Artificial Intelligence - Machine Learning Strategies for Crop Leaf Disease Detection

This research study reviews the recent advancements and emerging trends in developments and new directions in machine learning (ML) and artificial intelligence (AI) for precision agriculture's identification and management of crop leaf diseases. The productivity of agriculture is seriously threatened by crop diseases and, traditional detection methods are often time-consuming, labour-intensive, and poses a threat to environment due to excessive chemical treatments. AI-ML approaches, particularly image processing and deep learning techniques, offer a more efficient and sustainable solution to the identified problem statement. This paper reviews various AI-ML models used for identifying plant diseases from leaf images, utilizing data from both public datasets and field conditions. It also delves into AI-ML applications in disease management, including optimized chemical spraying and disease spread forecasting, which help improve precision in treatment and reduce environmental impact. Additionally, this research study highlights the challenges faced by these AI-ML models, such as adapting to real-world farming conditions, and identifies promising areas for future research and development. These include improving model robustness in varying environments and making AI-ML technologies more accessible to farmers.