Smart plant disease diagnosis using multiple deep learning and web application integration

Accurate and efficient plant disease diagnosis is crucial for sustainable agriculture and global food security, as diseases significantly impact crop productivity. Despite advancements in deep learning, the performance and scalability of many models remain limited. This study addresses this gap by e...

Full description

Saved in:
Bibliographic Details
Main Authors: Ahmed M.S. Kheir, Anis Koubaa, Vinothkumar Kolluru, Sudeep Mungara, Til Feike
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Journal of Agriculture and Food Research
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666154325003199
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849725583861219328
author Ahmed M.S. Kheir
Anis Koubaa
Vinothkumar Kolluru
Sudeep Mungara
Til Feike
author_facet Ahmed M.S. Kheir
Anis Koubaa
Vinothkumar Kolluru
Sudeep Mungara
Til Feike
author_sort Ahmed M.S. Kheir
collection DOAJ
description Accurate and efficient plant disease diagnosis is crucial for sustainable agriculture and global food security, as diseases significantly impact crop productivity. Despite advancements in deep learning, the performance and scalability of many models remain limited. This study addresses this gap by evaluating MobileViTv2, EfficientNet-B7, and a hybrid MobileViTv2-EfficientNet-B7 approach for classifying plant leaf images into four categories: healthy, rust, scab, and multiple diseases. Using a publicly available dataset of annotated leaf images, the models were trained and tested under optimized conditions. MobileViTv2 emerged as the superior model, achieving the highest classification accuracy (94 %) and F1 score (0.94). It demonstrated exceptional generalization capabilities, with Receiver Operating Characteristic (ROC) Area Under Curve (AUC) values of 0.95 for healthy, 0.97 for rust, and 0.99 for scab. In contrast, EfficientNet-B7 and the hybrid model performed moderately, highlighting MobileViTv2's efficiency in handling diverse image features. To demonstrate real-world applicability, the MobileViTv2 model was deployed in a web-based application. This platform enables real-time plant disease diagnosis with high confidence, identifying conditions such as rust (85.3 % confidence) and healthy leaves (90.2 % confidence). The user-friendly interface facilitates its integration into precision agriculture. This study highlights the strengths of MobileViTv2 for disease diagnosis, its scalability, and its potential to support decision-making in agriculture. Future work will focus on expanding the model to other crops and incorporating environmental variables for enhanced disease prediction. This research bridges the gap between advanced AI models and practical agricultural applications, offering a robust solution for early disease detection.
format Article
id doaj-art-ec8b56d24e094cb585e0149ba605b19a
institution DOAJ
issn 2666-1543
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Journal of Agriculture and Food Research
spelling doaj-art-ec8b56d24e094cb585e0149ba605b19a2025-08-20T03:10:25ZengElsevierJournal of Agriculture and Food Research2666-15432025-06-012110194810.1016/j.jafr.2025.101948Smart plant disease diagnosis using multiple deep learning and web application integrationAhmed M.S. Kheir0Anis Koubaa1Vinothkumar Kolluru2Sudeep Mungara3Til Feike4Julius Kühn Institute (JKI)—Federal Research Centre for Cultivated Plants, Institute for Strategies and Technology Assessment, 14532 Kleinmachnow, Germany; Soils, Water and Environment Research Institute, Agricultural Research Center, Giza, 12112, Egypt; Corresponding author. Institute for Strategies and Technology Assessment, Julius Kühn Institute (JKI), Federal Research Centre for Cultivated Plants, 14532, Kleinmachnow, Germany.Alfaisal University, Saudi Arabia, RiyadhDepartment of Data Science, Stevens Institute of Technology, 1 Castle Point Terrace, Hoboken, NJ, 07030, USAStevens Institute of Technology, 1 Castle Point Terrace, Hoboken, NJ, 07030, USAJulius Kühn Institute (JKI)—Federal Research Centre for Cultivated Plants, Institute for Strategies and Technology Assessment, 14532 Kleinmachnow, GermanyAccurate and efficient plant disease diagnosis is crucial for sustainable agriculture and global food security, as diseases significantly impact crop productivity. Despite advancements in deep learning, the performance and scalability of many models remain limited. This study addresses this gap by evaluating MobileViTv2, EfficientNet-B7, and a hybrid MobileViTv2-EfficientNet-B7 approach for classifying plant leaf images into four categories: healthy, rust, scab, and multiple diseases. Using a publicly available dataset of annotated leaf images, the models were trained and tested under optimized conditions. MobileViTv2 emerged as the superior model, achieving the highest classification accuracy (94 %) and F1 score (0.94). It demonstrated exceptional generalization capabilities, with Receiver Operating Characteristic (ROC) Area Under Curve (AUC) values of 0.95 for healthy, 0.97 for rust, and 0.99 for scab. In contrast, EfficientNet-B7 and the hybrid model performed moderately, highlighting MobileViTv2's efficiency in handling diverse image features. To demonstrate real-world applicability, the MobileViTv2 model was deployed in a web-based application. This platform enables real-time plant disease diagnosis with high confidence, identifying conditions such as rust (85.3 % confidence) and healthy leaves (90.2 % confidence). The user-friendly interface facilitates its integration into precision agriculture. This study highlights the strengths of MobileViTv2 for disease diagnosis, its scalability, and its potential to support decision-making in agriculture. Future work will focus on expanding the model to other crops and incorporating environmental variables for enhanced disease prediction. This research bridges the gap between advanced AI models and practical agricultural applications, offering a robust solution for early disease detection.http://www.sciencedirect.com/science/article/pii/S2666154325003199Plant disease diagnosisMobileViTv2EfficientNet-B7Hybrid deep learning modelsPrecision agricultureWeb-based application
spellingShingle Ahmed M.S. Kheir
Anis Koubaa
Vinothkumar Kolluru
Sudeep Mungara
Til Feike
Smart plant disease diagnosis using multiple deep learning and web application integration
Journal of Agriculture and Food Research
Plant disease diagnosis
MobileViTv2
EfficientNet-B7
Hybrid deep learning models
Precision agriculture
Web-based application
title Smart plant disease diagnosis using multiple deep learning and web application integration
title_full Smart plant disease diagnosis using multiple deep learning and web application integration
title_fullStr Smart plant disease diagnosis using multiple deep learning and web application integration
title_full_unstemmed Smart plant disease diagnosis using multiple deep learning and web application integration
title_short Smart plant disease diagnosis using multiple deep learning and web application integration
title_sort smart plant disease diagnosis using multiple deep learning and web application integration
topic Plant disease diagnosis
MobileViTv2
EfficientNet-B7
Hybrid deep learning models
Precision agriculture
Web-based application
url http://www.sciencedirect.com/science/article/pii/S2666154325003199
work_keys_str_mv AT ahmedmskheir smartplantdiseasediagnosisusingmultipledeeplearningandwebapplicationintegration
AT aniskoubaa smartplantdiseasediagnosisusingmultipledeeplearningandwebapplicationintegration
AT vinothkumarkolluru smartplantdiseasediagnosisusingmultipledeeplearningandwebapplicationintegration
AT sudeepmungara smartplantdiseasediagnosisusingmultipledeeplearningandwebapplicationintegration
AT tilfeike smartplantdiseasediagnosisusingmultipledeeplearningandwebapplicationintegration