelligence (AI) for overseeing crop health.
Introduction Perennial orchard systems are emerging as important yet underrepresented carbon sinks within the AFOLU sector, which contributes 20-24% of global GHG emissions. Many countries still rely on Tier 1 default values that fail to capture the structural and management characteristics of orchard species. Accurate biomass and carbon estimation, particularly through species-specific allometric equations, is essential for improving Tier 2-3 GHG reporting and recognizing orchards as meaningful contributors to climate-smart land management. Methods A systematic literature review was conducted using five major databases (2008-2024), following PRISMA guidelines. From 240 initial records, 53 studies met the inclusion criteria. These were categorized into three domains: (i) biometric modeling of fruit-tree biomass, (ii) species-specific allometric equation development, and (iii) carbon-sequestration assessments. Methodological trends, model performance, and research gaps were synthesized to inform an IPCC-aligned framework for orchard-specific emission and removal factors. Results Most studies were concentrated in Asia and the Mediterranean and focused on citrus, mango, apple, grape, and olive systems. Power-law allometric models dominated and generally showed high predictive performance (R² > 0.90) with variables such as diameter, height, and crown dimensions. However, major gaps remained: limited data for belowground biomass, juvenile trees, grafted architectures, vineyards, and uncertainty quantification-all of which restrict Tier 2-3 applicability. Discussion Based on these findings, this review proposes a standardized methodological framework linking biometric measurements, species-specific allometric modeling, remote-sensing integration, and uncertainty analysis to derive orchard-specific emission and removal factors consistent with IPCC guidance. Broader adoption of such protocols would improve transparency and accuracy in national AFOLU inventories and strengthen recognition of perennial orchards as viable nature-based climate solutions that support national net-zero targets.
Why it matches plant phenotyping methods果樹・ブドウ樹のバイオマスという植物形質を推定するアロメトリック手法を体系的にレビューし、計測・モデル化・リモートセンシング・不確実性分析を統合した標準化フレームワークを提案しており、手法が中心である。
abstractA systematic literature review was conducted using five major databases (2008-2024), following PRISMA guidelines.
Crop physiological and nutrient biochemical information plays a vital role in uncovering patterns of crop growth and development, as well as understanding their interactions with environmental factors. Unmanned aerial vehicles (UAV) -based hyperspectral imaging (HSI) technology offers an innovative tool for acquiring physiological and nutrient biochemical information through non-destructive and rapid collection of continuous spectral data from crops. However, challenges such as low signal-to-noise ratios (SNR), spectral variability for the same material, and high dimensionality in hyperspectral data make feature selection and extraction critical steps in data processing and analysis. Therefore, this review focuses on feature selection and extraction methods in the application of UAV-based hyperspectral technology for retrieving and monitoring crop physiological and biochemical information, providing theoretical support for its use in agriculture. Firstly, it provides a detailed discussion of feature selection methods, including filter-based, wrapper-based, and embedded approaches, along with various feature extraction techniques, analyzing their applicability and limitations in crop retrieving and monitoring. Secondly, the review highlights the use of vegetation indices (VIs) in feature extraction, covering advancements from basic indices to those optimized for specific applications. Finally, the article summarizes the main challenges of existing methods, particularly the issues of high-dimensional data processing and noise, and outlines potential future directions. This review highlights the significance of feature selection and extraction methods as critical tools for efficiently processing hyperspectral data. Through systematic analysis and synthesis, it provides theoretical support for agricultural researchers and practitioners while underscoring the importance of these techniques in driving innovation and advancements in hyperspectral technology.
Why it matches plant phenotyping methodsUAVハイパースペクトル画像から作物の生理・生化学形質を推定するための特徴選択・抽出手法を中心に扱う方法論レビューであり、植物フェノタイピング手法のレビューに該当する。
abstractthis review focuses on feature selection and extraction methods in the application of UAV-based hyperspectral technology for retrieving and monitoring crop physiological and biochemical information
Crop diseases pose a critical threat to global food security. Traditional diagnostic methods are inefficient and fail to meet the demands of modern precision agriculture. In recent years, artificial intelligence (AI) technologies centered on deep learning have revolutionized the rapid and precise identification of crop diseases. This paper systematically outlines key AI techniques for crop disease recognition, including computer vision-based image recognition, multimodal data fusion, and edge computing for field deployment. By analyzing representative domestic and international application cases, this paper highlights the significant advantages of this technology in terms of accuracy and efficiency. Simultaneously, it delves into current technical bottlenecks and deployment barriers, such as the few-shot learning problem, environmental interference, and low farmer trust. The paper concludes by outlining future directions, including self-supervised learning, digital twins, and industry integration, to advance the deep application and implementation of AI technology in smart agriculture.
Why it matches plant phenotyping methods作物病害を画像認識・深層学習で推定する技術を中心に、手法、精度、展開課題、将来方向を体系的にレビューしており、植物の病害状態を対象とするフェノタイピング方法レビューに該当する。
abstractThis paper systematically outlines key AI techniques for crop disease recognition, including computer vision-based image recognition, multimodal data fusion, and edge computing for field deployment.
Field / plotWhole plant / canopy / plot / fieldStress / disease detectionDisease symptoms / severityWater status / transpiration
Agricultural industry endeavors to increase the productivity and quality of crops at reduced costs, effort, and time. An obvious requirement is extensive crop health monitoring, which includes early detection of crop diseases and treatment, detection of intruders like birds, animals, and humans in the farms and their repulsion, and assessment of crop water requirements and irrigation. Unlike traditional agri-practices, advanced digital frameworks, such as Artificial Intelligence, Computer Vision, Edge Computing, and Internet of Things, provide much promising solutions, thereby escalating exhaustive researches in the agricultural domain. This communication reviews key crop health monitoring systems developed over the past decade, outlining their advantages and limitations, shedding light on real-world implementation challenges, and proposing potential directions for future research.
