Stormwater management modeling and machine learning for flash flood susceptibility prediction in Wadi Qows, Saudi Arabia

IF 0.6 Q4 WATER RESOURCES
Fahad Alamoudi, Mohamed Saber, Sameh A. Kantoush, Tayeb Boulmaiz, Karim I. Abdrabo, Hadir Abdelmoneim, Tetsuya Sumi
{"title":"Stormwater management modeling and machine learning for flash flood susceptibility prediction in Wadi Qows, Saudi Arabia","authors":"Fahad Alamoudi, Mohamed Saber, Sameh A. Kantoush, Tayeb Boulmaiz, Karim I. Abdrabo, Hadir Abdelmoneim, Tetsuya Sumi","doi":"10.3178/hrl.17.62","DOIUrl":null,"url":null,"abstract":"Predicting flash flood-prone areas is essential for proactive disaster management. ‎However, such predictions are challenging to obtain accurately with physical hydrological models owing to the scarcity of flood observation stations and the lack of monitoring systems. This study aims ‎to compare machine learning (ML) models (Random Forest, ‎Light, and CatBoost) and the Personal ‎Computer Storm Water Management Model ‎‎(PCSWMM) hydrological ‎model to predict flash flood susceptibility ‎‎maps (FFSMs) in an arid region (Wadi Qows in ‎Saudi Arabia). Nine independent factors ‎that influence FFSMs in the study area were ‎assessed. ‎Approximately 300 flash flood sites were identified through a post-flood survey after the ‎‎extreme flash floods of 2009 in Jeddah city. The dataset was randomly split into 70 percent for training and 30 percent for testing. The results ‎show that the area ‎under the receiver operating curve (ROC) values were ‎above 95% for all tested ‎models, indicating evident accuracy. The FFSMs developed by the ML ‎‎methods show acceptable agreement with the flood inundation map created using the ‎PCSWMM in terms of flood extension. Planners and officials can use the outcomes of this study to improve the mitigation measures for flood-prone regions in Saudi Arabia.","PeriodicalId":13111,"journal":{"name":"Hydrological Research Letters","volume":"158 1","pages":"0"},"PeriodicalIF":0.6000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Hydrological Research Letters","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3178/hrl.17.62","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"WATER RESOURCES","Score":null,"Total":0}
引用次数: 0

Abstract

Predicting flash flood-prone areas is essential for proactive disaster management. ‎However, such predictions are challenging to obtain accurately with physical hydrological models owing to the scarcity of flood observation stations and the lack of monitoring systems. This study aims ‎to compare machine learning (ML) models (Random Forest, ‎Light, and CatBoost) and the Personal ‎Computer Storm Water Management Model ‎‎(PCSWMM) hydrological ‎model to predict flash flood susceptibility ‎‎maps (FFSMs) in an arid region (Wadi Qows in ‎Saudi Arabia). Nine independent factors ‎that influence FFSMs in the study area were ‎assessed. ‎Approximately 300 flash flood sites were identified through a post-flood survey after the ‎‎extreme flash floods of 2009 in Jeddah city. The dataset was randomly split into 70 percent for training and 30 percent for testing. The results ‎show that the area ‎under the receiver operating curve (ROC) values were ‎above 95% for all tested ‎models, indicating evident accuracy. The FFSMs developed by the ML ‎‎methods show acceptable agreement with the flood inundation map created using the ‎PCSWMM in terms of flood extension. Planners and officials can use the outcomes of this study to improve the mitigation measures for flood-prone regions in Saudi Arabia.
沙特阿拉伯Wadi Qows洪水易感性预测的雨水管理模型和机器学习
预测易发山洪的地区对于积极主动的灾害管理至关重要。然而,由于洪水观测站的缺乏和监测系统的缺乏,这种预测很难用物理水文模型准确地获得。本研究旨在比较机器学习(ML)模型(Random Forest、Light和CatBoost)和个人计算机雨水管理模型(PCSWMM)水文模型,以预测干旱地区(沙特阿拉伯的Wadi Qows)的山洪易发性地图(FFSMs)。评估了影响研究区域FFSMs的9个独立因素。2009年吉达市极端山洪暴发后,通过灾后调查确定了大约300个山洪暴发点。数据集被随机分成70%用于训练,30%用于测试。结果表明,所有测试模型的受试者工作曲线(ROC)值下面积均在95%以上,具有较好的准确性。在洪水扩展方面,ML方法开发的FFSMs与使用PCSWMM绘制的洪水淹没图具有良好的一致性。规划者和官员可以利用这项研究的结果来改进沙特阿拉伯洪水易发地区的减灾措施。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
1.90
自引率
18.20%
发文量
9
审稿时长
10 weeks
期刊介绍: Hydrological Research Letters (HRL) is an international and trans-disciplinary electronic online journal published jointly by Japan Society of Hydrology and Water Resources (JSHWR), Japanese Association of Groundwater Hydrology (JAGH), Japanese Association of Hydrological Sciences (JAHS), and Japanese Society of Physical Hydrology (JSPH), aiming at rapid exchange and outgoing of information in these fields. The purpose is to disseminate original research findings and develop debates on a wide range of investigations on hydrology and water resources to researchers, students and the public. It also publishes reviews of various fields on hydrology and water resources and other information of interest to scientists to encourage communication and utilization of the published results. The editors welcome contributions from authors throughout the world. The decision on acceptance of a submitted manuscript is made by the journal editors on the basis of suitability of subject matter to the scope of the journal, originality of the contribution, potential impacts on societies and scientific merit. Manuscripts submitted to HRL may cover all aspects of hydrology and water resources, including research on physical and biological sciences, engineering, and social and political sciences from the aspects of hydrology and water resources.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信