Smart Fertilizer Recommendation System

Efficient fertilizer management is critical for enhancing crop yield, ensuring sustainable agricultural practices, and minimizing environmental impact. This paper presents a web-based application that leverages machine learning techniques to predict the most suitable fertilizer type based on real-time agricultural parameters. The system integrates multiple models, including ExtraTrees, CatBoost, Decision Trees, Linear Discriminant Analysis, and Gradient Boosting, to analyze factors such as temperature, humidity, soil moisture, nutrient levels (nitrogen, phosphorus, potassium), soil type, and crop variety. The application provides accurate fertilizer recommendations tailored to specific conditions, enabling farmers and agricultural professionals to make informed decisions. Additionally, the platform offers user and admin interfaces for data input, feedback management, and access to fertilizer store information. Experimental results demonstrate the effectiveness of the proposed system in optimizing fertilizer use, improving crop productivity, and supporting sustainable farming. This work contributes to precision agriculture by combining data-driven insights with user-friendly technology to promote resource conservation and environmental sustainability.