University of Oulu

Hamid Darabi, Bahram Choubin, Omid Rahmati, Ali Torabi Haghighi, Biswajeet Pradhan, Bjørn Kløve, Urban flood risk mapping using the GARP and QUEST models: A comparative study of machine learning techniques, Journal of Hydrology, Volume 569, 2019, Pages 142-154, ISSN 0022-1694, https://doi.org/10.1016/j.jhydrol.2018.12.002

Urban flood risk mapping using the GARP and QUEST models : a comparative study of machine learning techniques

Saved in:
Author: Darabi, Hamid1; Choubin, Bahram2; Rahmati, Omid3;
Organizations: 1Water Resources and Environmental Engineering, University of Oulu, P.O. Box 4300, FIN-90014 Oulu, Finland
2Department of Reclamation of Arid and Mountainous Regions, Faculty of Natural Resources, University of Tehran, Karaj, Iran
3Young Researchers and Elites Club, Khorramabad Branch, Islamic Azad University, Khorramabad, Iran
4Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), School of Information, Systems and Modelling, Faculty of Engineering and IT, University of Technology Sydney, 2007 NSW, Australia
5Department of Energy and Mineral Resources Engineering, Choongmu-gwan, Sejong University, 209 Neungdong-ro, Gwangjin-gu, Seoul 05006, Republic of Korea
Format: article
Version: accepted version
Access: embargoed
Persistent link: http://urn.fi/urn:nbn:fi-fe2019121046452
Language: English
Published: Elsevier, 2018
Publish Date: 2020-12-05
Description:

Abstract

Flood risk mapping and modeling is important to prevent urban flood damage. In this study, a flood risk map was produced with limited hydrological and hydraulic data using two state-of-the-art machine learning models: Genetic Algorithm Rule-Set Production (GARP) and Quick Unbiased Efficient Statistical Tree (QUEST). The flood conditioning factors used in modeling were: precipitation, slope, curve number, distance to river, distance to channel, depth to groundwater, land use, and elevation. Based on available reports and field surveys for Sari city (Iran), 113 points were identified as flooded areas (with each flooded zone assigned a value of 1). Different conditioning factors, including urban density, quality of buildings, age of buildings, population density, and socio-economic conditions, were taken into account to analyze flood vulnerability. In addition, the weight of these conditioning factors was determined based on expert knowledge and Fuzzy Analytical Network Process (FANP). An urban flood risk map was then produced using flood hazard and flood vulnerability maps. The area under the receiver-operator characteristic curve (AUC-ROC) and Kappa statistic were applied to evaluate model performance. The results demonstrated that the GARP model (AUC-ROC = 93.5%, Kappa = 0.86) had higher performance accuracy than the QUEST model (AUC-ROC = 89.2%, Kappa = 0.79). The results also indicated that distance to channel, land use, and elevation played major roles in flood hazard determination, whereas population density, quality of buildings, and urban density were the most important factors in terms of vulnerability. These findings demonstrate that machine learning models can help in flood risk mapping, especially in areas where detailed hydraulic and hydrological data are not available.

see all

Series: Journal of hydrology
ISSN: 0022-1694
ISSN-E: 1879-2707
ISSN-L: 0022-1694
Volume: 569
Issue: 154
Pages: 142 - 154
DOI: 10.1016/j.jhydrol.2018.12.002
OADOI: https://oadoi.org/10.1016/j.jhydrol.2018.12.002
Type of Publication: A1 Journal article – refereed
Field of Science: 212 Civil and construction engineering
1171 Geosciences
Subjects:
GIS
Copyright information: © 2018 Elsevier B.V. All rights reserved.