A RELIABLE MACHINE LEARNING FRAMEWORK FOR CROP RECOMMENDATION IN PRECISION AGRICULTURE

Abstract

Agriculture is the backbone of the Indian economy, providing livelihoods for a significant portion of the population. Selecting the most suitable crop based on soil and environmental conditions is essential for improving agricultural productivity and ensuring sustainable farming practices. Recent advancements in Machine Learning (ML) have enabled the development of intelligent decision support systems that assist farmers in making informed crop selection decisions. This study presents a machine learning-based crop recommendation system that predicts the most suitable crop using key soil and climatic parameters. The proposed model considers factors such as nitrogen (N), phosphorus (P), potassium (K), soil pH, temperature, humidity, and rainfall to generate accurate crop recommendations. Several supervised machine learning algorithms, including Random Forest (RF) and Extreme Gradient Boosting (XGBoost), are employed to analyze agricultural data and identify the most appropriate crop for specific field conditions. By integrating data-driven insights with precision agriculture, the proposed system helps farmers improve crop yield, optimize resource utilization, and support sustainable agricultural practices.