Timber Harvest Planning Using Reinforcement Learning: A Feasibility Study

This study developed a forest management plan model using reinforcement learning (Q-learning) to optimize both the economic and ecological functions of forests. Management objectives for national forests were established, and forest conditions were analyzed using GIS spatial data and administrative records. A 60-year forest management plan was formulated to predict timber production and management performance across different regions and time periods. Our analysis revealed that Scenario 3 (Carbon Storage Priority) demonstrated the highest economic value, starting at approximately KRW 576.2 billion in the initial period and escalating to KRW 775.7 billion over six 10-year periods, totaling 60 years. In addition to its economic performance, Scenario 3 effectively improved forest age class structure and ensured a stable timber supply, making it the most balanced approach for sustainable forest management. By focusing on carbon storage as a key management goal, this approach highlights the potential for achieving both economic and environmental benefits concurrently. These results suggest that reinforcement learning is a powerful tool for developing long-term forest management strategies that address multiple objectives, including economic viability, ecological sustainability, and resource optimization.