Published Paper Details:

Agriculture plays a vital role in economic growth and food security, but farmers often face challenges in crop selection, disease detection, soil analysis, fertilizer management, and yield prediction due to changing environmental conditions and lack of proper agricultural guidance. This project proposes an AI Powered Crop Recommendation System that uses Machine Learning and Deep Learning techniques to support smart and sustainable farming practices. The system analyzes soil properties, weather conditions, and agricultural parameters such as Nitrogen (N), Phosphorus (P), Potassium (K), temperature, humidity, rainfall, and pH level to recommend suitable crops using Random Forest and XGBoost algorithms. Soil type prediction is performed using a Convolutional Neural Network (CNN) model, while plant disease detection is carried out using a MobileNet-based CNN model that identifies diseases from leaf images and provides fertilizer suggestions along with disease prevention and management strategies. Additionally, crop yield prediction is performed using an LSTM model by considering soil conditions, climatic factors, and geographical location. The proposed system also supports real-time agricultural monitoring and helps farmers optimize the use of water, fertilizers, and other resources efficiently. By integrating Artificial Intelligence, Machine Learning, and Deep Learning technologies into agriculture, the system enables farmers to make accurate and data-driven decisions related to crop selection, disease control, fertilizer usage, and yield optimization. Overall, the project aims to improve agricultural productivity, reduce farming risks, promote sustainable farming practices, enhance farmer profitability, and contribute toward global food security and modern precision agriculture.