Why it matches plant phenotyping methods画像処理・AIを用いた作物の健康状態や病害の検出システムをレビューしており、植物状態の取得・判定手法が中心的に扱われている。ただし侵入者検知や灌漑需要評価も含むため、植物表現型への焦点はやや広い。
titleIn-Field Crop Health Monitoring Using Intelligent Image Processing over Internet of Things Framework: A Comprehensive Review
Early detection of plant diseases is crucial for ensuring crop health and preventing yield losses. Convolutional Neural Networks (CNN) have experienced rapid development in plant disease image recognition due to their ability to extract significant visual features from plant leaves. However, optimal results require CNN architecture customization according to unique disease and crop characteristics. While this approach offers high accuracy and efficiency, various challenges hinder widespread application, including limited representative datasets, high computational requirements, and difficulties in designing generalizable models for different field scenarios. Additionally, model interpretability issues often arise, hindering large-scale adoption among agricultural practitioners. This systematic literature review addresses these challenges and explores recent trends in optimized CNN development for plant leaf feature extraction. Through PRISMA methodology, 26 peer-reviewed studies from 2018-2024 were analyzed from Scopus Q1-Q4 journals. Key findings include the effectiveness of data augmentation techniques (improving dataset diversity by 40-60%), transfer learning approaches (reducing training time by 50-70%), and hybrid model integration (achieving 85-95% accuracy rates). Architecture improvements and optimization algorithms help overcome computational constraints, with lightweight models reducing processing time by 30-50% while maintaining 90%+ accuracy. This study provides comprehensive guidance for researchers and practitioners in developing more adaptive, accurate, and efficient plant disease detection solutions, ultimately improving agricultural yields and global food security.
Why it matches plant phenotyping methods植物葉の画像から病害状態を推定するCNN手法を体系的にレビューしており、画像取得・特徴抽出・モデル最適化が中心的な方法論的内容である。
abstractThis systematic literature review addresses these challenges and explores recent trends in optimized CNN development for plant leaf feature extraction.
Plant diseases are becoming more prevalent, which poses a significant threat to global agricultural profitability and necessitates the development of reliable and effective disease detection technologies. This work employs machine learning (ML) techniques to provide a comprehensive evaluation of prior research on plant leaf disease identification, highlighting the benefits, drawbacks, and practical applications of the various approaches used in the last several studies. The study focuses on a variety of machine learning techniques, including Support Vector Machines (SVM), Decision Trees, Random Forest, K-Nearest Neighbors (KNN), and Naïve Bayes classifiers, which have been widely used for plant disease prediction and classification. Applying these ML algorithms to a range of crop categories, our research shows that plant leaf diseases can be reliably identified and categorized. The study also examines the difficulties and potential for the future in this area, emphasizing the significance of creating complex, real-time monitoring systems to increase the precision of disease detection and promote sustainable agricultural productivity.
Why it matches plant phenotyping methods植物葉の病害を画像等から識別・分類する機械学習手法を比較・評価するレビューであり、病害状態のフェノタイピング手法が中心です。
abstractThis work employs machine learning (ML) techniques to provide a comprehensive evaluation of prior research on plant leaf disease identification
Tomato plants frequently be afflicted by diseases that may damage plants and decrease farmers’ earnings. finding these illnesse s early could be very vital for coping with them that affect tomato plants, like Yellow Leaf Curl Virus, Leaf mildew , late Blight, Early Blight, Septorial Spot, Bacterial Spot, goal Spot, Mosaic Virus, healthful, spotted Spider Mite, Powdery mould .We use deep getting to know strategies, especially a combination of EfficientNet-B0 with VGG-16, EfficientNet-B0 with CNN and VGG-16 with CNN, to investigate images of tomato leaves and decide if they may be healthful or diseased. The model learns to spot the specific signs of each disease, ensuring accurate detection. The system also suggests the best pesticides for treatment. By providing both disease identification and pesticide recommendations, this system helps farmers make better decisions to protect their crops, improve plant health and increase yield. This helps farmers grow healthier crops and increase food production in a sustainable way.
Why it matches plant phenotyping methodsトマト葉の画像から健全・罹病状態や病徴を分類する手法が中心であり、植物病害状態の画像ベース表現型計測に該当する。タイトル上はレビューで、手法の整理・評価を主題としている。
titleTomato Plant Leaf Disease Classification using Deep Learning: A Review
Plant diseases represent a critical global threat to food security, necessitating accurate and timely detection for sustainable agriculture. This systematic synthesis evaluates recent advancements in deep learning (DL) for plant leaf disease detection, analyzing 10 peer-reviewed studies published between 2021 and 2025. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, this review systematically examines Convolutional Neural Network (CNN)-based architectures, lightweight models (MobileNet, EfficientNet), and the integration of Explainable AI (XAI) to analyze the inherent trade-offs among efficiency, accuracy, and interpretability. Key findings indicate that while modern DL models achieve high classification accuracy ($\geqslant 97 \%$), practical deployment is significantly hindered by limited generalization across diverse field conditions and a critical lack of integrated XAI within lightweight hybrid architectures. This study provides a structured, cross-metric analysis to guide the development of next-generation DL models that are simultaneously efficient, accurate, and interpretable for realworld agricultural applications.
Why it matches plant phenotyping methods植物葉の病害状態を画像から検出する深層学習手法を体系的に比較・分析したレビューであり、病害表現型の取得・推定方法が中心です。
abstractThis systematic synthesis evaluates recent advancements in deep learning (DL) for plant leaf disease detection, analyzing 10 peer-reviewed studies published between 2021 and 2025.
Ensuring plant health and crop quality is vital for sustainable modern agriculture. Conventional detection methods for stress markers, contaminants, and pathogens are often constrained by labor-intensive procedures, bulky equipment, and reliance on centralized facilities, limiting real-time field monitoring. Surface-enhanced Raman scattering (SERS) has emerged as a promising solution, providing rapid, ultrasensitive, and non-destructive analysis across plant, soil, and water matrices. This review outlines the fundamental SERS mechanisms and strategies that boost sensing performance, and surveys recent advances in monitoring throughout the cultivation cycle, covering plant stress markers, metabolites, contaminants, and plant pathogens under realistic agricultural conditions. Emphasis is placed on substrate architecture (hot-spot control, composites/heterostructures, functionalization, flexible formats), enhancement mechanisms, and analytical performance (typical enhancement factor (EF), limit of detection (LOD), limit of quantitation (LOQ), and relative standard deviation (RSD) ranges). Persistent challenges, including substrate reproducibility, matrix interference, quantitative calibration, and scalable fabrication for field deployment, are evaluated alongside emerging solutions, including matrix-aware calibration (with ratiometric readout), fluorescence-robust preprocessing, and durable, large-area platforms. We close with practical considerations for durability and cost and with future perspectives toward next-generation, field-ready SERS tools for proactive plant-health management and crop-quality assurance.
