Novel hybrid models between bivariate statistics, artificial neural networks and boosting algorithms for flood susceptibility assessment. (1st July 2020)

• Record Type: Journal Article
• Authors: Costache, Romulus; Pham, Quoc Bao; Avand, Mohammadtaghi; Thuy Linh, Nguyen Thi; Vojtek, Matej; Vojteková, Jana; Lee, Sunmin; Khoi, Dao Nguyen; Thao Nhi, Pham Thi; Dung, Tran Duc
• Is Part Of: Journal of environmental management. Volume 265(2020)
• Publication Date: 2020-07-01
• Subjects: Flood susceptibility -- Machine learning -- Ensemble models -- Bivariate statistics; Environmental policy -- Periodicals; Environmental management -- Periodicals; Environment -- Periodicals; Ecology -- Periodicals; 363.705
• DOI: 10.1016/j.jenvman.2020.110485
• Languages: English
• ISSNs: 0301-4797

Abstract

Abstract: Across the world, the flood magnitude is expected to increase as well as the damage caused by their occurrence. In this case, the prediction of areas which are highly susceptible to these phenomena becomes very important for the authorities. The present study is focused on the evaluation of flood potential within Trotuș river basin in Romania using six ensemble models created by the combination of Analytical Hierarchy Process (AHP), Certainty Factor (CF) and Weights of Evidence (WOE) on one hand, and Gradient Boosting Trees (GBT) and Multilayer Perceptron (MLP) on the other hand. A number of 12 flood predictors, 172 flood locations and 172 non-flood locations were used. A percentage of 70% of flood and non-flood locations were used as input in models. From the input data, 70% were used as training sample and 30% as validating sample. The highest accuracy was obtained by the MLP-CF model in terms of both training (0.899) and testing (0.889) samples. A percentage between 21.88% and 36.33% of study area is covered with high and very high flood potential. The results validation, performed through the ROC Curve method, highlights that the MLP-CF model provided the most accurate results. Graphical abstract: Image 1 Highlights: This study presents six novel ensembles used to identify the areas susceptible to floods. Historical flood locations were considered into the methodological workflow. The model performances were assessed through several statistical metrics. Generally, more than 19% of the study area has a high and very high flood susceptibility.