Spatial modeling of flood hazard using machine learning and GIS in Ha Tinh province, Vietnam

• Published in: Journal of water and climate change Vol. 14; no. 1; pp. 200 - 222
• Main Author: Nguyen, Huu Duy
• Format: Journal Article
• Language: English
• Published: London IWA Publishing 01.01.2023
• Subjects: adaptive neuro-fuzzy inference system; Adaptive systems; Algorithms; Artificial neural networks; Chaos; Climate change; Decision making; Evolutionary computation; flood; Flood hazards; Flood mapping; Floods; Fuzzy logic; Fuzzy sets; Geographical information systems; ha tinh; Learning algorithms; Machine learning; Mathematical models; Missing persons; Modelling; Optimization; Optimization algorithms; Physics; Remote sensing; Root-mean-square errors; Support vector machines; Trigonometric functions; vietnam; Vietnam
• ISSN: 2040-2244; 2408-9354
• DOI: 10.2166/wcc.2022.257

Abstract The objective of this study was the development of an approach based on machine learning and GIS, namely Adaptive Neuro-Fuzzy Inference System (ANFIS), Gradient-Based Optimizer (GBO), Chaos Game Optimization (CGO), Sine Cosine Algorithm (SCA), Grey Wolf Optimization (GWO), and Differential Evolution (DE) to construct flood susceptibility maps in the Ha Tinh province of Vietnam. The database includes 13 conditioning factors and 1,843 flood locations, which were split by a ratio of 70/30 between those used to build and those used to validate the model, respectively. Various statistical indices, namely root mean square error (RMSE), area under curve (AUC), mean absolute error (MAE), accuracy, and R1 score, were applied to validate the models. The results show that all the proposed models performed well, with an AUC value of more than 0.95. Of the proposed models, ANFIS-GBO was the most accurate, with an AUC value of 0.96. Analysis of the flood susceptibility maps shows that approximately 32–38% of the study area is located in the high and very high flood susceptibility zone. The successful performance of the proposed models over a large-scale area can help local authorities and decision-makers develop policies and strategies to reduce the threats related to flooding in the future.