LeafScans-Orchard is a curated, multi-year RGB image dataset of orchard plant leaves designed to support research in computer vision, machine learning, and plant phenotyping. The dataset comprises 9708 high-quality leaf scans acquired during collection campaigns conducted between 2015 and 2025, covering seven orchard crop species: apple, pear, sweet cherry, sour cherry, plum, peach, and apricot. In total, the dataset includes 67 cultivar labels. All samples were acquired using flatbed scanning under controlled conditions on a uniform background, ensuring high visual consistency and minimal background variability. The original scans were captured at 1200 dpi and subsequently converted into a public release format at 300 dpi, stored as lossless TIFF images to preserve morphological and textural details. Each image corresponds to a single leaf and is organized in a hierarchical directory structure by species, cultivar, and acquisition year, accompanied by image-level metadata and aggregated species–cultivar–year counts. LeafScans-Orchard is suitable for plant species classification, cultivar recognition, leaf morphology analysis, texture analysis, and general visual feature extraction. In addition to the main release, a representative subset of 300 original 1200 dpi scans is provided to support high-resolution analyses. The dataset is particularly suited for fine-grained classification, morphology-driven analysis, and methodological studies under controlled imaging conditions.
Why it matches plant phenotyping methods果樹葉のRGBスキャン画像を収録した公開データセットで、植物フェノタイピングおよび葉形態解析を目的とする。標準化された画像取得と再利用可能なデータ構成が中心であり、フェノタイピング用データセットとして適格。
abstractLeafScans-Orchard is a curated, multi-year RGB image dataset of orchard plant leaves designed to support research in computer vision, machine learning, and plant phenotyping.
Reproduction assets foundThe paper's core asset is the LeafScans-Orchard dataset itself (9708 RGB leaf scans, 300 dpi TIFF release plus 1200 dpi subset, image-level metadata and summary counts), openly deposited on Zenodo with an explicit DOI and CC BY 4.0 license. This is a paper-specific, public, actionable phenotyping image dataset. No codeDataset · publicthe published version of the manuscript.
Funding: This research received no external funding.
Institutional Review Board Statement: Not applicable.
Informed Consent Statement: Not applicable.
Data Availability Statement: The dataset described in this article is openly available in Zenodo
as LeafScans-Orchard Dataset (v1.0.0) at https://doi.org/10.5281/zenodo.20187966 (accessed on
10 May 2026). The repository includes the 300 dpi image release, the 1200 dpi high-resolution subset,
image-level metadata, aggregated species–cultivar–year counts, and supporting documentation. The
complete archive of original 1200 dpi scans is retained locally by the authors but is not included in
the current pubOpen asset ↗Zenodo · 10.5281/zenodo.20187966pdf-raw-page:12 lines:1-46Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Plums, commonly known as Indian jujube, are economically important, valued for nutritional benefits and consumed by people from all over the world. The development of a comprehensive Plum leaf and fruit dataset is highly essential for advancing agricultural research and enabling effective disease management systems using machine learning techniques. This dataset serves as a foundational resource for machine learning based classification and bridges the gap between agricultural research and computer vision to support automated disease detection and fruit quality assessment. Researchers will be able to utilize this dataset to implement early disease detection which leads to improve crop management and supply quality and reduce the usage of chemicals. Proper utilization of this dataset can help farmers to reduce financial losses and encourage sustainable farming practices. The dataset was collected between December 2024 and February 2025 under various environmental conditions. It consists of 3,554 original images, an equal number of processed images and 18,000 augmented images generated from the original dataset. The dataset is categorized into six distinct classes: Shot Hole, Bacterial Spot, Wilted Leaf, Healthy Leaf, Unhealthy Plum, and Healthy Plum. This dataset contributes significantly to advance deep learning in agriculture enabling early disease detection and fruit quality monitoring.
Why it matches plant phenotyping methods植物の葉・果実画像から病害状態を分類するためのデータセット構築が研究の中心であり、植物病害フェノタイピング用の再利用可能な資源に該当する。
abstractThis dataset contributes significantly to advance deep learning in agriculture enabling early disease detection and fruit quality monitoring.
Reproduction assets foundThe paper is a Data in Brief describing a public Mendeley Data repository containing the authors' own plum leaf/fruit image dataset (3,554 original, processed, and 18,000 augmented images) used for plant disease classification. This is a paper-specific, publicly available image dataset with an explicit URL and DOI.Dataset · publicil Smart City, Birulia, Savar, Dhaka, Bangladesh. (Latitude: 23° 52′ 39.22" N, Longitude: 90° 19′ 12.47" E)
3.