Why it matches plant phenotyping methods植物の健康状態やストレス指標を測定するSERSセンシング手法を中心に、基板設計、分析性能、校正、再現性、フィールド展開上の課題を体系的にレビューしており、植物フェノタイピング手法のレビューに該当する。
abstractThis review outlines the fundamental SERS mechanisms and strategies that boost sensing performance, and surveys recent advances in monitoring throughout the cultivation cycle
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 6 Sept 2026
Fruit agriculture is undergoing a profound transformation driven by multi-omics, high-throughput phenotyping, and machine learning-driven bioinformatics. However, we demonstrate that this technological revolution has paradoxically created a 'valley of death' where most of genomic discoveries fail to reach farmers' fields. While we can now identify beneficial alleles in days and edit genomes in weeks, it still takes 10 years and 14,5 million euros to deliver a single improved cultivar to European markets - the same timeline as 30 years ago. This review exposes how data abundance has shifted, not eliminated, the fundamental bottlenecks in fruit crop improvement. We critically assess how these tools reshape genetic and metabolic diversity, emphasizing both their transformative promises and structural limitations. We highlight three persistent gaps: the challenge of integrating heterogeneous multi-omics datasets, the phenotyping bottleneck for complex traits, and the tension between innovation and biodiversity conservation. By framing fruit breeding as a "data-to-decisions" challenge, we outline the systemic changes needed for sustainable, resilient, and high-quality fruit production.
Why it matches plant phenotyping methods果樹育種におけるハイスループット表現型解析とデータ統合の課題を批判的にレビューしており、表現型解析が中心的な方法論テーマの一つである。
abstractThis review exposes how data abundance has shifted, not eliminated, the fundamental bottlenecks in fruit crop improvement.
Detecting plant diseases is essential to contemporary agriculture since it allows for early intervention to increase crop output and reduce financial losses. Recent developments in deep learning (DL) and machine learning (ML) have shown great promise for automating the detection of diseases using sensor and visual data. Convolutional neural networks (CNNs), ResNet, DenseNet, U-Net, Mask R-CNN, and YOLO are examples of state-of-the-art DL architectures that are frequently used for extracting and learning hierarchical features from leaf pictures, hyperspectral images, and other multimodal plant datasets. This paper reviews developments in the field from 2015 to 2022. Prominent datasets like PlantVillage, Agri-Vision, and PlantDoc have made it easier to compare and test different models. Using a hybrid convolutional backbone based on EfficientNet-B7 to strike a compromise between high representational capacity and computational economy, we offer a repeatable framework that combines many cutting-edge methods for better illness detection and classification. Multiscale dilated convolutions are used to capture multiscale disease patterns, enhancing feature representations without adding more computational overhead, and adaptive segmentation mechanisms allow precise lesion localization for region-level analysis that supports severity assessment and classification. The framework emphasizes repeatability and practical application for research and industrial usage, and it is accompanied by comprehensive methodological explanations, algorithm pseudocode, and illustrated diagrams and flowcharts. In addition, the paper addresses common issues in plant disease detection, such as the lack of labeled datasets, inter-domain variability, class imbalance, and hardware constraints for real-time deployment. It also discusses mitigation strategies, such as transfer learning from pre-trained models, generative adversarial network (GAN)-based data augmentation, and model compression techniques for optimal edge deployment. In order to direct future research and real-world application, evaluation measures, performance analyses, and robustness concerns are also included. Overall, this survey and suggested methodology offer a thorough overview of current developments and solutions in ML- and DL-based plant disease detection. They show how integrating hybrid convolutional architectures, multiscale dilations, and adaptive segmentation can improve detection accuracy while addressing practical limitations, providing a scalable approach for precision agriculture and assisting researchers, agronomists, and practitioners in creating dependable, effective, and repeatable plant disease detection systems.
Why it matches plant phenotyping methods植物病害の画像認識・病斑局在化・重症度評価を扱うレビューであり、植物の病害状態を画像から抽出する方法論が中心です。
abstractThis paper reviews developments in the field from 2015 to 2022.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · Crossref · checked 14 Sept 2026
Accurate diagnosis of crop water demand is a core challenge in alleviating agricultural water scarcity. Traditional diagnostic methods, which rely mainly on soil moisture sensor monitoring or empirical models based on meteorological data, suffer from limitations such as insufficient spatiotemporal representativeness and an inability to reflect crop physiological status in real time, leading to an annual water waste of 10–30%. Therefore, developing technologies that enable real-time, non-destructive, and precise monitoring of crop water status is crucial. In recent years, the rapid advancement of high-throughput phenotyping technology has provided revolutionary tools to address this challenge. By integrating multi-source sensors (e.g., thermal infrared and hyperspectral imaging), multi-dimensional response characteristics of crops under water stress can be rapidly acquired. This paper systematically reviews research progress in using high-throughput phenotyping to obtain water-sensitive phenotypic traits and construct crop water demand diagnosis models. It focuses on: (1) the connotation and acquisition techniques of key water-sensitive phenotypic indicators, such as canopy temperature, spectral indices, and chlorophyll fluorescence; (2) the advantages, limitations, and fusion strategies of multi-platform data acquisition systems, including unmanned aerial vehicles (UAVs), ground mobile platforms, and satellite remote sensing; and (3) the construction methods, performance evaluation, and practical application cases of diagnostic models based on machine learning (e.g., Random Forest, XGBoost), deep learning (e.g., CNN, LSTM), and mechanism-coupled models. The innovation of this review lies in its systematic integration of the entire technological chain—"phenotyping acquisition → model construction → decision-making"—while identifying current research challenges, including field environmental complexity, model generalization capability, data barriers, and interpretability. Future development pathways are proposed, focusing on low-cost sensing, explainable AI, multi-source data fusion, and cloud-edge collaborative decision systems. This review aims to provide a systematic theoretical and practical reference for water management in precision irrigation and smart agriculture.
