National Research and Innovatuon Agency
Doctor on Environmental Science, Universitas Indonesia
Water Resource Management, Flood Risk Management, Environmental Science
The hydrological response to changes in Land Use Land Cover (LULC) requires a multidisciplinary approach. The process involves identifying current LULC using remote sensing and GIS technology. Machine learning and deep learning algorithms can be used to analyze large-scale datasets and predict future LULC scenarios. Satellite precipitation data is essential for understanding hydrological processes and their relationship with LULC changes. Climate change models are incorporated to assess the impact of changing climatic conditions on the hydrological system. Hydrological modeling simulates water movement, accounting for factors like infiltration, evaporation, and runoff. By integrating the simulated hydrological response with digital elevation models, researchers can identify flood-prone areas and make informed decisions for land-use planning and disaster management.
Coastal areas face flood risks from land subsidence and rising sea levels. To manage these risks, monitoring land subsidence patterns is crucial. Satellite InSAR data provides detailed measurements of surface deformation, helping identify affected areas. Ground measurements validate satellite data accuracy. Predictive models based on historical data and machine learning techniques forecast future land subsidence rates and locations. Groundwater extraction contributes to subsidence, emphasizing the need for sustainable management practices. Geospatial analysis integrates subsidence data, sea level rise projections, flood maps, and vulnerability assessments. Machine learning algorithms identify high-risk areas and assess community resilience. Combining these insights improves early warning systems, land-use planning, infrastructure resilience, and adaptation measures. These efforts enhance safety, well-being, and sustainable development along the coast.