Industrial Park Land-Use Composition and Occupancy Performance: Explaining Nonlinear Determinants of Industrial Land Absorption in South Korea
This study utilizes interpretable machine learning on 1,161 South Korean industrial parks to demonstrate that non-linear thresholds in internal land-use composition, particularly the balance between industrial and public facility land, are more decisive for occupancy performance than broad locational factors, thereby advocating for a policy shift from land expansion to targeted functional rebalancing.