The integration of explainable artificial intelligence (XAI) in crop recommendation systems represents a transformative approach to enhancing agricultural decision-making and improving yield predictions. Traditional machine learning models often operate as “black boxes,” providing limited insights into their processes of decision-making. This lack of transparency can hinder trust among farmers and agricultural stakeholders. This paper presents a machine learning-based crop recommendation system designed to enhance agricultural planning by analyzing and identifying the most suitable crops for specific regions. With the growing demand for sustainable crop yield optimization, this model leverages extensive datasets from reputable sources such as the National Agricultural Portal, Indian Council of Agricultural Research (ICAR), and agricultural departments (at state levels), encompassing key agronomic attributes such as soil nutrient levels (nitro-gen, phosphorus, potassium), pH, temperature, humidity, and rainfall. These features capture the environmental diversity across India, enabling the model to provide region-specific recommendations that support data-driven agricultural decisions. To ensure transparency and usability, explainable AI techniques, including SHAP (SHapley Additive Explanations) and LIME (Local Interpretable Model-Agnostic Explanations), are employed. SHAP provides a global understanding of feature importance, highlighting how variables such as soil nutrient content and climate factors influence crop suitability across different conditions, whereas LIME offers case-specific insights, demonstrating the rationale behind recommendations for particular soil and climate profiles. By clarifying the model’s reasoning, these explainability methods build trust among farmers and agricultural advisors, empowering them to make informed, accessible decisions for crop se-lection tailored to local conditions.