Why it matches plant phenotyping methods作物の水状態に関する表現型形質の取得技術と診断モデルを体系的にレビューしており、植物フェノタイピング手法が中心である。
abstractThis paper systematically reviews research progress in using high-throughput phenotyping to obtain water-sensitive phenotypic traits and construct crop water demand diagnosis models.
Field / plotMultimodalRootWhole plant / canopy / plot / fieldCountingObject detectionStress / disease detectionGrowth / time-series analysisGrowth / development / phenologyRoot system architecture
• Presents a full-process review of image-based high-throughput plant phenotyping (HTPP). • Covers recent advances in platforms, sensors, deep learning, and field-level applications. • Highlights emerging methods like Promptable models, Digital Twins, and weak supervision. • Discusses deployment challenges including data scarcity and model generalization. • Proposes future directions: multimodal fusion, uncertainty modeling, and lightweight design. With the rapid global population growth and increasing challenges in sustainable agriculture, high-throughput plant phenotyping (HTPP) has become a vital tool for advancing crop breeding and precision agriculture. This review provides a comprehensive overview of recent technological trends in image-based HTPP, focusing on the integration of advanced sensors, automated phenotyping platforms, and deep learning techniques. We summarize the evolution of imaging modalities, including 2D, 2.5D, and 3D sensors, and their respective applications in phenotype acquisition. We then examine the progress of deep learning-based models in core phenotyping tasks such as stress and disease detection, growth monitoring, organ counting, root system analysis, and postharvest quality assessment. Special attention is given to the emergence of Transformer architectures, multimodal fusion strategies, weakly supervised learning, and prompt-based foundation models. Despite significant advancements, current HTPP systems still face several challenges, including high costs, limited generalization in open-field conditions, and the need for large-scale annotated datasets. To address these, we discuss potential solutions such as transfer learning, synthetic data generation via digital twins, lightweight deployment for edge devices, and uncertainty estimation for model interpretability. By highlighting key developments and open problems, this review aims to guide future research toward scalable, robust, and intelligent plant phenotyping systems that can operate reliably in real-world agricultural environments.
Why it matches plant phenotyping methods画像ベース高スループット植物フェノタイピングのセンサー、プラットフォーム、画像解析技術を包括的にレビューしており、方法論が中心です。
abstractPresents a full-process review of image-based high-throughput plant phenotyping (HTPP).
Existing tasks such as fruit growth monitoring, harvesting, and quality sorting still suffer from low precision and insufficient automation. 3D reconstruction technology can accurately capture the external characteristics of fruits and shows great potential for enhancing automated fruit detection and processing. This paper, guided by two core application needs in the fruit industry: real-time online sensing and offline high-precision analysis, provides a detailed overview of research progress in 3D reconstruction technology for fruits. It first introduces the principles, workflows, and advantages and limitations of classical 3D reconstruction methods. Then, it focuses on the basic framework of learning-based 3D reconstruction approaches, their improvement directions, and their applications in fruits and other agricultural products. In addition, the challenges encountered in fruit 3D reconstruction, such as occlusion and complex lighting conditions, are summarized, along with potential solutions. Finally, future research directions are discussed. This review serves as a valuable reference for promoting the integration of computer vision and agricultural intelligence and advancing the fruit industry chain’s digital and intelligent transformation.
Why it matches plant phenotyping methods果実の外部形質を取得する3D再構成手法を中心に、原理・ワークフロー・限界・応用・課題を体系的にレビューしており、植物フェノタイピング手法のレビューに該当する。
titleProcess, challenges and solutions of fruit 3D reconstruction: A review
Plant phenotyping relevance match · UnverifiedCrossref · OpenAlex · Europe PMC · checked 15 Sept 2026
Plant phenotyping plays a pivotal role in understanding plant traits and their interactions with the environment, making it crucial for advancing precision agriculture and crop improvement. 3D reconstruction technologies have emerged as powerful tools for capturing detailed plant morphology and structure, offering significant potential for accurate and automated phenotyping. This paper provides a comprehensive review of the 3D reconstruction techniques for plant phenotyping, covering classical reconstruction methods, emerging Neural Radiance Fields (NeRF), and the novel 3D Gaussian Splatting (3DGS) approach. Classical methods, which often rely on high-resolution sensors, are widely adopted due to their simplicity and flexibility in representing plant structures. However, they face challenges such as data density, noise, and scalability. NeRF, a recent advancement, enables high-quality, photorealistic 3D reconstructions from sparse viewpoints, but its computational cost and applicability in outdoor environments remain areas of active research. The emerging 3DGS technique introduces a new paradigm in reconstructing plant structures by representing geometry through Gaussian primitives, offering potential benefits in both efficiency and scalability. We review the methodologies, applications, and performance of these approaches in plant phenotyping and discuss their respective strengths, limitations, and future prospects (https://github.com/JiajiaLi04/3D-Reconstruction-Plants). Through this review, we aim to provide insights into how these diverse 3D reconstruction techniques can be effectively leveraged for automated and high-throughput plant phenotyping, contributing to the next generation of agricultural technology.
Why it matches plant phenotyping methods植物フェノタイピング向け3D再構成手法を体系的にレビューし、方法論・応用・性能を扱うことが中心であるため。
abstractThis paper provides a comprehensive review of the 3D reconstruction techniques for plant phenotyping, covering classical reconstruction methods, emerging Neural Radiance Fields (NeRF), and the novel 3D Gaussian Splatting (3DGS) approach.
