Explainable AI Enhanced Deep Learning for Tomato Disease Classification using Resnet-50 and Mobilenetv2

Authors

Abrhaley Gebreslassie Gebremariam, Adigrat University, Ethiopia

Guesh Dagnew Demewez, Mekelle University, Ethiopia

Published in

IST-Africa 2026 Conference Proceedings

ISSN: 2576-8581

ISBN: 978-1-905824-76-2

DOI: https://doi.org/tbc

Publisher

IST-Africa Institute and IIMC International Information Management Corporation Ltd

Published in Ireland

Abstract

Tomato crops are vulnerable to various disease that threaten food security and farmers livelihoods, especially in resource -limited regions like Tigray, Ethiopia. This study presents a hybrid deep learning model combining Resnet-50 and MobilenetV2 with Explainable AI (Grad-CAM) for automated tomato leaf disease classification. Using a benchmark dataset of 17,920 annotated images across 10 disease classes, Resnet-50 achieved training accuracy 99.25% and 94.5% validation accuracy, while MobilenetV2 reached training accuracy 94.6% and validation accuracy 89%, offering a trade-off between accuracy and deployment feasibility. Grad-cam visualization confirmed model focus on biologically relevant leaf regions, enhancing interpretability. The proposed system demonstrates potential for real-world deployment in precision agriculture and supports small holder farmers through early disease detection and informed crop management.

Keywords

Tomato disease detection, convolutional neural network (CNN), MobileNetV2, ResNet-50, Explainable AI, Grad-CAM, Deep learning

Cite this paper

A.G. Gebremariam and G.D. Demewez (2026) "Explainable AI Enhanced Deep Learning for Tomato Disease Classification using Resnet-50 and Mobilenetv2", IST-Africa 2026 Conference Proceedings, Miriam Cunningham and Paul Cunningham (Eds), IST-Africa Institute and IIMC, 2026, ISSN: 2576-8581, ISBN: 978-1-905824-76-2, https://doi.org/tbc

Access Paper

Click here to access this paper.

IST-Africa Community Members can download papers by logging into their existing account.

If you wish to become a member of IST-Africa Community, pleaseregister your profile and you will then receive login details which you can use to access the papers.

Access to papers in the IST-Africa 2026 Conference Proceedings is for INDIVIDUAL USE only. Neither the Conference Proceedings (or individual double blind peer reviewed papers) are to be included in any public or institutional repository or processed in the context of any AI tool or large language model without prior written permission from the Publishers.

While the IST-Africa Institute and IIMC retain copyright of the Conference Proceedings, each author retains copyright to their individual paper. No paper or part thereof may be reproduced without the written permission of both the Conference Proceedings Publishers and appropriate author(s).