Flood susceptibility modelling using advanced ensemble machine learning models

作     者：Abu Reza Md Towfiqul Islam Swapan Talukdar Susanta Mahato Sonali Kundu Kutub Uddin Eibek Quoc Bao Pham Alban Kuriqi Nguyen Thi Thuy Linh Abu Reza Md Towfiqul Islam;Swapan Talukdar;Susanta Mahato;Sonali Kundu;Kutub Uddin Eibek;Quoc Bao Pham;Alban Kuriqi;Nguyen Thi Thuy Linh

作者机构：Department of Disaster ManagementBegum Rokeya UniversityRangpurBangladesh Department of GeographyUniversity of Gour BangaMaldaWest BengalIndia Environmental QualityAtmospheric Science and Climate Change Research GroupTon Duc Thang UniversityHo Chi Minh CityVietnam Faculty of Environment and Labour SafetyTon Duc Thang UniversityHo Chi Minh CityVietnam CERISInstituto Superior TécnicoUniversidade de LisboaLisbonPortugal Institute of Research and DevelopmentDuy Tan UniversityDanang 550000Vietnam Faculty of Environmental and Chemical EngineeringDuy Tan UniversityDanang 550000Vietnam 

出 版 物：《Geoscience Frontiers》 (地学前缘（英文版）)

年 卷 期：2021年第12卷第3期

页      面：60-77页

核心收录：

学科分类：083002[工学-环境工程] 0830[工学-环境科学与工程（可授工学、理学、农学学位）] 081504[工学-水利水电工程] 08[工学] 0815[工学-水利工程] 

基　　金：supported by a PhD scholarship granted by Fundacao para a Ciencia e a Tecnologia I.P.(FCT) Portugal under the PhD Programme FLUVIO–River Restoration and Management grant number:PD/BD/114558/2016 

主　　题：Flood hazard Flood vulnerability Flash floods Debris flow Teesta River basin Bangladesh 

摘      要：Floods are one of nature s most destructive disasters because of the immense damage to land,buildings,and human *** is difficult to forecast the areas that are vulnerable to flash flooding due to the dynamic and complex nature of the flash ***,earlier identification of flash flood susceptible sites can be performed using advanced machine learning models for managing flood *** this study,we applied and assessed two new hybrid ensemble models,namely Dagging and Random Subspace(RS)coupled with Artificial Neural Network(ANN),Random Forest(RF),and Support Vector Machine(SVM)which are the other three state-of-the-art machine learning models for modelling flood susceptibility maps at the Teesta River basin,the northern region of *** application of these models includes twelve flood influencing factors with 413 current and former flooding points,which were transferred in a GIS *** information gain ratio,the multicollinearity diagnostics tests were employed to determine the association between the occurrences and flood influential *** the validation and the comparison of these models,for the ability to predict the statistical appraisal measures such as Freidman,Wilcoxon signed-rank,and t-paired tests and Receiver Operating Characteristic Curve(ROC)were *** value of the Area Under the Curve(AUC)of ROC was above 0.80 for all *** flood susceptibility modelling,the Dagging model performs superior,followed by RF,the ANN,the SVM,and the RS,then the several benchmark *** approach and solution-oriented outcomes outlined in this paper will assist state and local authorities as well as policy makers in reducing flood-related threats and will also assist in the implementation of effective mitigation strategies to mitigate future damage.