International Journal of Advanced Research in Computer and Communication Engineering

Abstract: Soil fertility plays a crucial role in agricultural productivity, yet farmers often struggle to identify nutrient deficiencies and select suitable fertilizers. Traditional methods are time-consuming, costly, and lack personalized recommendations. To address this, we propose Soil IQ, an Explainable AI (XAI)–based system that predicts soil nutrient levels (N, P, K, pH, organic carbon) and recommends optimal fertilizers with transparent model explanations. The system uses machine learning algorithms such as Random Forest and Decision Trees, combined with SHAP-based explainability, to generate interpretable recommendations. Experimental results demonstrate high accuracy in nutrient prediction and improved decision-making for fertilizer selection. Soil IQ empowers farmers with data-driven insights, enhances crop productivity, and promotes sustainable fertilizer usage.

Keywords: Soil Analysis, Fertilizer Recommendation, Explainable AI, Machine Learning, Agriculture, SHAP.

Downloads: | DOI: 10.17148/IJARCCE.2025.1411118