DEM resolution effects on machine learning performance for flood probability mapping

IF 2.4 3区 环境科学与生态学 Q2 ENGINEERING, CIVIL
Mohammadtaghi Avand , Alban Kuriqi , Majid Khazaei , Omid Ghorbanzadeh
{"title":"DEM resolution effects on machine learning performance for flood probability mapping","authors":"Mohammadtaghi Avand ,&nbsp;Alban Kuriqi ,&nbsp;Majid Khazaei ,&nbsp;Omid Ghorbanzadeh","doi":"10.1016/j.jher.2021.10.002","DOIUrl":null,"url":null,"abstract":"<div><p>Floods are among the devastating natural disasters that occurred very frequently in arid regions during the last decades. Accurate assessment of the flood susceptibility mapping is crucial in sustainable development. It helps respective authorities to prevent as much as possible their irreversible consequences. The Digital Elevation Model (DEM) spatial resolution is one of the most crucial base layer factors for modeling Flood Probability Maps (FPMs). Therefore, the main objective of this study was to assess the influence of the spatial resolution of the DEMs 12.5 m (ALOS PALSAR) and 30 m (ASTER) on the accuracy of flood probability prediction using three machine learning models (MLMs), including Random Forest (RF), Artificial Neural Network (ANN), and Generalized Linear Model (GLM). This study selected 14 causative factors in the flood as independent variables, and 220 flood locations were selected as dependent variables. Dependent variables were divided into training (70%) and validation (30%) for flood susceptibility modeling. The Receiver Operating Characteristic Curve (ROC), Kappa index, accuracy, and other statistical criteria were used to evaluate the models' accuracy. The results showed that resolving the DEM alone cannot significantly affect the accuracy of flood probability prediction regardless of the applied MLM and independently of the statistical model used to assess the performance accuracy. In contrast, the factors such as altitude, precipitation, and distance from the river have a considerable impact on floods in this region. Also, the evaluation results of the models showed that the RF (AUC<sub>12.5,30m</sub> = 0.983, 0.975) model is more accurate in preparing the FPM than the ANN (AUC<sub>12.5,30m</sub> = 0.949, 0.93) and GLM (AUC<sub>12.5,30m</sub> = 0.965, 0.949) models. This study's solution-oriented findings might help water managers and decision-makers to make the most effective adaptation and mitigation measures against potential flooding.</p></div>","PeriodicalId":49303,"journal":{"name":"Journal of Hydro-environment Research","volume":null,"pages":null},"PeriodicalIF":2.4000,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1570644321000769/pdfft?md5=13acefc3fd1e4c0759676b3882f1f2d6&pid=1-s2.0-S1570644321000769-main.pdf","citationCount":"48","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Hydro-environment Research","FirstCategoryId":"93","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1570644321000769","RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, CIVIL","Score":null,"Total":0}
引用次数: 48

Abstract

Floods are among the devastating natural disasters that occurred very frequently in arid regions during the last decades. Accurate assessment of the flood susceptibility mapping is crucial in sustainable development. It helps respective authorities to prevent as much as possible their irreversible consequences. The Digital Elevation Model (DEM) spatial resolution is one of the most crucial base layer factors for modeling Flood Probability Maps (FPMs). Therefore, the main objective of this study was to assess the influence of the spatial resolution of the DEMs 12.5 m (ALOS PALSAR) and 30 m (ASTER) on the accuracy of flood probability prediction using three machine learning models (MLMs), including Random Forest (RF), Artificial Neural Network (ANN), and Generalized Linear Model (GLM). This study selected 14 causative factors in the flood as independent variables, and 220 flood locations were selected as dependent variables. Dependent variables were divided into training (70%) and validation (30%) for flood susceptibility modeling. The Receiver Operating Characteristic Curve (ROC), Kappa index, accuracy, and other statistical criteria were used to evaluate the models' accuracy. The results showed that resolving the DEM alone cannot significantly affect the accuracy of flood probability prediction regardless of the applied MLM and independently of the statistical model used to assess the performance accuracy. In contrast, the factors such as altitude, precipitation, and distance from the river have a considerable impact on floods in this region. Also, the evaluation results of the models showed that the RF (AUC12.5,30m = 0.983, 0.975) model is more accurate in preparing the FPM than the ANN (AUC12.5,30m = 0.949, 0.93) and GLM (AUC12.5,30m = 0.965, 0.949) models. This study's solution-oriented findings might help water managers and decision-makers to make the most effective adaptation and mitigation measures against potential flooding.

Abstract Image

DEM分辨率对洪水概率映射机器学习性能的影响
洪水是过去几十年来干旱地区频繁发生的破坏性自然灾害之一。准确评估洪水易感性地图对可持续发展至关重要。它有助于有关当局尽可能地防止其不可逆转的后果。数字高程模型(DEM)空间分辨率是洪水概率图(FPMs)建模中最关键的基础层因子之一。因此,本研究的主要目的是评估dem 12.5 m (ALOS PALSAR)和30 m (ASTER)空间分辨率对随机森林(RF)、人工神经网络(ANN)和广义线性模型(GLM) 3种机器学习模型(MLMs)洪水概率预测精度的影响。本研究选取洪水的14个致病因素作为自变量,选取220个洪水发生地作为因变量。因变量分为训练(70%)和验证(30%),用于洪水敏感性建模。采用受试者工作特征曲线(ROC)、Kappa指数、准确率等统计标准评价模型的准确性。结果表明,无论采用何种MLM,无论采用何种统计模型,单独解析DEM都不能显著影响洪水概率预测的精度。相比之下,海拔、降水、离河距离等因素对该地区的洪水影响较大。模型的评价结果表明,RF (AUC12.5,30m = 0.983, 0.975)模型比ANN (AUC12.5,30m = 0.949, 0.93)和GLM (AUC12.5,30m = 0.965, 0.949)模型更准确地制备FPM。这项研究以解决方案为导向的发现可能有助于水资源管理者和决策者制定最有效的适应和缓解措施,以应对潜在的洪水。
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
Journal of Hydro-environment Research
Journal of Hydro-environment Research ENGINEERING, CIVIL-ENVIRONMENTAL SCIENCES
CiteScore
5.80
自引率
0.00%
发文量
34
审稿时长
98 days
期刊介绍: The journal aims to provide an international platform for the dissemination of research and engineering applications related to water and hydraulic problems in the Asia-Pacific region. The journal provides a wide distribution at affordable subscription rate, as well as a rapid reviewing and publication time. The journal particularly encourages papers from young researchers. Papers that require extensive language editing, qualify for editorial assistance with American Journal Experts, a Language Editing Company that Elsevier recommends. Authors submitting to this journal are entitled to a 10% discount.
×
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