CROP RECOMMENDATION WITH EXPLAINABLE ARTIFICIAL INTELLIGENCE

Abstract

Agriculture plays a vital role in ensuring food security and economic stability, especially in countries where farming is a primary occupation. Selecting the appropriate crop based on environmental and soil conditions is a critical decision that directly impacts yield and productivity. Traditional crop selection methods often rely on farmer experience and generalized recommendations, which may not always be accurate or adaptable to changing climatic conditions. To address this challenge, this project proposes a Crop Recommendation System using Explainable Artificial Intelligence (XAI) that not only predicts suitable crops but also provides transparent and interpretable insights behind each recommendation. The system utilizes machine learning algorithms trained on agricultural datasets containing parameters such as soil nutrients (Nitrogen, Phosphorus, Potassium), temperature, humidity, pH level, and rainfall. Unlike conventional “black-box” models, the proposed system integrates explainability techniques such as feature importance analysis and model interpretation methods to help users understand how different factors influence crop recommendations. This improves trust, usability, and decision-making for farmers and agricultural stakeholders.