Rahman et al. (2025) Flood susceptibility mapping using supervised machine learning models: insights into predictors’ significance and models’ performance

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

Identification

• Journal: Geomatics Natural Hazards and Risk
• Year: 2025
• Date: 2025-08-07
• Authors: Zahid Ur Rahman, Meimei Zhang, Fang Chen, Safi Ullah, Mansoor Ahmad, Aamir Feroz, Samir Shehu Danhassan, Abdullah Azzam
• DOI: 10.1080/19475705.2025.2516728

Research Groups

Not specified

Short Summary

This study evaluates six supervised machine learning models to map flood susceptibility in the transboundary Kabul River Basin, identifying XGBoost as the most accurate predictive model.

Objective

• To predict flood susceptibility hotspots, identify significant flood predictors, and evaluate the performance of various supervised machine learning models in the Kabul River Basin (KRB).

Study Configuration

• Spatial Scale: Transboundary Kabul River Basin (KRB), Eastern Hindu Kush (EHK) region.
• Temporal Scale: Not specified.

Methodology and Data

• Models used: Logistic Regression (LR), Artificial Neural Network (ANN), eXtreme Gradient Boost (XGBoost), Random Forest (RF), K-Nearest Neighbors (KNN), and Naïve Bayes (NB).
• Data sources: A flood inventory consisting of 570 flooded and 570 non-flooded locations, and 16 topographical, hydrological, vegetational, and environmental predictors.

Main Results

• XGBoost demonstrated the highest predictive performance, followed by Random Forest (RF).
• Flood susceptibility is highest in the southern, southeastern, and stream-adjacent regions of the basin.

Contributions

• Provides a robust assessment of flood susceptibility for the transboundary Kabul River Basin, offering critical data to enhance early warning systems, mitigation strategies, and community resilience in a high-risk region.

Funding

Not specified

Citation

@article{Rahman2025Flood,
  author = {Rahman, Zahid Ur and Zhang, Meimei and Chen, Fang and Ullah, Safi and Ahmad, Mansoor and Feroz, Aamir and Danhassan, Samir Shehu and Azzam, Abdullah},
  title = {Flood susceptibility mapping using supervised machine learning models: insights into predictors’ significance and models’ performance},
  journal = {Geomatics Natural Hazards and Risk},
  year = {2025},
  doi = {10.1080/19475705.2025.2516728},
  url = {https://doi.org/10.1080/19475705.2025.2516728}
}