Q-ACRY: Efficient Q-learning based Adaptive Crop Rotation technique for maximizing Yield

This research paper addresses the challenge of maximizing crop yield through an intelligent approach in crop rotation using Q-learning and rule-based decision-making. The objective is to develop an adaptable crop rotation system that continuously monitors and refines the crop rotation sequence for enhanced efficacy and sustainability . Traditional crop rotation methods based on expert knowledge often fail to optimize crop yields, necessitating the use of computational models . The proposed approach integrates the Markov decision process (MDP) and Q-learning to determine an optimal crop rotation plan. A Q-learning approach is employed here to iteratively update Q-values and identify the best sequence of crops to be planted. The rewards are estimated based on yield values, providing a realistic assessment of the impact of crop rotation on crop yield. The effectiveness of the rotation sequence is evaluated over 50 years through year-wise yield assessments. Additionally, a rule-based decision-making process is introduced to modify the rotation sequence based on yield evaluations, ensuring continuous improvement in crop yield. The model is assessed using reward, Q-value, and yield, revealing improvements of 36.13%, 2.04%, and 35.73% in respective metrics. Simulation results confirm the proposed approach’s superiority over existing methods. • Intelligent crop rotation using yield-based reward and Q-learning algorithm. • Addressing yield-based sustainability in agriculture using optimized crop rotation. • Data-driven assessment of the crop rotation strategy for informed decision making . • Continuous monitoring for adaptability of the crop sequence to boost crop yield.