MultimodalLiDAR / point cloudAnnotation / quality controlClassificationObject detectionCalibration / preprocessingSegmentationTracking
Plant phenomics, the comprehensive study of plant phenotypes, has gained prominence as a vital tool for understanding the intricate relationships between genotypes and the environment. Image-based plant phenomics has progressed rapidly, and three-dimensional (3D) phenotyping is a valuable extension of traditional 2D phenomics. However, the increased data dimensionality poses challenges to feature extraction and phenotyping. In recent decades, deep learning has led to remarkable progress in revolutionizing 3D phenotyping. Therefore, this review highlights the importance of using deep learning in 3D plant phenomics. It systematically overviews the capabilities of deep learning for 3D computer vision, covering 3D representation, classification, detection and tracking, semantic segmentation, instance segmentation, and generation. Additionally, deep learning techniques for 3D point preprocessing (e.g., annotation, downsampling, and dataset organization) and various plant phenotyping tasks are discussed. Finally, the challenges and perspectives associated with deep learning in 3D plant phenomics are summarized, including (1) benchmark dataset construction by using synthetic datasets and methods such as generative artificial intelligence and unsupervised or weakly supervised learning; (2) accurate and efficient 3D point cloud analysis by leveraging multitask learning, lightweight models, and self-supervised learning; and (3) deep learning for 3D plant phenomics by exploring interpretability, extensibility, and multimodal data utilization. The exploration of deep learning in 3D plant phenomics is poised to spur breakthroughs in a new dimension of plant science.
Why it matches plant phenotyping methods3D植物フェノミクスにおける深層学習手法を体系的にレビューしており、植物形質の抽出・推定手法が中心である。
abstractTherefore, this review highlights the importance of using deep learning in 3D plant phenomics.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Dataset · publicThe dataset can be downloaded from https://github.com/Jinlab-AiPhenomics/Mazie3D.Open asset ↗Jinlab-AiPhenomics/Mazie3Dhtml-lines:332-336Plant phenotyping relevance match · UnverifiedCrossref · checked 14 Sept 2026
Lignocellulosic biomass (LB), which encompasses various plant samples, requires thorough characterization to optimize its use as a carbon resource. Chemical imaging simultaneously provides chemical and spatial information, offering significant benefits for LB analysis. This review presents an overview of the most advanced techniques for achieving this goal. By combining spectrometry and microscopy, microspectroscopy enables chemical imaging using various irradiation sources (IR, Raman, fluorescence, among others), allowing for the quantitative mapping of key LB components such as lignins, cellulose, and hemicelluloses. Mass Spectrometry Imaging (MSI) generates a mass spectrum for each spot of a sample thereby creating a chemical image pixel-by-pixel. MSI techniques like Matrix-Assisted Laser Desorption/Ionization (MALDI), down to 2-5 μm spatial resolution, and Secondary Ion Mass Spectrometry (SIMS), down to 300 nm for molecular analysis, effectively map small molecules in LB. In contrast, Desorption ElectroSpray Ionization (DESI) has been applied to plant extracts but remains largely unexplored for LB applications. Nuclear Magnetic Resonance (NMR) provides insight into various LB properties too. Solid-state NMR (ssNMR) and Dynamic Nuclear Polarization (DNP) help elucidate the structure of LB, sometimes aided by 3D atomistic modeling, whereas micro-Magnetic Resonance Imaging (micro-MRI) and Time-Domain (TD-NMR) probe the impact of water on LB properties.
Why it matches plant phenotyping methods植物バイオマスの化学成分を空間的に定量・マッピングする化学イメージング手法のレビューであり、植物試料の観察・形質抽出法が中心である。
abstractThis review presents an overview of the most advanced techniques for achieving this goal.
Plants in natural environments often face unpredictable, co-occurring stresses, such as heatwaves and droughts, a trend that is intensifying with climate change. Reflectance spectroscopy, a valuable tool for monitoring plant health, has been widely used to detect single stress, but its potential for assessing combined stresses remains underexplored. While several reviews have explored plant molecular and physiological responses to combined stress, none has discussed the role of spectroscopy in this context. This review addresses this gap by synthesizing existing findings on plant spectral responses to two common stress combinations: drought + nitrogen deficiency and drought + heat stress. Although a limited number of studies exist, they reveal that plant spectral responses to combined stresses are often unique compared with individual stresses. These results point to three potential pathways by which spectroscopy can enhance plant resilience under combined stress: generating new hypotheses, facilitating the selection of broad-spectrum stress-tolerant genotypes, and improving stress detection for precision management. This review also suggests that spectral responses to combined stresses differ from individual stresses across spectral regions, plant species, scale of spectral sensing, and possibly other factors not yet considered here. To advance reflectance spectroscopy as a tool for studying combined stress, future research should prioritize enhanced experimental designs, standardized data presentation, integrated modeling, and sensor synergies.
Why it matches plant phenotyping methods植物の複合ストレスを反射分光で評価する方法を中心に既存研究を統合したレビューであり、植物状態のセンシング手法が主題である。
abstractReflectance spectroscopy, a valuable tool for monitoring plant health, has been widely used to detect single stress, but its potential for assessing combined stresses remains underexplored.
Plant phenotyping relevance match · UnverifiedCrossref · OpenAlex · Europe PMC · checked 6 Sept 2026
As with many fields of science, plant science and agriculture have seen a rapid adoption of deep learning in recent years. The present moment is significant as it marks one decade since the first applications of deep learning began to appear in the literature on plant phenotyping. In this short time, a new research community was founded and new connections between computer vision and biology were established. In this letter, we reflect on this critical period of time from the inception of the field to where it stands today.
Why it matches plant phenotyping methods植物フェノタイピングにおける深層学習の発展を総括する方法論的レビューであり、対象分野の技術的進展が中心です。
titleDeep learning in plant phenotyping: the first ten years
As an important part of terrestrial ecosystems, the growth and development of plants were regulated by a variety of environmental factors. The rapid development of precision agriculture had put forward higher requirements for real-time monitoring of crop growth environments. Although traditional sensing technology could provide environmental data, it had limitations such as strong invasiveness, large dimensional rigidity, and insufficient long-term monitoring capabilities. The review aimed to systematically review the progress and applications of plant flexible sensors in plant science, highlighting their potential to overcome the limitations of traditional sensors through non-invasive, real-time, and dynamic monitoring of plant physiological and environmental parameters. The review focused on the material systems, fabrication processes, and functional applications of plant flexible sensors. Special attention was given to the roles of conductive polymers, carbon-based materials, and biocompatible substrates in sensor development. Plant flexible sensors, due to their mechanical compliance, functional sensitivity, and energy-efficient operation, offered significant advantages over traditional biosensors. These included in-situ monitoring, long-term operational stability, multi-parameter sensing capabilities, and enhanced adaptability to complex environmental conditions. The reviewed literature demonstrated that plant flexible sensors provided effective and precise monitoring solutions across a wide range of plant physiological processes and environmental conditions. The review provided theoretical guidance and technical reference for the design and application of plant flexible sensors in future agricultural research. The insights gained from this review could facilitate the development of smart agriculture systems, promote advances in plant phenomics, and support sustainable ecological monitoring efforts.
