A novel approach for assessing flood risk with machine learning and multi-criteria decision-making methods

• Published in: Applied geography (Sevenoaks) Vol. 158; p. 103035
• Main Authors: Rashidi Shikhteymour, Sharareh, Borji, Moslem, Bagheri-Gavkosh, Mehdi, Azimi, Ehsan, Collins, Timothy W.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.09.2023
• Subjects: Arid and semi-arid regions; climate; discriminant analysis; drainage; Flood; flood control; geography; Hazard; Iran; multi-criteria decision making; population density; regression analysis; risk; Risk zone; support vector machines; vegetation; Vulnerability; Iran; Vulnerability; Flood; Risk zone; Arid and semi-arid regions; Hazard
• ISSN: 0143-6228
• DOI: 10.1016/j.apgeog.2023.103035

Hazardous flooding occurs across most climate zones. Owing to the lack of appropriate infrastructures and applicable predictive methods, flooding in arid and semi-arid regions may be especially damaging. Based on a study of Abarkuh County, Iran, we introduce an integrated approach for identifying high-priority flood risk areas using machine learning (ML) and multi-criteria decision-making (MCDM) methods, which is transferable to other (semi)arid regions. Results indicate that among the ML models we examined—including classification and regression tree (CART), mixture discriminant analysis (MDA), and support vector machine (SVM)—the SVM model performs best. We estimate that 75% of the study area is subject to high or very flood hazard. Our application of the Jackknife technique identifies precipitation, vegetation, and drainage density as the most important conditional factors for regional flood hazards. Our analytical network process (ANP)-decision making trial and evaluation laboratory (DEMATEL) results reveal that population density and agricultural area density have the greatest influence on flood vulnerability. Results integrating SVM and ANP-DEMATEL flood hazard and vulnerability maps indicate that 6% of the study area is at high or very high flood risk. Application of this approach can assist local authorities in identifying priority areas for flood management interventions. [Display omitted] •Introduces new, transferable approach to assess flood risk in (semi)arid areas.•Maps flood susceptibility using machine learning (ML) techniques.•Maps flood vulnerability using multi-criteria decision-making (MCDM) methods.•ML results show that 75% of the study area is highly susceptible to flooding.•Integrated ML and MCDM results show that 6% of the area is at high flood risk.