AI-Driven Water Quality Assessment and Crop Suitability System

Water quality assessment is crucial for sustainable agriculture and food security. Contaminated water can significantly impact crop yield and environmental health. This research presents an AI-powered system for water quality classification and crop suitability prediction. Using machine learning models, including Random Forest, Gaussian Naive Bayes, and XGBoost, the system classifies water into highly preferred, moderately preferred, and least preferred categories. The Random Forest model achieved the highest performance with 94.2% accuracy, 92.5% precision, 93.8% recall, and 93.1% F1-score. Additionally, it provides a crop recommendation system tailored to the classified water quality. The proposed framework includes a web-based application that enables real-time interaction with end- users. This facilitates rapid decision-making for farmers and agricultural agencies, contributing to efficient water resource utilization and improved crop planning.