An integrative principal component analysis-artificial neural network (PCA-ANN) framework was developed to characterize ecotypic variation among parsley landraces and predict quality-related traits in medicinal and aromatic plants. Fifteen Iranian parsley landraces collected from diverse agro-ecological regions, together with two commercial cultivars as reference genotypes, were analyzed to establish predictive links between easily measurable morphological traits and key biochemical, mineral, and essential-oil (EO) characteristics. Twenty-one independent morphological variables were recorded and used as model inputs. To minimize redundancy and multicollinearity, PCA was applied exclusively to the morphological dataset, reducing it to a smaller set of uncorrelated components that preserved most of the variance. These components served as input features for optimized ANN architectures developed to predict antioxidant properties, EO yield and composition, and mineral nutrient content. The resulting PCA-ANN framework achieved strong predictive performance, with R² up to 0.94. It accurately predicted antioxidant, mineral, and compositional profiles from morphological traits alone, demonstrating the potential of morphological phenotyping as a rapid, non-destructive proxy for complex chemical analyses. This integrative modeling approach reduces reliance on time-consuming and costly procedures such as GC-MS and offers a practical decision-support tool for genotype selection, breeding, and quality evaluation in medicinal and aromatic crops. The proposed framework provides a scalable, data-driven strategy for advancing precision agriculture and sustainable management of herbal plant resources.
Why it matches plant phenotyping methods形態形質から抗酸化性、精油、ミネラルなどを推定するPCA-ANNフレームワークの開発が研究の中心であり、形態フェノタイピングを用いた非破壊的な形質推定法に該当する。
abstractAn integrative principal component analysis-artificial neural network (PCA-ANN) framework was developed to characterize ecotypic variation among parsley landraces and predict quality-related traits in medicinal and aromatic plants.
Root rot in hydroponically-grown leafy vegetables is difficult to detect via conventional manual and machine vision-based approaches as symptoms of infection are not clearly visible on the canopy at earlier stages of infection. Hence, the present study investigates the potential of using machine learning for assessing canopy information obtained from multiple imaging platforms synergistically to improve root rot detection. Herein, flat-leaf parsley seedlings were grown in an experimental hydroponic vertical farm and inoculated with Pythium irregulare and Phytophthora nicotianae . Subsequently, the seedlings were imaged via 3D, multispectral, and thermal sensors at various stages of growth to obtain twenty-six image-based plant features. Following a preliminary screening of redundant features via regression analysis, data for seventeen image features associated with morphometric, spectral, and thermal attributes was co-analyzed using supervised machine learning by Support Vector Machines (SVM). Exhaustive feature selection using different SVM kernels and maximum feature thresholds was performed to identify optimal feature subsets. It was observed that combining parameters obtained from all three imaging platforms enabled better identification of infected samples (>99%) than using a higher number of attributes from individual imaging systems. In addition, model performance was improved considerably by including temporal information during model training. Hence, it may be inferred that fusion of data from multiple imaging systems and using it with temporal information can enable better real-time high-throughput monitoring of root rot.
Why it matches plant phenotyping methods複数の画像センサーから植物形質を取得し、機械学習で根腐病症状を推定する統合的フェノタイピング手法の開発・評価が研究の中心である。
abstractthe present study investigates the potential of using machine learning for assessing canopy information obtained from multiple imaging platforms synergistically to improve root rot detection
Abstract Use of vertical farms is increasing rapidly as it enables year-round crop production, made possible by fully controlled growing environments situated within supply chains. However, intensive planting and high relative humidity make such systems ideal for the proliferation of fungal pathogens. Thus, despite the use of bio-fungicides and enhanced biosecurity measures, contamination of crops does happen, leading to extensive crop loss, necessitating the use of high-throughput monitoring for early detection of infected plants. In the present study, progression of foliar symptoms caused by Pythium irregulare -induced root rot was monitored for flat-leaf parsley grown in an experimental hydroponic vertical farming setup. Structural and spectral changes in plant canopy were recorded non-invasively at regular intervals using a 3D multispectral scanner. Five morphometric and nine spectral features were selected, and different combinations of these features were subjected to multivariate data analysis via principal component analysis to identify temporal trends for early disease detection. Combining morphometric and spectral features enabled a clear segregation of healthy and diseased plants at 4–7 days post inoculation (DPI), whereas use of only morphometric or spectral features allowed this at 7–9 DPI. Minimal datasets combining the six most effective features also resulted in effective grouping of healthy and diseased plants at 4–7 DPI. This suggests that selectively combining morphometric and spectral features can enable accurate early identification of infected plants, thus creating the scope for improving high-throughput crop monitoring in vertical farms.
Why it matches plant phenotyping methods3Dマルチスペクトルスキャナーで植物キャノピーの形態・スペクトル特徴を取得し、根腐病の症状を早期検出する手法が研究の中心であるため。
abstractStructural and spectral changes in plant canopy were recorded non-invasively at regular intervals using a 3D multispectral scanner.
