Flood Susceptibility Model Developed for Demak District, Indonesia

Strategic Insights -

Research has been conducted to develop a flood susceptibility model for Demak District, Indonesia, by integrating remote sensing data, machine learning techniques, and CMIP6 Global Climate Model (GCM) data. The study aimed to develop a reliable model for predicting flood-prone areas and providing valuable sustainable planning insights for flood risk management and adaptation to climate change. The research involved mapping current flood susceptibility using Sentinel-1 SAR data as the flood inventory and applying machine learning algorithms to predict future flood susceptibility. The results showed a significant increase in flood susceptibility, especially under higher emission scenarios, with very high susceptibility areas growing from 16.67% in the current period to 27.43% by 2081-2100.

Key Takeaways:

  • The study developed a flood susceptibility model for Demak District, Indonesia, by integrating remote sensing data, machine learning techniques, and CMIP6 Global Climate Model (GCM) data.
  • The research involved mapping current flood susceptibility using Sentinel-1 SAR data as the flood inventory and applying machine learning algorithms to predict future flood susceptibility.
  • The XGBoost model demonstrated the best performance in both current and future projections, providing valuable sustainable planning insights for flood risk management and adaptation to climate change.
  • The results showed a significant increase in flood susceptibility, especially under higher emission scenarios, with very high susceptibility areas growing from 16.67% in the current period to 27.43% by 2081-2100.
  • The study employed a multi-model ensemble approach by combining the outputs of multiple GCMs to reduce model uncertainties.
  • The research was financially supported by the Taiwan National Science and Technology Council (NSTC).
  • The study provides valuable insights for sustainable planning and adaptation to climate change in flood-prone areas.

Statistics:

  • 16.67%: current period's very high susceptibility areas
  • 27.43%: very high susceptibility areas by 2081-2100 under higher emission scenarios
  • 1031: page number of the study's report in Global Warming Focus
  • 2021-2100: time period covered by the CMIP6 GCM data
  • 3: number of Shared Socioeconomic Pathway (SSP) scenarios used in the study

Sources:

  • Integrating Cmip6 and Remote Sensing Datasets for Current and Future Flood Susceptibility Projections Using Machine Learning Under Climate Change Scenarios In Demak District for Future Sustainable Planning. Sustainability, 2025;17(18):8188.
  • National Central University, Ctr Space & Remote Sensing Res, 300 Zhongda Rd, Taoyuan 32001, Taiwan.
  • Mdpi, St Alban-Anlage 66, Ch-4052 Basel, Switzerland.