A Data-Driven Decision Support Framework for Crop Recommendation Based on Soil and Climatic Factors

Crop productivity is increasingly challenged by soil degradation, climate variability, and the absence of reliable, data-driven decision-support tools, particularly in rural and underdeveloped regions. Farmers often rely on experience-based or generalized crop calendars that fail to capture local soil characteristics and dynamic climatic conditions, leading to inefficient resource use and reduced yields. To address this problem, this study presents an intelligent crop recommendation system based on Artificial Intelligence and Machine Learning that integrates soil parameters, historical climate data, and real-time weather information. The proposed framework employs a hybrid learning approach to analyze multi-source agricultural data and generate region-specific crop recommendations. Experimental results demonstrate improved recommendation accuracy, adaptability across agro-climatic zones, and enhanced resource efficiency compared to conventional selection methods. The findings indicate that the system can support informed decision-making while promoting sustainable agricultural practices. The proposed solution can be deployed as a decision-support tool for farmers, agricultural extension services, and policymakers, enabling optimized crop planning, reduced financial risk, and improved productivity, particularly for small and marginal farmers.