AI - Driven Decision Support System for Optimizing Soil Analysis and Crop Management in Zimbabwe

Agricultural productivity among smallholder farmers in Zimbabwe is hindered by limited access to advanced soil management technologies and sustainable farming practices. This study presents the development of an AI-driven Decision Support System (AI-DSS) designed to optimize soil analysis and crop management, addressing these challenges through real-time, data-driven insights. The AI-DSS integrates soil sensor data, satellite imagery and local weather information to provide precise, actionable recommendations that improve soil health and crop yield. Using a mixed-methods approach, we combined qualitative insights from focus group discussions with quantitative data to enhance system usability and relevance for farmers. The model, based on Decision Trees and Neural Networks, achieved a 92% accuracy rate in diagnosing soil health, resulting in a 15% improvement in crop yields during field trials. This study contributes to sustainable agriculture in Zimbabwe by delivering a scalable, context-sensitive solution tailored to the specific needs of smallholder farmers. Our findings underscore the potential of AI-driven systems to transform resource-constrained farming, providing a model adaptable to similar agricultural settings globally.