Flash-flood susceptibility mapping based on XGBoost, random forest and boosted regression trees

Abstract

Historical exploration of flash flood events and producing flash-flood susceptibility maps are crucial steps for decision makers in disaster management. In this article, classification and regression tree (CART) methodology and its ensemble models of random forest (RF), boosted regression trees (BRT) and extreme gradient boosting (XGBoost) were implemented to create a flash-flood susceptibility map of the Bâsca Chiojdului River Basin, one of the areas in Romania that is constantly exposed to flash floods. The torrential areas including 962 flash flood events were delineated from orthophotomaps and field observations. Furthermore, a set of conditioning forces to explain the flash floods was constructed which included aspect, land use and land cover (LULC), hydrological soil groups lithology, slope, topographic wetness index (TWI), topographic position index (TPI), profile curvature, convergence index and stream power index (SPI). All models indicated the slope as the most important factor triggering the flash flood occurrence. The highest area under the curve (AUC) was achieved by the RF model (AUC = 0.956), followed by the BRT model (AUC = 0.899), XGBoost model (AUC = 0.892) and CART model (AUC = 0.868), respectively. The results showed that the central part of the Bâsca Chiojdului river basin, which covers approximately 30% of the study area, is more susceptible to flash flooding.

Keywords:

• Bâsca Chiojdului
• flash flood phenomena
• machine learning
• GIS
• torrential areas

Disclosure statement

This manuscript has not been published or presented elsewhere in part or in its entirety and is not under consideration by another journal. There are no conflicts of interest to declare.

Rahebeh Abedi: Writing- original draft, Software, Formal analysis, Visualization, Data curation. Romulus Costache: Formal analysis; Writing- original draft, Visualization. Hossein Shafizadeh-Moghadam: Project administration, Software, Writing, Review and editing. Quoc Bao Pham: Supervision, Writing, Review, Editing.

Funding

This work was supported by a grant of the Romanian Ministry of Education and Research, CNCS – UEFISCDI, project number PN-III-P1-1.1-PD-2019-0424-P, within PNCDI III.

Data availability statement

The data that supports the findings of this study is available from the corresponding author, upon reasonable request.

Correction Statement

This article has been republished with minor changes. These changes do not impact the academic content of the article.