Explainable AI-Based Smart Farming System for Crop Recommendation and Irrigation Optimization

Agriculture is a vital sector for ensuring food security and sustainable development, particularly in developing countries like India. However, traditional farming practices often rely on manual decision-making, leading to inefficient resource utilization and reduced crop productivity. This paper proposes an Explainable Artificial Intelligence (XAI)-based smart farming system integrated with the Internet of Robotic Things (IoRT) to provide accurate crop recommendations and optimized irrigation strategies. The proposed system leverages real-time data collected from sensors, including soil moisture, temperature, humidity, rainfall, and pH levels, and processes it using machine learning models such as Decision Tree and Random Forest. To address the limitations of black-box models, XAI techniques such as SHAP and LIME are incorporated to interpret model predictions by identifying the contribution of each input feature. The system not only generates reliable predictions but also provides transparent and understandable explanations, enabling farmers to make informed decisions. Experimental results demonstrate improved accuracy, efficiency, and resource optimization compared to traditional approaches. The integration of IoRT, machine learning, and explainable AI enhances system reliability, promotes sustainable agricultural practices, and supports real-time decision-making in modern precision farming.