An explainable AI-based cotton leaf disease classification using EfficientNet, Grad-Cam, Lime, and Shap

Sumera Nazim; Abdul Samad; Nisha Tanwani; Jalal Bhayo; Mushtaque Ahmed Rahu

An explainable AI-based cotton leaf disease classification using EfficientNet, Grad-Cam, Lime, and Shap

Authors

Sumera Nazim Assistant professor, Department of Economics, Ayesha Girls Degree College, Nawab Shah, Pakistan
Abdul Samad Lecturer, Department of Computer Science, Shaheed Benazir Bhutto University, Shaheed Benazirabad, Pakistan
Nisha Tanwani Lecturer, Department of Computer Science, Govt: Sachal Sarmast College, Nawabshah, Pakistan
Jalal Bhayo Assistant Professor, Department of Computer Science, Govt Degree College Khipro, College Education Department, Sindh, Pakistan
Mushtaque Ahmed Rahu PhD in Electronic Engineering, Department of Electronic Engineering, Quaid-e-Awam University of Engineering, Science and Technology, Nawabshah, Pakistan

Keywords:

explainable AI, precision agriculture, deep learning, EfficientNet cotton crop disease detection, smart agriculture

Abstract

The quality of the cotton crop is reduced in terms of fibre, yield quality, and economic standard, especially due to leaf infections and disease symptoms, which spread in all field areas. The automated visualisation of disease screening from the infected images of leaves, due to limitations of the black box nature of the deep learning models, creates the less agriculture developments. This research provides a framework with integration of the deep learning and explainable AI-based approach for the detection and classification with the EfficientNet approach for the cotton crop disease, along with an explanation by adopting the Grad-CAM and SHAP discussion and explanation. The experimentation is performed using 800 Images with labelled leaf images of cotton crop disease obtained from Kaggle. The data preprocessing is used for the image resized as 224 x 224 pixels, augmented and normalised, with spilt into validation, training, and testing data subsets. The results show that after 20 epochs, the EfficientNet Model provides subtle results and is stable with 92% accuracy for image disease detection. The confusion matrix shows the 45 correctly healthy classified images, the disease leaves 43, false positives 5, and false negatives 7 by providing the 88.00% yielding test accuracy and 89.58% the precision of the disease class, recall 86.00%, f1 score 87.76%. The spatial heatmap, highlighted by the Grad-CAM, provides the symptoms of the leaf region. Whereas the pixel-level explanation is obtained by the LIME and summarises the visual contextual explanation of the feature from the image. The predictive performance is focused in this framework with transparency, reliability, and interpretability for the cotton crop diseases.

References

Malik, V., AlJarullah, A., Alsubait, T., Ikram, A., Goyal, S. B., & Khan, M. (2026). Explainable artificial-intelligence-based hyperspectral image analysis for leaf disease detection in an intercropping system. Frontiers in Plant Science, 17, 1789542.

Toral Patel, D. S. D., & Soni, D. A Review of Artificial Intelligence Techniques for Cotton Leaf Disease Identification. environments, 7, 10.

Rahu, Mushtaque Ahmed, Sarang Karim, Rehan Shams, Ayaz Ahmed Soomro, and Abdul Fattah Chandio. "Wireless Sensor Networks-based Smart Agriculture: Sensing Technologies, Application, and Future Directions." Sukkur IBA Journal of Emerging Technologies 5, no. 2 (2022): 18-32.

Haque, M. E., Saykat, M. T. H., Al-Imran, M., Siam, A. H., Uddin, J., & Ghose, D. (2026). An attention-enhanced CNN ensemble for interpretable and accurate cotton leaf disease classification. Scientific Reports.

M. A. Rahu, A. F. Chandio, K. Aurangzeb, S. Karim, M. Alhussein, and M. S. Anwar, "Toward Design of Internet of Things and Machine Learning-Enabled Frameworks for Analysis and Prediction of Water Quality," in IEEE Access, vol. 11, pp. 101055-101086, 2023, doi: 10.1109/ACCESS.2023.3315649.

