<![CDATA[Coastal regions are highly dynamic environments that experience continuous land cover changes driven by urban expansion, aquaculture development, agricultural activities, shoreline erosion, and ecosystem degradation. Monitoring these changes is essential for supporting sustainable coastal management, environmental conservation, and climate adaptation. This study evaluates the integration of remote sensing and artificial intelligence (AI) for monitoring land cover dynamics in the coastal area of Cirebon Regency, Indonesia, during the period 2015–2025. Multi-temporal Landsat satellite imagery was processed through atmospheric and geometric corrections, cloud masking, image compositing, and feature extraction. Spectral indices, including the Normalized Difference Water Index (NDWI), Normalized Difference Built-up Index (NDBI), Normalized Difference Vegetation Index (NDVI), and Mangrove Vegetation Index (MVI), were employed to improve the discrimination of water bodies, mangroves, built-up areas, and other vegetation. A Random Forest algorithm was applied to classify land cover and detect spatial and temporal changes with improved accuracy and efficiency compared with conventional approaches. The results indicate a continuous expansion of built-up areas accompanied by a substantial decline in mangrove forests and water bodies, reflecting increasing anthropogenic pressure on coastal ecosystems. Although other vegetation exhibited a moderate increase, it cannot compensate for the ecological functions lost through mangrove degradation, particularly in coastal protection, biodiversity conservation, and blue carbon storage. These findings provide valuable baseline information for sustainable coastal spatial planning, ecosystem restoration, disaster risk reduction, and environmental impact assessment of future infrastructure developments, including the Giant Sea Wall (GSW), while demonstrating the effectiveness of AI-assisted remote sensing for long-term coastal resource management in Indonesia]]>
Copyrights © 2026
