Abstract

In this study, we propose a novel methodology for the automatic control of heap leaching by means of policies obtained using Reinforcement Learning (RL). This methodology models the leaching dynamics as a Markov Decision Process (MDP) whose reward function captures the economic profit of the heap leaching operation. As a case study, the leaching process of copper oxide heaps is simulated and controlled under various conditions. Results show that controlling this process using the proposed approach outperforms a heuristic control strategy that emulates real mining operations by increasing recovery rates by 2.25 times, reducing water consumption by 32.4% and acid consumption by 19.9%, and enhancing economic returns by 17.5%. This approach highlights the robustness of a Deep Reinforcement Learning (DRL) policy in heap leaching operations under significant out -of -distribution (OOD) conditions, demonstrating its adaptability and effectiveness under diverse and unpredictable conditions. Furthermore, this research highlights the potential for this methodology to be applied to other leachable ores, as it could reduce the overall environmental impact of this operation by using fewer resources.