Sharankhola, Bagerhat, Khulna, Bangladesh (Latitude: 22° 13′ 26.0" N, Longitude: 89° 48′ 20.0" E).
Data accessibility
Repository name: Mendeley Data
Data identification number: 10.17632/w7sdx55m7z.1
Direct URL to data: https://data.mendeley.com/datasets/w7sdx55m7z/1
Related research article
none
1
Value of the Data
•Open asset ↗Mendeley Data · 10.17632/w7sdx55m7z.1lines:1-52Code / dataset availability confirmedarXiv · OpenAlex · checked 13 Sept 2026
AppleCitrusMangoPeachPearPlumField / plotLiDAR / point cloudRGB / grayscaleFruit
We introduce FruitNeRF, a unified novel fruit counting framework that leverages state-of-the-art view synthesis methods to count any fruit type directly in 3D. Our framework takes an unordered set of posed images captured by a monocular camera and segments fruit in each image. To make our system independent of the fruit type, we employ a foundation model that generates binary segmentation masks for any fruit. Utilizing both modalities, RGB and semantic, we train a semantic neural radiance field. Through uniform volume sampling of the implicit Fruit Field, we obtain fruit-only point clouds. By applying cascaded clustering on the extracted point cloud, our approach achieves precise fruit count.The use of neural radiance fields provides significant advantages over conventional methods such as object tracking or optical flow, as the counting itself is lifted into 3D. Our method prevents double counting fruit and avoids counting irrelevant fruit.We evaluate our methodology using both real-world and synthetic datasets. The real-world dataset consists of three apple trees with manually counted ground truths, a benchmark apple dataset with one row and ground truth fruit location, while the synthetic dataset comprises various fruit types including apple, plum, lemon, pear, peach, and mango.Additionally, we assess the performance of fruit counting using the foundation model compared to a U-Net.
Why it matches plant phenotyping methods果実を対象に、画像・NeRF・点群クラスタリングを組み合わせて3D果実数を推定する手法を開発し、実データおよび合成データで評価しているため、植物表現型取得法が中心である。
abstractWe introduce FruitNeRF, a unified novel fruit counting framework that leverages state-of-the-art view synthesis methods to count any fruit type directly in 3D.
Reproduction assets foundThe paper's real-world apple tree image dataset with manual ground-truth counts and synthetic Blender fruit tree data are publicly released via the project website, and the FruitNeRF analysis code is open-source on GitHub. The Zenodo DOI refers to the third-party BlenderNeRF plugin (cited tool), not a paper-specific.Dataset · publicThe data has been made publicly available, and visualizations can be accessed on the project website.Open asset ↗lines:183-221Code · publicFruitNeRF code: https://github.com/meyerls/FruitNeRF has been made open-source.Open asset ↗meyerls/FruitNeRFlines:74-108Code / dataset availability confirmedbioRxiv · checked 14 Sept 2026
The evolutionary histories of species have been shaped by genomic, environmental, and morphological variation. Understanding the interactions among these sources of variation is critical to infer accurately the biogeographic history of lineages. Here, using the geographically widely distributed plum genus (Prunus, Rosaceae) as a model, we investigate how changes in genomic and environmental variation drove the diversification of this group, and we quantify the morphological features that facilitated or resulted from diversification. We sequenced 587 nuclear loci and complete chloroplast genomes from 99 species representing all major lineages in Prunus, with a special focus on the understudied tropical racemose group. The environmental variation in extant species was quantified by synthesizing bioclimatic variables into principal components of environmental variation using thousands of georeferenced herbarium specimens. We used machine learning algorithms to classify and measure morphological variation present in thousands of digitized herbarium sheet images. Our phylogenomic and biogeographic analyses revealed that ancient hybridization and/or allopolyploidy spurred the initial rapid diversification of the genus in the early Eocene, with subsequent diversification in the north temperate zone, neotropics, and paleotropics. This diversification involved successful transitions between tropical and temperate biomes, an exceedingly rare event in woody plant lineages, accompanied by morphological changes in leaf and reproductive morphology. The machine learning approach detected morphological variation associated with ancient hybridization and quantified the breadth of morphospace occupied by major lineages within the genus. The paleotropical lineages of Prunus have diversified steadily since the late Eocene/early Oligocene, while the neotropical lineages diversified much later. Critically, both the tropical and temperate lineages have continued to diversify. We conclude that the genomic rearrangements created by reticulation deep in the phylogeny of Prunus may explain why this group has been more successful than other groups with tropical origins that currently persist only in either tropical or temperate regions, but not both.
