High-accuracy estimation method of typhoon storm surge disaster loss under small sample conditions by information diffusion model coupled with machine learning models

Datos Bibliográficos

ID22025844
AutoresXuexue Du (0000-0003-3007-7044, China University of Petroleum, East China), Xiaomin Li (0000-0003-4488-0356, Ministry of Natural Resources), Suming Zhang (China University of Petroleum, East China), Tangqi Zhao (China University of Petroleum, East China), Qi Hou (China University of Petroleum, East China), Xifang Jin (National Marine Environmental Forecasting Center), Jie Zhang (0000-0002-6538-2770, Ministry of Natural Resources, autor de correspondencia)
Año2022
Volumen82
Páginas103307
Fecha de publicación2022-11-01
Peer ReviewedSí
Open AccessSí
TipoARTICLE
RevistaInternational Journal of Disaster Risk Reduction (JOURNAL)
Identificadores de la revistaISSN: 2212-4209
EditorialElsevier BV (PUBLISHER)
DOI10.1016/j.ijdrr.2022.103307
OpenAlexW4296818685
IdiomaEN
Citas recibidas2
Referencias citadas49

Typhoon storm surge disaster is the most severe marine disaster in China. Accurate estimation of typhoon storm surge disaster loss (TSSDL) is significant for emergency decisions and economic sustainability development. However, the TSSDL estimation is limited by small sample conditions, resulting in the low accuracy of the TSSDL estimation model based on machine learning. To solve the problems of easy overfitting and poor generalization ability of machine learning models under small sample conditions, the high-accuracy TSSDL estimation method was proposed. Firstly, this estimation method combines Gaussian Noise with the Information Diffusion Model based on the Vibrating String equation (named GN-VSIDM) to generate virtual samples to augment the original training set. Then, the augmented training set was applied to train three machine learning models. The results are as follows: the virtual sample generation method, i.e., GN-VSIDM, solves the small sample problem in the TSSDL estimation process and improves the machine models’ accuracy and robustness. Based on the GN-VSIDM and the eXtreme Gradient Boosting (named XGBoost) methods, the joint model GN-VSIDM-XGBoost is the optimal TSSDL estimation model. Compared with the original XGBoost model, the RMSE and R2 of the GN-VSIDM-XGBoost model are 0.1089 and 0.8292, which reduces 25.67% and improves 19.88%, respectively. Besides, the GN-VSIDM-XGBoost model possesses excellent robustness. The GN-VSIDM overcomes the limitation on the performance of TSSDL estimation models based on machine learning under small sample conditions. This study provides an effective case and method for solving the small sample problem in disaster loss assessment

Artificial neural network · Extreme Learning Machine · Machine learning · Meteorology · Overfitting · Storm · Storm surge · Typhoon · Computer Science · Flood Risk Assessment and Management · Hydrological Forecasting Using AI · Tropical and Extratropical Cyclones Research · Artificial Intelligence