Why it matches plant phenotyping methods植物フレキシブルセンサーによる生理状態の非侵襲・リアルタイム計測を中心に、材料、作製、機能応用を体系的にレビューしており、植物フェノタイピング手法のレビューとして適格。
abstractThe review aimed to systematically review the progress and applications of plant flexible sensors in plant science, highlighting their potential to overcome the limitations of traditional sensors through non-invasive, real-time, and dynamic monitoring of plant physiological and environmental parameters.
This paper presents a systematic and comprehensive review of deep learning (DL) methodologies used in precision agriculture (PA). It focuses on three critical application areas in particular: plant classification, plant disease detection, and weed detection. The study covers 93 peer-reviewed papers published between 2020 and 2025 and indexed in the SCI and SCI-Expanded indexed WoS database. Of these, 68 studies addressed disease detection, 13 focused on plant classification, and 12 examined weed detection strategies. The review describes a wide range of DL architectures, including Convolutional Neural Networks (CNNs), Residual Networks (ResNet), You Only Look Once (YOLO), Image Transformers (ViT), and various hybrid frameworks. A large number of models demonstrated exceptional performance with classification accuracies reaching up to 99.64% and precision and sensitivity values exceeding 98%. Studies have evaluated a wide range of datasets such as PlantVillage, COCO, and privately acquired RGB/UAV imagery, and a variety of sensor platforms such as drones, smartphones, hyperspectral, and LiDAR systems. Moreover, transfer learning and ensemble learning approaches have been frequently adopted to enhance generalization capabilities and model robustness. The integration of DL models with advanced technologies such as unmanned aerial vehicles (UAVs), unmanned ground robots (UGRs), depth-sensing cameras, and mobile-based platforms facilitates automation in agricultural monitoring, disease diagnosis, and yield prediction. This review not only consolidates the current technological developments, but also analyzes the emerging trends, methodological gaps, and possible directions for the advancement of sustainable, data-driven agricultural systems using artificial intelligence.
Why it matches plant phenotyping methods植物病害検出を含む画像・センサー・深層学習手法を体系的にレビューし、データセット、モデル、センサープラットフォーム、性能を比較しているため、方法論レビューとして中心的である。
abstractThis paper presents a systematic and comprehensive review of deep learning (DL) methodologies used in precision agriculture (PA).
Large-scale rainfed cropping systems (broadacre agriculture) face intensifying climate and resource stresses that undermine yield stability and farm livelihoods. Remote sensing (RS) offers critical tools for improving resilience by monitoring crop performance—productivity, phenology, and environmental stress—across large areas and timeframes. This review aims to synthesize methodological advances over the past two decades in applying RS for broadacre crop monitoring and to identify key challenges and integration opportunities. Peer-reviewed studies across diverse crops and regions were systematically examined to evaluate the strengths, limitations, and emerging trends across the three RS application themes. The review finds that (1) RS enables spatially explicit yield estimation from regional to paddock scales, with vegetation indices (VIs) and phenology-adjusted metrics closely correlated with yield. (2) Time-series analyses of RS data effectively capture phenological transitions critical for forecasting, supported by advances in curve fitting, sensor fusion, and machine learning. (3) Thermal and multispectral indices support the early detection of abiotic (drought, heat, salinity) and biotic (pests, disease) stresses, though specificity remains limited. Across themes, methodological silos and sensor integration barriers hinder holistic application. Emerging approaches, such as multi-sensor/scale fusion, RS–crop model data assimilation, and operational and big data integration, provide promising pathways toward resilience-focused decision support. Future research should define quantifiable resilience metrics, cross-theme predictive integration, and accessible tools to guide climate adaptation.
Why it matches plant phenotyping methods作物の生産性、フェノロジー、環境ストレスをリモートセンシングで推定する方法論的レビューであり、植物状態の取得・推定手法が中心である。
abstractThis review aims to synthesize methodological advances over the past two decades in applying RS for broadacre crop monitoring
Monitoring of crops, is considered a crucial component of today's agriculture, which allows for early identification of pests, diseases, and stress, as well as resource optimization and the promotion of sustainable practices. Digital image processing (DIP) techniques, particularly those applied to satellite and drone photos, play an important role in soil moisture retrieval, crop health assessment, yield prediction, and insect identification. These technologies enable the deployment of precision agriculture, which leads to increased production, lower costs, and more ecologically friendly agricultural practices. Traditional manual approaches, on the other hand, are inefficient, time-consuming, and susceptible to inconsistencies, whereas DIP-based crop monitoring systems provide a more accurate, efficient, and scalable alternative. In this paper, an exhaustive review of DIP-based crop monitoring techniques using satellite and drone images, along with a bibliometric study of articles published between 2015 and 2024 and the growing impact of precision agriculture, internet of things (IoT), and machine learning on global agricultural practices, revealing key trends and influential research contributions from various regions, has been conducted. It is observed that in the future, precision agriculture systems using explainable artificial intelligence (AI) can enhance crop management by accurately identifying plant stress and infections through visualization maps, leading to smarter, data-driven farming decisions.