Background Conventional crop protection has major drawbacks, such as developing pest and pathogen insensitivity to pesticides and low environmental compatibility. Therefore, alternative crop protection strategies are needed. One promising approach treats crops with chemical compounds that induce the primed state of enhanced defense. However, identifying priming compounds is often tedious as it requires offline sampling and analysis. High throughput screening methods for the analysis of priming-active compounds have great potential to simplify the search for such compounds. One established method to identify priming makes use of parsley cell cultures. This method relies on measurement of fluorescence of furanocoumarins in the final sample. This study demonstrates for the first time the online measurement of furanocoumarins in microtiter plates. As not all plants produce fluorescence molecules as immune response, a signal, which is not restricted to a specific plant is required, to extend online screening methods to other plant cell cultures. It was shown that the breathing activity of primed parsley cell cultures increases, compared to unprimed parsley cell cultures. The breathing activity can by monitored online. Therefore, online identification of priming-inducing compounds by recording breathing activity represents a promising, straight-forward and highly informative approach. However, so far breathing has been recorded in shake flasks which suffer from low throughput. For industrial application we here report a high-throughput, online identification method for identifying priming-inducing chemistry. Results This study describes the development of a high-throughput screening system that enables identifying and analyzing the impact of defense priming-inducing compounds in microtiter plates. This screening system relies on the breathing activity of parsley cell cultures. The validity of measuring the breathing activity in microtiter plates to drawing conclusions regarding priming-inducing activity was demonstrated. Furthermore, for the first time, the fluorescence of the priming-active reference compound salicylic acid and of furanocoumarins were simultaneously monitored online. Dose and time studies with salicylic acid-treated parsley cell suspensions revealed a wide range of possible addition times and concentrations that cause priming. The online fluorescence measuring method was further confirmed with three additional compounds with known priming-causing activity. Conclusions Determining the OTR, fluorescence of the priming-active chemical compound SA and of furanocoumarins in parsley suspension cultures in MTPs by online measurement is a powerful and high-throughput tool to study possible priming compounds. It allows an in-depth screening for priming compounds and a better understanding of the priming process induced by a given substance. Evaluation of priming phenomena via OTR should also be applicable to cell suspensions of other plant species and varieties and allow screening for priming-inducing chemical compounds in intact plants. These online fluorescence methods to measure the breathing activity, furanocoumarin and SA have the potential to accelerate the search for new priming compounds and promote priming as a promising, eco-friendly crop protection strategy.
Why it matches plant phenotyping methods植物細胞の防御プライミング状態を呼吸活性・蛍光としてオンライン測定する高スループット手法を開発し、妥当性を検証しているため、植物フェノタイピング手法が中心である。
abstractThis study demonstrates for the first time the online measurement of furanocoumarins in microtiter plates.
Background Ethylene is an important plant hormone that controls many physiological processes in plants. Conventional methods for detecting ethylene include gas chromatographs or optical mid-infrared sensors, which are expensive and, in the case of gas chromatographs, are hardly suitable for automated parallelized online measurement. Electrochemical ethylene sensors are cheap but often suffer from poor resolution, baseline drifting, and target gas oxidation. Thus, measuring ethylene at extremely low levels is challenging. Results This report demonstrates the integration of electrochemical ethylene sensors into a respiration activity monitoring system (RAMOS) that measures, in addition to the oxygen transfer rate, the ethylene transfer rate in eight parallel shake flasks. A calibration method is presented that is not prone to baseline drifting and considers target gas oxidation at the sensor. In this way, changes in ethylene transfer rate as low as 4 nmol/L/h can be resolved. In confirmatory experiments, the overall accuracy of the method was similar to that of gas chromatography-mass spectrometry (GC/MS) measurements. The RAMOS-based ethylene determination method was exemplified with parsley suspension-cultured cells that were primed for enhanced defense by pretreatment with salicylic acid, methyl jasmonate or 4-chlorosalicylic acid and challenged with the microbial pattern Pep13. Ethylene release into the headspace of the shake flask was observed upon treatment with salicylic acid and methyl jasmonate was further enhanced, in case of salicylic acid and 4-chlorosalicylic acid, upon Pep13 challenge. Conclusion A conventional RAMOS device was modified for simultaneous measurement of the ethylene transfer rate in eight parallel shake flasks at nmol/L/h resolution. For the first time electrochemical sensors are used to provide a medium-throughput method for monitoring ethylene release by plants. Currently, this can only be achieved by costly laser-based detection systems and automated gas chromatographs. The new method is particularly suitable for plant cell suspension cultures. However, the method may also be applicable to intact plants, detached leaves or other plant tissues. In addition, the general principle of the technology is likely extendable to other volatiles or gases as well, such as nitric oxide or hydrogen peroxide.
Why it matches plant phenotyping methods植物からのエチレン放出量を並列・オンライン測定するセンサー／RAMOS法の開発、校正、GC/MSとの精度比較が研究の中心であり、植物状態の生理形質を測定する方法論に該当する。
abstractThis report demonstrates the integration of electrochemical ethylene sensors into a respiration activity monitoring system (RAMOS) that measures, in addition to the oxygen transfer rate, the ethylene transfer rate in eight parallel shake flasks.