AI-based Smart Crop Recommendation System for Sustainable Agricultural Production: A Data-driven Approach to Minimize Resource Use and Maximize Yield

This paper presents an innovative crop recommendation system powered by artificial intelligence to support sustainable agricultural practices. The proposed solution uses multiple machine learning algorithms to predict the most suitable crops based on key environmental and soil parameters, including nitrogen (N), phosphorus (P), potassium (K), temperature, humidity, pH, and rainfall. Several models were evaluated, including Logistic Regression, Decision Trees, K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Naive Bayes, Random Forests, and XGBoost. Among these, the Random Forest classifier achieved the highest accuracy at 98.2 percent. A web-based application was developed using Flask, providing an interactive and accessible platform for farmers to receive categorized crop suggestions as Recommended, Slightly Recommended, and Not Recommended. The system is designed for scalability, ease of use, and real-time responsiveness, offering a promising tool for data-driven, resource-efficient, and yield-optimized farming.