Research Smart Farming: AI-Powered Plant Disease Detection System

This work presents a production-ready Smart Farming system that integrates deep learning, Google Gemini AI, multilingual support, and cloud deployment for accurate and accessible plant disease diagnosis. The proposed framework includes data preprocessing, targeted augmentation for class imbalance reduction, CNN-based disease classification, threshold optimization, and AI-assisted recommendation generation. The trained CNN model achieved 97.82% accuracy, 99.92% precision, 96.90% recall, 98.39% F1-score, and an AUC of 0.9998, demonstrating high reliability for real-world applications. The integration of Google Gemini 2.5 Flash enables context-aware, disease-specific recommendations in English, Hindi, and Marathi, improving the usability of the system for diverse users. Furthermore, deployment on Hugging Face Spaces using Docker and GitHub Actions provides a scalable and publicly accessible platform. The proposed system offers a practical solution for early plant disease detection and has the potential to support precision agriculture by enabling timely diagnosis and informed crop management decisions.

[1] Mohanty, S. P., Hughes, D. P., & Salathé, M. (2016). Using Deep Learning for Image-Based Plant Disease Detection. Frontiers in Plant Science, 7, 1419. [2] Ferentinos, K. P. (2018). Deep Learning Models for Plant Disease Detection and Diagnosis. Computers and Electronics in Agriculture, 145, 311–318. [3] Ramcharan, A., Baranowski, K., McCloskey, P., Ahmed, B., Legg, J., & Hughes, D. P. (2017). Deep Learning for Image-Based Cassava Disease Detection. Frontiers in Plant Science, 8, 1852. [4] Thenmozhi, K., & Reddy, U. S. (2019). Crop Disease Detection Using Deep Learning. In 2019 International Conference on Vision Towards Emerging Trends in Communication and Networking (ViTECoN). [5] Barbedo, J. G. A. (2018). Factors Influencing the Use of Deep Learning for Plant Disease Recognition. Biosystems Engineering, 172, 84–91. [6] Fawcett, T. (2006). An Introduction to ROC Analysis. Pattern Recognition Letters, 27(8), 861– 874. [7] Kamilaris, A., & Prenafeta-Boldú, F. X. (2018). Deep Learning in Agriculture: A Survey. Computers and Electronics in Agriculture, 147, 70–90. [8] Wei, J., et al. (2022). Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. Advances in Neural Information Processing Systems, 35, 24824–24837.