Swapno, S. M. R., Sakib, A., Hossain, A., Debnath, J., Al Noman, A., Al Sakib, A., ... & Appaji, A. (2026). Explainable transformer framework for fast cotton leaf diagnostics and fabric defect detection. Iscience, 29(2).

Rahu, Mushtaque Ahmed, Muhammad Mujtaba Shaikh, Sarang Karim, Abdul Fattah Chandio, Safia Amir Dahri, Sarfraz Ahmed Soomro, and Sayed Mazhar Ali. "An IoT and machine learning solutions for monitoring agricultural water quality: a robust framework." Mehran University Research Journal of Engineering and Technology 43, no. 1 (2024): 192-205.

Srinivasan, S., A R. K., B. A, N., Tanwar, J., Singh, V. P., & Moorthy, U. (2026). Multi-class classification of plant leaf diseases using a hybrid deep neural transformer system and explainable AI techniques. Scientific Reports.

Rahu, M.A., Shaikh, M.M., Karim, S. et al. “Water Quality Monitoring and Assessment for Efficient Water Resource Management through Internet of Things and Machine Learning Approaches for Agricultural Irrigation”. Water

Resource Management (2024). https://doi.org/10.

/s11269-024-03899-5.

Ganesan, N., & Kandhasamy, V. (2026). Early Detection of Cotton Plant Diseases Using Zebra Optimiser with Deep Learning Approach. Traitement du Signal, 43(1), 519.

Kaur, G., Al‐Yarimi, F. A. M., Bharany, S., Rehman, A. U., & Hussen, S. (2025). Explainable AI for Cotton Leaf Disease Classification: A Metaheuristic-Optimised Deep Learning Approach. Food Science & Nutrition, 13(7), e70658.

Karim, S., Hussain, K., Alvi, M. B., Rahu, M. A., Kaloi, M. A., & Haleem, H. (2025). Artificial Intelligence in Sustainable Smart Agriculture: Concepts, Applications, and Challenges. VAWKUM Transactions on Computer Sciences, 13(1), 307–342. https://doi.org/10.21015/vtcs.v13i1.2151

Rashid, M. R. A., Korim, M. A. E., Hasan, M., Ali, M. S., Islam, M. M., Jabid, T., ... & Islam, M. (2025). An Ensemble Learning Framework with Explainable AI for interpretable leaf disease detection. Array, 26, 100386.

Hussain, M., Ali, S. M., Rahu, M. A., Tunio, N. A., & Chandio, A. F. (2025). IoT-Enabled Machine Learning Framework for Precision Agriculture: Achieving Near-Perfect Crop Yield Prediction in Pakistan’s Diverse Agro-Climatic Zones. VAWKUM Transactions on Computer Sciences, 13(2), 263–275. https://doi.org/10.21015/vtcs.v13i2.2310.

Shafi, H., Ghulam, A., Talpur, S. H., Sikander, R., Ali, A., Jabeen, N., ... & Iskandar, Y. (2025). A Comprehensive Review of Complex Network Methods for Cotton Plant Disease Detection. Journal of Information Communication Technologies and Robotic Applications, 16(1).

Imran Khan Jatoi, Mushtaque Ahmed Rahu, Nimra Memon, Muhammad Aurangzaib, & Urooj Oad. (2026). “Integrating New Frontier Digital Twins Technology in Smart Agriculture Revolution”. International Journal of Agriculture Innovations and Cutting-Edge Research (HEC Recognised), 4(2), 1–13. https://jai.bworesearches.com/index.php/jwr/article/view/228.

Shafik, W., Tufail, A., De Silva, L. C., Haji Mohd Apong, R. A. A., & Kim, K. H. (2025). Deep learning technique for plant disease classification, pest detection, and model explainability, elevating agricultural sustainability. BMC Plant Biology, 25(1), 1491.

