Rashid et al. (2026) Integrated Data-Driven Multi-Criteria Analysis and Machine Learning Approaches for Assessment of Flood Susceptibility Mapping

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

Identification

• Journal: Water
• Year: 2026
• Date: 2026-04-01
• Authors: Muhammad Rashid, S. M. Akram Ullah, Farnaz, Saba Farooq, Saif Haider, Isabella Serena Liso, Mario Parise
• DOI: 10.3390/w18070844

Research Groups

Specific research groups, labs, or departments are not explicitly mentioned in the provided text. The study focuses on the Mohmand Dam catchment in Pakistan.

Short Summary

This study identifies key factors contributing to flood occurrence and maps flood susceptibility in the Mohmand Dam catchment, Pakistan, finding that rainfall, LULC, and soil texture are the most influential factors, with approximately 31.67% (4320.40 km²) of the area at high flood risk.

Objective

• To identify the key factors contributing to flood occurrence in the Mohmand Dam catchment, Pakistan.
• To produce a flood susceptibility map for the Mohmand Dam catchment using multi-criteria analysis and machine learning models.

Study Configuration

• Spatial Scale: Mohmand Dam catchment, Pakistan, covering an area of approximately 4320.40 square kilometers.
• Temporal Scale: Not explicitly defined for the data used in the current study, though previous attention to flood events in the region was noted for 2010 and 2022.

Methodology and Data

• Models used:
  • Multi-criteria analyses: Analytic Hierarchy Process (AHP), Fuzzy Analytic Hierarchy Process (FAHP).
  • Machine learning models: Logistic Regression, K-Nearest Neighbors, Random Forest, Support Vector Machine, Multi-Layer Perceptron.
• Data sources: Various geospatial datasets processed via Google Earth Engine to extract fourteen flood-related indices. Specific types of raw data (e.g., satellite imagery, meteorological data) are implied but not detailed.

Main Results

• Rainfall, Land Use/Land Cover (LULC), and soil texture were identified as the most influential factors contributing to flood susceptibility, each accounting for 11.11% of the influence.
• The Random Forest machine learning model demonstrated superior predictive performance compared to the AHP and FAHP multi-criteria analysis techniques.
• The flood susceptibility map revealed that approximately 31.67% (4320.40 km²) of the Mohmand Dam catchment is classified as having a high flood risk.

Contributions

• Provides a comprehensive methodology for flood susceptibility mapping by integrating both multi-criteria analysis (AHP, FAHP) and multiple machine learning models.
• Identifies and quantifies the relative importance of key flood influencing factors specific to the Mohmand Dam catchment.
• Generates a detailed and spatially explicit flood susceptibility map, highlighting high-risk areas within the study region.
• Offers a valuable tool and framework for planners, policymakers, and disaster management authorities to develop effective flood mitigation and watershed management strategies.

Funding

Not explicitly mentioned in the provided text.

Citation

@article{Rashid2026Integrated,
  author = {Rashid, Muhammad and Ullah, S. M. Akram and Farnaz and Farooq, Saba and Haider, Saif and Liso, Isabella Serena and Parise, Mario},
  title = {Integrated Data-Driven Multi-Criteria Analysis and Machine Learning Approaches for Assessment of Flood Susceptibility Mapping},
  journal = {Water},
  year = {2026},
  doi = {10.3390/w18070844},
  url = {https://doi.org/10.3390/w18070844}
}