Why it matches plant phenotyping methods衛星・ドローン画像による作物状態・ストレス・感染・収量などの抽出手法を対象とするレビューであり、画像処理手法の整理が中心。ただし土壌水分や害虫同定など非フェノタイピング用途も含む。
titleA BIBLIOMETRIC REVIEW OF DIGITAL IMAGE PROCESSING APPROACHES FOR CROP MONITORING IN PRECISION AGRICULTURE
Accuracy and real-time performance are two major challenges in monitoring plant growth, detecting crops, and recognizing diseases in complex real-world agricultural environments. Growing environments present significant difficulties for object detection due to factors such as variable weather and lighting conditions, shooting distances, varying degrees of occlusion, and diverse morphological characteristics. The YOLO series of models, especially the prominent YOLOv8, are state-of-the-art models for object recognition that have revolutionized the field by achieving an optimal balance between speed and accuracy. Since YOLOv8 appeared two and a half years ago, many improvement measures or modifications have been proposed in the literature for different detection tasks and applications. This paper systematically reviews these Improved YOLOv8 algorithms, focusing on object detection in plants (e.g., crops, diseases, and growth stages), to evaluate the proposed changes or improvements. Inspired by the reviewed architectures and comparative analyses, we propose a modular architecture called PLANT-YOLOv8 based on the YOLOv8 framework. The proposed modular configuration of the YOLOv8 structure is flexible, easy to implement, and extendable. Additionally, our analysis provides recommendations and potential improvements for each YOLOv8 component that could be replaced or enhanced. Lastly, we present and evaluate Improved YOLOv8 architectures from the reviewed literature to demonstrate their composition and complexity as prime examples of our modular PLANT-YOLOv8 architecture.
Why it matches plant phenotyping methods植物の成長・病害・作物を対象とする物体検出手法を体系的にレビューし、植物向けYOLOv8派生アーキテクチャを提案・評価しており、フェノタイピング手法が中心である。
abstractThis paper systematically reviews these Improved YOLOv8 algorithms, focusing on object detection in plants (e.g., crops, diseases, and growth stages), to evaluate the proposed changes or improvements.
Plant leaf diseases (PLDs) can continue to be a significant problem in the agricultural sector, leading to significant losses in production and jeopardizing food security. Early detection is essential, and recent achievements in the domain of deep learning (DL) have made automated high-accuracy solutions possible. The most popular and commonly used of these is the You Only Look Once (YOLO) family of object detection models, which have been proposed to detect plant diseases in real time. This review presents a new and in-depth synthesis of YOLO-based methods, including YOLOv1 to YOLOv10 and the domain-specific variants, including CTB-YOLO (coriander), BED-YOLO (YOLOv10n), and RAG-augmented YOLOv8 (coffee). This work compares to previous surveys in that (i) it presents a structured dataset catalog containing information on size, resolution, disease classes, and limitations (such as imbalance and annotation problems); (ii) it provides comparative benchmarking analysis of performance measures (accuracy, precision, recall, F1-score, mean Average Precision, and frames per second) across versions of YOLO to illustrate trade-offs between speed and accuracy; and (iii) it gives forward-looking discussion on how (ii) open challenges and (iii) future research directions, including lightweight YOLO models to run on mobile. This review presents a summative reference and a new contribution to the progress of the YOLO-based PLD detection approach to sustainable agriculture.
Why it matches plant phenotyping methods植物葉の病害状態を画像から検出・分類するYOLO手法を中心に、データセットと性能を比較するレビューであり、植物表現型計測法のレビューとして適格。
abstractThis review presents a new and in-depth synthesis of YOLO-based methods, including YOLOv1 to YOLOv10 and the domain-specific variants
High-throughput plant phenotyping plays an important role in plant breeding, identifying superior genotypes in a fast and accurate manner. Consequently, researchers are seeking new image-based plant phenotyping strategies to enhance phenotyping efficiency. RGB (red, green, blue) sensors and their applications offer a cost-effective and accessible approach while maintaining the advantageous characteristics of high-throughput phenotyping technologies. Various RGB image-based indices are now available to measure diverse phenotypic traits accurately. Despite a wide range of advantages, some limitations reduce the accuracy of the method. We systematically reviewed scientific articles published between 2000 and 2024 to ascertain the significance, available knowledge, and gaps in the domain of RGB image-based plant phenotyping. This review paper provides a comprehensive survey on the significance of current RGB imaging technologies and their applications in plant phenotyping, emphasizing their advantages and limitations. RGB image-based plant phenotyping demonstrates considerable accuracy in the estimation of morphological traits. However, this technique gives significantly lower accuracy for physiological traits compared with other sensors. Furthermore, variation of light conditions, varied backgrounds, and overlapping are major drawbacks of this technique. Future studies should focus on the development of precise image acquisition systems, advanced image processing techniques (including image segmentation), the identification of novel color parameters, the implementation of robust artificial intelligence and machine learning models, and the integration of complementary sensor technologies to address existing challenges.
Why it matches plant phenotyping methodsRGB画像による植物表現型計測を対象とし、既存研究の体系的レビュー、精度、限界、画像取得・処理技術を扱うため、方法論レビューとして中心的です。
titleApplication of RGB-Imaging techniques for high-throughput plant phenotyping- A Review
High-Throughput Phenotyping (HTP) has revolutionized plant breeding in developed nations, utilizing automated gantries, advanced drones, and spectral sensors to capture genomic performance with unprecedented precision. However, the "phenotyping gap" persists: while the Global North accelerates genetic gain via "Big Data," smallholder farmers in the Global South remain disconnected from these advancements, often growing varieties ill-suited to their hyper-local microclimates. This review protocol, "Translating High-Throughput Breeding into Frugal Field Solutions," explores the democratization of phenomics through the concept of "frugal innovation." We analyze the shift from expensive centralized platforms to decentralized data collection tools based on smartphones (e.g., Field Book, OneKK) and low-cost remote sensing (e.g., nanosatellites). By leveraging the ubiquity of mobile technology, we can transform smallholder fields into a distributed network of research stations, enabling "Citizen Science" based breeding. This document will detail how frugal tools can increase selection intensity and accuracy —two pillars of the Breeder’s Equation—in resource-constrained environments, ultimately bridging the gap between elite genomic research and farm-level reality.
Why it matches plant phenotyping methods植物フェノタイピングの民主化を目的に、スマートフォンツールや低コストリモートセンシングによる分散型データ収集・育種フェノミクスを検討するレビューであり、方法論が中心です。
abstractThis review protocol, "Translating High-Throughput Breeding into Frugal Field Solutions," explores the democratization of phenomics through the concept of "frugal innovation."
