Implementation of a GeoAI Model to Detect Ground-Mounted Photovoltaic Power Stations in Thailand

A comprehensive and publicly available geospatial database of PV installations is crucial for effective policymaking and infrastructure planning towards Thailand’s carbon neutrality and net-zero greenhouse gas emissions plan. This study introduces a national-scale mapping framework for ground-mounted photovoltaic power stations using geospatial artificial intelligence (GeoAI). A pretrained deep learning model is applied to Sentinel-2 satellite imagery to delineate solar photovoltaic sites. The outputs are cross-checked and verified with official statistical data. Geospatial analyses and regression-based comparisons are conducted to validate the infrastructure inventory. The results indicate that all registered solar PV sites were identified, with a total mapped area of 14.55 km2 and a capacity of 506.4 megawatts. Furthermore, the research clarifies that without official administrative ownership data, GeoAI cannot be applied more broadly for policy evaluation. Closing these data infrastructure gaps is necessary to support more effective energy planning and monitoring in Thailand.