Pai, D. G., Balachandra, M., & Kamath, R. (2025). Explainable AI in agriculture: Review of applications, methodologies, and future directions. Engineering Research Express, 7(3), 032202.

Vidivelli, S., Manikandan, R., Magesh, S., Cho, J., & Easwaramoorthy, S. V. (2025, October). Exploring precision agriculture: Employing Grad-CAM for a deep neural network in cotton image detection and segmentation with XAI. In AIP Conference Proceedings (Vol. 3335, No. 1, p. 030009). AIP Publishing LLC.

Kaler, B., & Kaur, A. (2025). A systematic survey on explainable artificial intelligence (XAI) for plant health monitoring: challenges and opportunities. Applied Intelligence, 55(12), 889.

Fan, J., Zhang, Y., Wen, W., Gu, S., Lu, X., & Guo, X. (2021). The future of Internet of Things in agriculture: Plant high-throughput phenotypic platform. Journal of Cleaner Production, 280, 123651. https://doi.org/10.1016/j.jclepro.2020.123651

Kalmani, V. H., Dharwadkar, N. V., & Thapa, V. (2024). Crop Yield Prediction using a Deep Learning Algorithm based on CNN-LSTM with an Attention Layer and Skip Connection. Indian Journal Of Agricultural Research, 59(Of), 1303–1311. https://doi.org/10.18805/ijare.a-6300

Mirani, A. A., Muhammad, E., Memon, S., Chohan, R., Sodhar, I. N., & Rahu, M. A. (2021). Irrigation scheduling, water pollution monitoring in IoT : A Review. 10. https://www.researchgate.net/profile/Azeem

Mirani/publication/354646929_Irrigation_and_Drainage_Systems_Engineering_Irrigation_scheduling_water_pollution_monitoring_in_IoT_A_Review/links/6144116aa609b152aa157bcf/Irrigation-and-Drainage-Systems-Engineering

Natsir, M. H., Mahmudy, W. F., Tono, M., & Nuningtyas, Y. F. (2025). Advancements in artificial intelligence and machine learning for poultry farming: Applications, challenges, and prospects. Smart Agricultural Technology, 12(February), 101307. https://doi.org/10.1016/j.atech.2025.101307

Shaikh, U. R. (2019). A Review of Agro-Industry in IoT : Applications and Challenges. 17(1), 28–33.

Veenadhari, S., Misra, B., & Singh, C. D. (2014). Machine learning approach for forecasting crop yield based on climatic parameters. 2014 International Conference on Computer Communication and Informatics: Ushering in Technologies of Tomorrow, Today, ICCCI 2014, XIII(V), 9–11. https://doi.org/10.1109/ICCCI.2014.6921718

Wang, X., Liu, S., Wang, Z., Geng, Z., Li, W., Wu, C., Xiao, Y., Yang, W., & Duan, L. (2025). GAN-based image prediction of maize growth across varieties and developmental stages. Plant Methods, 21(1). https://doi.org/10.1186/s13007-025-01430-4

Wilkens, U., Lutzeyer, I., Zheng, C., Beser, A., & Prilla, M. (2025). Augmenting diversity in hiring decisions with artificial intelligence tools. International Journal of Human Resource Management, 0(0), 1–38. https://doi.org/10.1080/09585192.2025.2492867

Zafat, I., Iqbal, A., Khan, M., Ahmad, N., & Ali Alshara, M. (2025). GenIIoT: Generative Models Aided Proactive Fault Management in Industrial Internet of Things. Information (Switzerland), 16(12), 1–27. https://doi.org/10.3390/info16121114

Zualkernan, I., Abuhani, D. A., Hussain, M. H., Khan, J., & ElMohandes, M. (2023). Machine Learning for Precision Agriculture Using Imagery from Unmanned Aerial Vehicles (UAVs): A Survey. Drones, 7(6). https://doi.org/10.3390/drones7060382.

An explainable AI-based cotton leaf disease classification using EfficientNet, Grad-Cam, Lime, and Shap