High-Throughput Phenotyping (HTP) has revolutionized plant breeding in developed nations, utilizing automated gantries, advanced drones, and spectral sensors to capture genomic performance with unprecedented precision. However, the "phenotyping gap" persists: while the Global North accelerates genetic gain via "Big Data," smallholder farmers in the Global South remain disconnected from these advancements, often growing varieties ill-suited to their hyper-local microclimates. This review protocol, "Translating High-Throughput Breeding into Frugal Field Solutions," explores the democratization of phenomics through the concept of "frugal innovation." We analyze the shift from expensive centralized platforms to decentralized data collection tools based on smartphones (e.g., Field Book, OneKK) and low-cost remote sensing (e.g., nanosatellites). By leveraging the ubiquity of mobile technology, we can transform smallholder fields into a distributed network of research stations, enabling "Citizen Science" based breeding. This document will detail how frugal tools can increase selection intensity and accuracy —two pillars of the Breeder’s Equation—in resource-constrained environments, ultimately bridging the gap between elite genomic research and farm-level reality.
Why it matches plant phenotyping methods植物フェノタイピングの低コストなデータ収集ツールとプラットフォームの普及・設計を中心に扱うレビュー・プロトコルであり、方法論的役割が明確です。
abstractThis review protocol, "Translating High-Throughput Breeding into Frugal Field Solutions," explores the democratization of phenomics through the concept of "frugal innovation."
LiDAR / point cloudThermalFruitGrowth / time-series analysisGrowth / development / phenologyFruit / seed / panicle traitsPlant / canopy temperature
Temperature plays a vital role in plant metabolism, and effective crop temperature appears to be influenced by variables related to climate change. While extreme weather events are widely discussed, the effects of moderate temperature changes pose consistent yet underexplored challenges for farmers. The “growing degree days” (GDD) also termed “heat unit”, is the most widely used approach in agricultural and ecological studies to quantify the relationship between temperature and plant development. This review provides a comprehensive examination of GDD methodology as applied to horticultural crop production, specifically from initial fruit development to fruit maturity, and postharvest. It is the first integrated synthesis of the conceptual evolution, methodological refinement, and broad application of GDD, thereby highlighting the need to optimize GDD approaches in light of emerging technological tools. While the GDD model is valuable for predicting crop development based on heat accumulation, it has limitations in capturing the effects of other environmental factors. Additionally, air temperature may not provide precise data on each plant organ. Recent advances in remote sensing, such as the integration of thermal imaging, RGB cameras, and lidar have enabled the measurement of spatially resolved temperature distribution within crop canopies, including fruit surface temperature. Recent advances, highlighted in the literature, suggest that integrating sensor innovations with machine learning approaches holds high potential for improving the precision of modeling temperature-dependent growth responses and their interactions with other environmental variables. By addressing these challenges and expanding its applications, GDD can continue to serve as an essential tool in promoting sustainable horticultural practices and adapting to global warming.
Why it matches plant phenotyping methodsGDDを用いて温度から作物の発育段階・成熟を推定する方法論を中心にレビューしており、植物状態の計算的な表現型推定に該当する。
abstractThis review provides a comprehensive examination of GDD methodology as applied to horticultural crop production, specifically from initial fruit development to fruit maturity, and postharvest.
Maize (Zea mays L), a cultigen derived from domesticated teosinte, is the queen of cereals because of its broad environmental adaptability and high genetic yield potential. It has major economic importance as both raw corn and as feedstock for numerous value-added products, with each kernel type serving multiple agri-industries. Driven by technological advances and expanded resources, breeders and researchers increasingly prioritize maize breeding and development. This paper systematically reviews the last decade of image analysis advancements in maize, focusing on techniques adopted for phenotyping, plant classification and disease identification. We examine why image-based phenotyping is necessary for modern agriculture, why maize is a primary model for image analysis and which maize traits remain underexplored. We summarize how machine learning and deep learning simplify image processing and feature extraction; identify the main challenges researchers encounter when adopting these methods and propose potential solutions. Our review shows that integrating advanced imaging, computer vision and AI have enabled earlier stress detection, improved yield prediction and more efficient trait mapping in maize. Continued innovation in scalability, robustness and interpretability is essential to translate these technological advances into real-world agricultural impact.
Why it matches plant phenotyping methodsトウモロコシの画像解析による表現型計測手法を体系的にレビューしており、フェノタイピング手法が中心である。
abstractThis paper systematically reviews the last decade of image analysis advancements in maize, focusing on techniques adopted for phenotyping, plant classification and disease identification.
Non-destructive testing (NDT) methods are playing a crucial role in modern agriculture by providing efficient, rapid, and non-invasive means of evaluating agricultural materials. This shift from traditional, often destructive, testing methods is driven by the need for better quality control, improved food safety, and the demands of intelligent and precise agriculture Polarization spectroscopy analysis (PSA) has emerged as an advanced, non-destructive testing method of growing importance in agricultural engineering. By integrating polarization characteristics with spectral data, PSA enables the detailed analysis of various agricultural products and processes.This review provides a systematic overview of the principles and key parameters of polarimetry. Furthermore, it highlights a wide range of PSA applications in agricultural materials, such as crop health assessment, pest detection, chlorophyll estimation, and the evaluation of water, nitrogen, phosphorus, and potassium content. In addition, it sheds light on further applications, including non-destructive testing of seed health and agricultural product quality, soil moisture and pollution monitoring, underwater and nighttime environmental imaging, and integration with hyperspectral and multispectral technologies.Polarization spectroscopy is an analytical technology capable of revealing physical structural information unresolved by traditional spectroscopy, especially in complex environments where it demonstrates greater resistance to interference. With its ability to monitor plant nutrition, predict seed germination, assess fruit and vegetable quality, and detect early pests and diseases, this technology holds great promise for precision agriculture. Future efforts should optimize data fusion, build efficient models, miniaturize intelligent equipment, and enhance the real-time performance and adaptability of non-destructive testing to support smart agriculture..
Why it matches plant phenotyping methods偏光分光法を農業材料へ適用するレビューであり、作物健全性、クロロフィル、栄養、発芽、病害虫など植物形質・状態の非破壊推定を主要な応用として扱っているため、植物フェノタイピング手法レビューに該当する。
abstractThis review provides a systematic overview of the principles and key parameters of polarimetry.