Why it matches plant phenotyping methods機械学習を用いて標本画像から植物の形態変異を分類・測定し、葉および生殖形態の表現型を定量化しており、形態計測ワークフローが研究の中心的要素である。
abstractWe used machine learning algorithms to classify and measure morphological variation present in thousands of digitized herbarium sheet images.
Reproduction assets foundThe paper's herbarium image data and supplementary material are deposited in Dryad; trained Prunus ML classifiers are on Hugging Face; author Jupyter notebooks for the ML workflow are on GitHub. All are paper-specific, public, and actionable.Dataset · public1126 Data Availability
1127
1128 Data available from the Dryad Digital Repository: DOI: 10.5061/dryad.x95x69pwr; Reviewer
1129 URL: http://datadryad.org/share/L-QUcxrgnpTr6l0Td3MxdfJDCUT1iRbPmT4SzA2LwMA.
1130
1131 Supplementary material, image data, and DNA sequence matrices are available from the Dryad
1132 Digital Repository. Raw sequence data were submitted to NCBI GenBank (SUB13638423).
1133 Machine learning models are hosted on Hugging Face with temporary URLs
1134 (https://huggingface.co/richiehodel/Prunus_lineage_classiOpen asset ↗Dryad Digital Repository · 10.5061/dryad.x95x69pwrpdf-layout-page:54 lines:1-31Code / dataset availability confirmedOpenAlex · Crossref · Europe PMC · checked 8 Sept 2026
One of the objectives of many studies conducted by breeding programs is to characterize and select rootstocks well-adapted to drought conditions. In recent years, field high-throughput phenotyping methods have been developed to characterize plant traits and to identify the most water use efficient varieties and rootstocks. However, none of these studies have been able to quantify the behavior of crop evapotranspiration in almond rootstocks under different water regimes. In this study, remote sensing phenotyping methods were used to assess the evapotranspiration of almond cv. “Marinada” grafted onto a rootstock collection. In particular, the two-source energy balance and Shuttleworth and Wallace models were used to, respectively, estimate the actual and potential evapotranspiration of almonds grafted onto 10 rootstock under three different irrigation treatments. For this purpose, three flights were conducted during the 2018 and 2019 growing seasons with an aircraft equipped with a thermal and multispectral camera. Stem water potential (Ψstem) was also measured concomitant to image acquisition. Biophysical traits of the vegetation were firstly assessed through photogrammetry techniques, spectral vegetation indices and the radiative transfer model PROSAIL. The estimates of canopy height, leaf area index and daily fraction of intercepted radiation had root mean square errors of 0.57 m, 0.24 m m–1 and 0.07%, respectively. Findings of this study showed significant differences between rootstocks in all of the evaluated parameters. Cadaman® and Garnem® had the highest canopy vigor traits, evapotranspiration, Ψstem and kernel yield. In contrast, Rootpac® 20 and Rootpac® R had the lowest values of the same parameters, suggesting that this was due to an incompatibility between plum-almond species or to a lower water absorption capability of the rooting system. Among the rootstocks with medium canopy vigor, Adesoto and IRTA 1 had a lower evapotranspiration than Rootpac® 40 and Ishtara®. Water productivity (WP) (kg kernel/mm water evapotranspired) tended to decrease with Ψstem, mainly in 2018. Cadaman® and Garnem® had the highest WP, followed by INRA GF-677, IRTA 1, IRTA 2, and Rootpac® 40. Despite the low Ψstem of Rootpac® R, the WP of this rootstock was also high.
Why it matches plant phenotyping methodsリモートセンシングによる植物形質・蒸発散の推定が研究の中心で、熱・マルチスペクトル画像、フォトグラメトリ、モデルを用いた推定精度も評価している。
abstractIn recent years, field high-throughput phenotyping methods have been developed to characterize plant traits and to identify the most water use efficient varieties and rootstocks.
Reproduction assets foundThe paper's data availability statement points to the author's public GitHub profile (Héctor Nieto, pyTSEB developer) as the location of the datasets analyzed, which include the remote sensing phenotyping measurements (thermal/multispectral imagery-derived ETa, LAI, fiPAR, Ψstem relationships) and the TSEB-based model.Dataset · publicPublicly available datasets were analyzed in this study. This data can be found here: https://github.com/hectornieto .Open asset ↗hectornietolines:1046-1107