Ghose et al. (2025) Predictive Flood Susceptibility Modelling with Machine Learning: Insights from The Baitarani River Basin, Odisha

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Springer Link (Chiba Institute of Technology)
• Year: 2025
• Date: 2025-12-19
• Authors: Dillip Kumar Ghose, Bibhu Prasad Mishra, Sourav Ghose
• DOI: 10.1051/epjconf/202534305016/pdf

Research Groups

Not explicitly stated in the provided text.

Short Summary

This study analyzed historical flood records from 2003 to 2023 to delineate flood-susceptible zones in the Baitarani River Basin using Fuzzy Support Vector Machine (FSVM) and Simulated Annealing-optimized FSVM (SA-FSVM) models. The SA-FSVM model achieved superior predictive performance (AUROC 0.91), identifying low-lying coastal zones as highly vulnerable to flooding.

Objective

• To analyze historical flood records from 2003 to 2023 to delineate flood-susceptible zones within the Baitarani River Basin (BRB) using machine learning models.

Study Configuration

• Spatial Scale: Baitarani River Basin (BRB)
• Temporal Scale: 2003 to 2023 (21 years)

Methodology and Data

• Models used: Fuzzy Support Vector Machine (FSVM), Simulated Annealing-optimized Fuzzy Support Vector Machine (SA-FSVM)
• Data sources: Historical flood records, multiple contributing environmental factors (implied)

Main Results

• The SA-FSVM model achieved the highest predictive performance with an Area Under the Receiver Operating Characteristic (AUROC) value of 0.91.
• Low-lying coastal zones, particularly in the southeastern portions of the Baitarani River Basin, were identified as highly vulnerable to flooding.

Contributions

• Demonstrates the effective application of advanced machine learning techniques (FSVM and SA-FSVM) for flood susceptibility mapping.
• Provides specific flood susceptibility mapping for the Baitarani River Basin, aiding in disaster management and planning.
• Highlights the importance of these techniques in guiding flood mitigation strategies and enhancing disaster preparedness.

Funding

Not explicitly stated in the provided text.

Citation

@article{Ghose2025Predictive,
  author = {Ghose, Dillip Kumar and Mishra, Bibhu Prasad and Ghose, Sourav},
  title = {Predictive Flood Susceptibility Modelling with Machine Learning: Insights from The Baitarani River Basin, Odisha},
  journal = {Springer Link (Chiba Institute of Technology)},
  year = {2025},
  doi = {10.1051/epjconf/202534305016/pdf},
  url = {https://doi.org/10.1051/epjconf/202534305016/pdf}
}