Urban flash flood hazard mapping using machine learning, Bahir Dar, Ethiopia

Increased frequency and magnitude of flooding pose a significant natural hazard to urban areas worldwide. Mapping flood hazard areas are crucial for mitigating potential damage to human life and property. However, conventional hydrodynamic approaches are hindered by their extensive data requirements...

Descripción completa

Detalles Bibliográficos
Autores principales: Leggesse, E. S., Derseh, W. A., Zimale, F. A., Tilahun, Seifu A., Meshesha, M. A.
Formato: Journal Article
Lenguaje:Inglés
Publicado: IWA Publishing 2024
Materias:
Acceso en línea:https://hdl.handle.net/10568/152514
_version_ 1855528822921756672
author Leggesse, E. S.
Derseh, W. A.
Zimale, F. A.
Tilahun, Seifu A.
Meshesha, M. A.
author_browse Derseh, W. A.
Leggesse, E. S.
Meshesha, M. A.
Tilahun, Seifu A.
Zimale, F. A.
author_facet Leggesse, E. S.
Derseh, W. A.
Zimale, F. A.
Tilahun, Seifu A.
Meshesha, M. A.
author_sort Leggesse, E. S.
collection Repository of Agricultural Research Outputs (CGSpace)
description Increased frequency and magnitude of flooding pose a significant natural hazard to urban areas worldwide. Mapping flood hazard areas are crucial for mitigating potential damage to human life and property. However, conventional hydrodynamic approaches are hindered by their extensive data requirements and computational expenses. As an alternative solution, this paper explores the use of machine learning (ML) techniques to map flood hazards based on readily available geo-environmental variables. We employed various ML classifiers, including decision tree (DT), random forest (RF), XGBoost (XGB), and k-nearest neighbor (kNN), to assess their performance in flood hazard mapping. Model evaluation was conducted using the area under the receiver operating characteristic curve (AUC) and root mean square error (RMSE). Our results demonstrated promising outcomes, with AUC values of 93% (DT), 97% (RF), 98% (XGB), and 91% (kNN) for the validation dataset. RF and XGB have slightly higher performance than DT and kNN and distance to river was the most important factor. The study highlights the potential of ML for urban flood modeling, offering reasonable accuracy and supporting early warning systems. By leveraging available geo-environmental variables, ML techniques provide valuable insights into flood hazard mapping, aiding in effective urban planning and disaster management strategies.
format Journal Article
id CGSpace152514
institution CGIAR Consortium
language Inglés
publishDate 2024
publishDateRange 2024
publishDateSort 2024
publisher IWA Publishing
publisherStr IWA Publishing
record_format dspace
spelling CGSpace1525142025-10-26T12:57:04Z Urban flash flood hazard mapping using machine learning, Bahir Dar, Ethiopia Leggesse, E. S. Derseh, W. A. Zimale, F. A. Tilahun, Seifu A. Meshesha, M. A. flash flooding urban areas weather hazards mapping risk management machine learning techniques modelling land use land cover Increased frequency and magnitude of flooding pose a significant natural hazard to urban areas worldwide. Mapping flood hazard areas are crucial for mitigating potential damage to human life and property. However, conventional hydrodynamic approaches are hindered by their extensive data requirements and computational expenses. As an alternative solution, this paper explores the use of machine learning (ML) techniques to map flood hazards based on readily available geo-environmental variables. We employed various ML classifiers, including decision tree (DT), random forest (RF), XGBoost (XGB), and k-nearest neighbor (kNN), to assess their performance in flood hazard mapping. Model evaluation was conducted using the area under the receiver operating characteristic curve (AUC) and root mean square error (RMSE). Our results demonstrated promising outcomes, with AUC values of 93% (DT), 97% (RF), 98% (XGB), and 91% (kNN) for the validation dataset. RF and XGB have slightly higher performance than DT and kNN and distance to river was the most important factor. The study highlights the potential of ML for urban flood modeling, offering reasonable accuracy and supporting early warning systems. By leveraging available geo-environmental variables, ML techniques provide valuable insights into flood hazard mapping, aiding in effective urban planning and disaster management strategies. 2024-09-01 2024-09-30T21:12:03Z 2024-09-30T21:12:03Z Journal Article https://hdl.handle.net/10568/152514 en Open Access IWA Publishing Leggesse, E. S.; Derseh, W. A.; Zimale, F. A.; Tilahun, Seifu Admassu; Meshesha, M. A. 2024. Urban flash flood hazard mapping using machine learning, Bahir Dar, Ethiopia. Journal of Hydroinformatics, 26(9):2124-2145. [doi: https://doi.org/10.2166/hydro.2024.277]
spellingShingle flash flooding
urban areas
weather hazards
mapping
risk management
machine learning
techniques
modelling
land use
land cover
Leggesse, E. S.
Derseh, W. A.
Zimale, F. A.
Tilahun, Seifu A.
Meshesha, M. A.
Urban flash flood hazard mapping using machine learning, Bahir Dar, Ethiopia
title Urban flash flood hazard mapping using machine learning, Bahir Dar, Ethiopia
title_full Urban flash flood hazard mapping using machine learning, Bahir Dar, Ethiopia
title_fullStr Urban flash flood hazard mapping using machine learning, Bahir Dar, Ethiopia
title_full_unstemmed Urban flash flood hazard mapping using machine learning, Bahir Dar, Ethiopia
title_short Urban flash flood hazard mapping using machine learning, Bahir Dar, Ethiopia
title_sort urban flash flood hazard mapping using machine learning bahir dar ethiopia
topic flash flooding
urban areas
weather hazards
mapping
risk management
machine learning
techniques
modelling
land use
land cover
url https://hdl.handle.net/10568/152514
work_keys_str_mv AT leggessees urbanflashfloodhazardmappingusingmachinelearningbahirdarethiopia
AT dersehwa urbanflashfloodhazardmappingusingmachinelearningbahirdarethiopia
AT zimalefa urbanflashfloodhazardmappingusingmachinelearningbahirdarethiopia
AT tilahunseifua urbanflashfloodhazardmappingusingmachinelearningbahirdarethiopia
AT mesheshama urbanflashfloodhazardmappingusingmachinelearningbahirdarethiopia