2026-10-06T08:35:40Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34041414 2026-10-01T16:46:54Z category_23941 category_29161 category_28879 item_type_3 month_year_10_2026

Data and code for: Evaluating Multitask Deep Learning for Multi-Crop Plant Health Recognition under Seed Variation and Crop Transfer Ajay Pinto (25155285) Crop and pasture protection (incl. pests, diseases and weeds) Deep learning Computer vision Plant disease recognition multitask learning multi-seed evaluation disease severity inter assessor agreement external validation ResNet50 betel vine brinjal okra malabar spinach potato <p dir="ltr">This item contains the data records and code supporting the study "Evaluating Multitask Deep Learning for Multi-Crop Plant Health Recognition under Seed Variation and Crop Transfer" (Cogent Food & Agriculture, under review).</p><p dir="ltr">The study compares four output formulations (single-task joint classification, independent multitask heads, multitask fusion, and fusion conditioned on task posteriors) on a shared frozen ResNet50 backbone, each trained with five random seeds (20 models), on a compiled benchmark of 5,235 leaf images of betel vine, brinjal, ladies finger (okra) and Malabar spinach in healthy and unhealthy states. An ordinal severity reference was built for 96 images by independent dual assessment and pre-specified adjudication. All models were also evaluated on 3,295 images of an unseen crop (potato).</p><p dir="ltr">Contents:<br>(1) manifests_and_audits.zip – the frozen dataset manifest (5,235 images, SHA256 fingerprints), train/validation/test split manifests (seed 42, 70:15:15), provenance table, integrity and duplicate-screening audits, and the potato external-validation manifest and exclusion log;<br>(2) severity_reference.zip – the 96-image assessment batch, both assessors' rating records and event logs, agreement analysis, adjudication records and the final adjudicated severity reference;<br>(3) code_and_results.zip – Jupyter notebooks for dataset auditing, splitting, severity rating and adjudication, model training (TensorFlow 2.20.0, Keras 3.13.2, Python 3.13), the decision-policy simulation and all downstream analyses, with per-model result tables;<br>(4) README.txt – file descriptions and run order.</p><p dir="ltr">Third-party images are not redistributed. They are listed in the manifests by original filename and can be obtained from their sources: Betel Leaf Image Dataset from Bangladesh (<a href="https://doi.org/10.17632/g7fpgj57wc.2" target="_blank">https://doi.org/10.17632/g7fpgj57wc.2</a>), SLIF-Brinjal (<a href="https://doi.org/10.17632/6yg6vktrc2.2" target="_blank">https://doi.org/10.17632/6yg6vktrc2.2</a>) and PLDD-UP (<a href="https://doi.org/10.17632/3j4nfkvp2n.1" target="_blank">https://doi.org/10.17632/3j4nfkvp2n.1</a>). images_author_captured.zip </p> 2026-10-01T16:46:54Z Dataset Dataset 10.6084/m9.figshare.34041414.v1 https://figshare.com/articles/dataset/Data_and_code_for_Evaluating_Multitask_Deep_Learning_for_Multi-Crop_Plant_Health_Recognition_under_Seed_Variation_and_Crop_Transfer/34041414 CC BY 4.0