ResNet 50 and Inception V3-based Deep Learning Classification of Potato Leaf Diseases

This study evaluated deep learning models to classify potato leaf diseases using different training setups. The results prove that tuning the batch size is vital for maximizing classification success. The Proposed Model with a batch size of 64 and a learning rate of 0.0001 delivered the best results, yielding a 94.33% validation accuracy and a 0.0418 validation loss. This outshone the best ResNet50 configuration, which reached 91.50% accuracy. These findings show that our optimized deep learning approach can reliably identify potato plant diseases. In the future, this model could be built into mobile apps or drone systems to help farmers spot crop diseases early in the field, reducing pesticide use and protecting crop yields

[1] Singh, S. (2026). Agriculture in the Indian economy: growth, employment, and structural challenges. Social Science Journal for Advanced Research, 6(1), 73–77. https://doi.org/10.54741/ssjar/6.1.2026.321.   [2] Dolničar, P. (2021). Importance of potato as a crop and practical approaches to potato breeding. Methods in Molecular Biology, 2354, 3 20. https://doi.org/ 10.1007 /978-1-0716-1609-3_1.   [    [3] Pooja, Chauhan, P., Kumar, A., Kumar, A., Rithesh, L., Kumar, A., & Kumar, A. (2025). Recent insights into potato dry rot an emerging Disease: Focusing on pathogen diversity, host-pathogen interactions, and management strategies. Microbial Pathogenesis, 207, 107866. https://doi.org/10.1016/j.micpath.2025.107866.   [    [4] Farooq, M. S., Kamran, A., Raza, S. A., Wasiq, M. F., Hassan, B., & Herzog, N. J. (2025). Advancing early blight detection in potato leaves through ZeroShot learning. Journal of Imaging, 11(8), 256. https://doi.org/10.3390/jimaging 11080256.   [   [5]Sharma, A., Singh, V., Sharma, C., Ansari, G., Kumar, S., & Joshi, K. (2024). Potato Leaf Disease Detection and Classification Using Deep Learning Technique (pp.505-509) https://doi.org/10.1109/ictacs 62700.2024.10840790.   [  [6] Sinamenye, J. H., Chatterjee, A., & Shrestha, R. (2025). Potato plant disease detection: leveraging hybrid deep learning models. BMC Plant Biology, 25(1), 647. https://doi.org/10.1186/s12870-025-06679-4.   [   [7] Shaheed, K., Qureshi, I., Abbas, F., Jabbar, S., Abbas, Q., Ahmad, H., & Sajid, M. Z. (2023). EfficientRMT-NeT—An efficient RESNET-50 and Vision Transformers approach for classifying potato plant leaf diseases. Sensors, 23(23),9516. https://doi.org/10.3390/s23239516.   [   [8]Nur, K. N. A., Addyna, N. I., Windarto, A. P., Wanto, A., & Poningsih, P. (2025). OPTIMIZATION OF THE INCEPTIONV3 ARCHITECTURE FOR POTATO LEAF DISEASE CLASSIFICATION. JITK (Jurnal Ilmu Pengetahuan Dan Teknologi Komputer), 10(4), 849–858. https://doi.org/10.33480/jitk.v10i4.6554.  [9] A. Suryavanshi, S. Tanwar, V. Kukreja, A. Choudhary and S. Chamoli, "An Integrated Approach to Potato Leaf Disease Detection Using Convolutional Neural Networks and Random Forest," 2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), Chennai, India, 2023, pp. 1-7, doi: 10.1109/ICSES60034.2023.10465557.   [10] Asif, M., Abbas, T., Iqbal, S. et al. MapReduce-based deep learning framework for potato leaf disease detection in sustainable precision agriculture. Sci Rep 16, 1607 (2026). https://doi.org/10.1038/s41598-025-30940-3.