Crop Recommendation System with XAI

Abstract

Modern agriculture is increasingly leveraging advanced technologies like XAI for improving crop recommendation systems. This paper presents a unique approach that integrates XAI methodologies into crop recommendation frameworks to improve transparency and interpretability. By harnessing machine learning models such as classification & regression techniques and ensemble techniques alongside XAI explanations, our system offers personalized crop suggestions based on environmental and geographic data. Our study contributes to the agricultural sector by enhancing the transparency of crop recommendation systems using XAI, allowing farmers to grasp the underlying factors influencing each recommendation. We investigate various machine learning algorithms and their interpretability within the context of crop selection, emphasizing user-friendly design and actionable insights. This research aims to advance agricultural decision-making by advocating for the adoption of XAI-driven crop recommendation systems, empowering farmers with accessible and understandable information to optimize crop yield and sustainability. This approach not only supports informed decision-making but also fosters trust and acceptance of AI-driven solutions in agriculture. Keywords Crop recommendation, ML algorithms, XAI, Agriculture, Decision support, Precision farming