AI based paddy diseases prediction system

This research introduces an AI-based approach for paddy disease prediction and classification. A cutting-edge Convolutional Neural Network is fine-tuned on a leaf image dataset to achieve excellent diagnostic accuracy. This technique could help farmers diagnose crop diseases earlier and more accurately, allowing them to intervene and protect yields. Further development will improve the system's capabilities and holisticality: Mobile Application Deployment: Optimising the model with TensorFlow Lite and creating an intuitive mobile app for farmers to use offline in the field. Recommendation System Integration: Creating a knowledge-based module that recommends regionally available insecticides, fungicides, or cultural treatments for the projected disease. Severity Estimation: Using picture segmentation to calculate the disease's leaf area % can help determine treatment intensity. Advanced Multi-Modal Prediction Model: Integrating picture data with weather forecasts and soil sensor data to predict disease outbreaks before visual signs develop.

[1] S. Phadikar and J. Sil, "Rice disease identification using pattern recognition techniques," in Proc. 11th International Conference on Computer and Information Technology, 2008. [2] P. R. and V. K., "Detection of unhealthy region of plant leaves and classification of plant leaf diseases using texture features," in Agricultural Engineering International: CIGR Journal, vol. 16, no. 1, pp. 211-217, 2014. [3] K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. [4] S. P. Mohanty, D. P. Hughes, and M. Salathé, "Using Deep Learning for Image-Based Plant Disease Detection," in Frontiers in Plant Science, vol. 7, p. 1419, 2016. [5] K. P. A. and S. M. B., "Detection of paddy leaf diseases using image processing," in Proc. 3rd International Conference on Signal Processing, Communication and Networking (ICSCN), 2015. [6] M. Tan and Q. V. Le, "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks," in Proc. International Conference on Machine Learning (ICML), 2019.