AgroInsight: Empowering Sustainable Agriculture through Machine Learning-Driven Crop Recommendation and Leaf Disease Prediction

Agriculture's profound significance in India's economy, culture, and society encompasses its contribution to GDP, employment generation, food security, rural sustenance, and industrial raw materials. Additionally, it upholds cultural traditions, supports poverty alleviation, and fosters environmental sustainability. Despite its crucial role, mismatches between crops and specific conditions like soil, climate, and season can lead to an array of challenges, such as reduced yields, resource wastage, soil degradation, and biodiversity loss. Concurrently, plant diseases impose threats like yield reduction, financial strain, environmental pollution, and market access issues. Addressing these demands informed practices, emphasizing sustainable methods, and leveraging disease-resistant cultivars. Amid these concerns, the integration of machine learning techniques—such as SVM, Random Forest, Decision Trees, Naive Bayes, and CNN—emerges as a solution. These methods can bolster crop recommendations by processing factors for precise suggestions and detecting leaf diseases via image analysis, ensuring timely diagnosis and effective management. Notably, this project introduces an AgroInsight that recommends crops aligned with regional and soil conditions, alongside predicting plant diseases to prevent future issues. It crucially aids in determining optimal fertilizer usage timing through historical climate data analysis, utilizing ML techniques. The implementation of such an approach holds immense potential to enhance agricultural practices, ensuring both optimal crop selection and disease management, thereby fostering a more resilient and sustainable agricultural landscape.