Current Research Bulletin

Paddy (Rice) leaf illnesses form a notable threat to crop productivity and food efficiency, especially in developing countries where rice is regarded as a staple crop. Conventional illness diagnosis approaches rely on manual observation, which is laborious, erroneous, and unfit for large-scale farming. Deep learning methods, specifically Convolutional Neural Networks (CNNs), have remarkably depicted great success in computerized disease classification. Though, numerous existing methods are constrained by lofty computational complexity, high memory exploitation, and poor interpretability. This research offers a baseline study using MobileNetV2 for rice leaves disease detection. The proposed baseline model uses transfer learning for classification of four different rice leaf ailments: Brown-Spot, Bacterial Leaf Blight, Rice Blast, and Rice Tungro. The dataset comprises 5952 images obtained from Mendeley database and preprocessing techniques were applied on them. Experiments were carried out by using Google Colab CPU runtime under common parameters and settings. The MobileNetV2 baseline architecture has excellently produced accuracy of 99.27%, macro F1-score of 0.9929, with reasonably small model size and low latency against memory consuming CNN architectures. The results present MobileNetV2 as a reliable and strong lightweight baseline for rice leaf disease detection and offer a benchmark for future hybrid interpretable architectures.

Rice leaf illness, MobileNetV2, transfer learning, lightweight CNN, deep learning, plant disease detection, interpretability

1. Chauhan, B.S.; Jabran, K.; Mahajan, G. Rice Production Worldwide; Springer: Berlin/Heidelberg,  Germany, 2017; Volume 247. [Google Scholar]
2. Automatic Recognition of Rice Leaf Diseases Using Transfer Learning. Simhadri, C. G., & Kondaveeti, H. K. (2023). Automatic recognition of rice leaf diseases using transfer learning. Agronomy, 13(4), 961. https://doi.org/10.3390/agronomy13040961
3. Thompson, N.C.; Greenewald, K.; Lee, K.; Manso, G.F. The computational limits of deep learning. arXiv 2020, arXiv:2007.05558. [Google Scholar]
4. Barbedo, J.G.A. Impact of dataset size and variety on the effectiveness of deep learning and transfer learning for plant disease classification. Comput. Electron. Agric. 2018, 153, 46–53. 
5. H. A. A and A. A, "Smart Agriculture Rice Leaf Disease Detection using Deep Learning Model," 2024 International Conference on Emerging Research in Computational Science (ICERCS), Coimbatore, India, 2024, pp. 1-7, doi: 10.1109/ICERCS63125.2024.10895956.
6. Li, R., Chen, S., Matsumoto, H. et al. Predicting rice diseases using advanced technologies at different scales: present status and future perspectives.aBIOTECH 4, 359–371 (2023). https://doi.org/10.1007/s42994-023-00126-4
7. Hajoub, M.W., Touil, H., Begdouri, M.A. (2026). A Comparative Analysis of Deep Learning Architectures for Plant Disease Diagnosis. In: Kodad, M., Moussaoui, O. (eds) The 3rd International Conference on Artificial Intelligence and Smart Applications (AISA’25), Volume 1: Artificial Intelligence, IoT, and Smart Applications. AISA 2025. Lecture Notes in Networks and Systems, vol 1841. Springer, Cham. https://doi.org/10.1007/978-3-032-18716-1_27 
8. Ginting, Yudha & Ramadhan, Fadil & Sinaga, Sophian. (2025). Implementation of MobileNetV2 Architecture In Rice Disease Detection System Using Digital Images. International Journal of Science and Environment (IJSE). 5. 125-132. 10.51601/ijse.v5i2.140.
9. S. Abotula, D. V. Rajasagi, P. Patnaikuni, A. S. Kesavapatnam and S. D. Rambha, "Rice Leaf Disease Prediction Using MobileNetV2," 2025 4th International Conference on Sentiment Analysis and Deep Learning (ICSADL), Bhimdatta, Nepal, 2025, pp. 1320-1323, doi: 10.1109/ICSADL65848.2025.10933476.
10. P. Raj, Jyoti, A. Kumar and P. Singh, "Detecting Paddy Leaf Diseases Using MobileNetV2 and Machine Learning Techniques," 2024 International Conference on Progressive Innovations in Intelligent Systems and Data Science (ICPIDS), Pattaya, Thailand, 2024, pp. 120-128, doi: 10.1109/ICPIDS65698.2024.00028.
11. B. R. Raju, B. P. Goud, C. Nanditha, V. Shruthi, T. Vandana and N. N. Lakshmi, "Smart Detection of Rice Leaf Disease using Deep Learning Models," 2025 5th International Conference on Intelligent Technologies (CONIT), HUBBALI, India, 2025, pp. 1-6, doi: 10.1109/CONIT65521.2025.11166984.
12. L. Tian, Chen, S., Li, J., & Zhou, Z. (2020). Transfer learning for plant disease detection with convolutional neural networks. BMC Bioinformatics, 21, 369. https://doi.org/10.1186/s12859-020-03753-z.
13. Elakya, R.; Manoranjitham, T. Classification of diseases in Paddy by using Deep transfer learning MobileNetV2 model. In Proceedings of the 2022 1st International Conference on Computational Science and Technology (ICCST), Chennai, India, 9–10 November 2022; pp. 936–940.
14. Asvitha S., Dhivya, T., Dhivyasree, H., & Bhavadharini, R. (2022). Paddy Pro: A MobileNetV3-based app to identify paddy leaf diseases. In Proceedings of the International Conference on Computing, Communications, and Cyber-Security (pp. 203–216). Delhi, India.
15. Wang Z., Wei, Y., Mu, C., Zhang, Y., & Qiao, X. (2024). Rice disease classification using a stacked ensemble of deep convolutional neural networks. Sustainability, 17(1), 124. https://doi.org/10.3390/su17010124.
16. Wang H., Qiu, S., Ye, H., & Liao, X. (2023). A plant disease classification algorithm based on Attention MobileNetV2. Algorithms, 16(4), 442. https://doi.org/10.3390/a16090442.
17. Chen J., Chen, W., Zeb, A., Zhang, D., & Nanehkaran, Y. A. (2021). Crop pest recognition using attention-embedded lightweight network under field conditions. Applied Entomology and Zoology, 56, 427–442.
18. Zhao Y., Chen, J., Xu, X., Lei, J., & Zhou, W. (2021). SEV-Net: Residual network embedded with attention mechanism for plant disease severity detection. Concurrency and Computation: Practice and Experience, 33, e6161.