AUTHOR=Guo Hongbo , Yin Kedong , Huang Chong 

TITLE=Modeling of Direct Economic Losses of Storm Surge Disasters Based on a Novel Hybrid Forecasting System

JOURNAL=Frontiers in Marine Science

VOLUME=Volume 8 - 2021

YEAR=2022

URL=https://www.frontiersin.org/journals/marine-science/articles/10.3389/fmars.2021.804541

DOI=10.3389/fmars.2021.804541

ISSN=2296-7745

ABSTRACT=Modelling of the direct economic losses of storm surge disasters can assess the disaster situation timely and improve the work efficiency of post disaster management availably, which is acknowledged as one of the most significant issues in clean production. However, it is a challenge to improve the forecasting accuracy of direct economic losses caused by storm surge disasters, which is also a major concern in the field of disaster risk management. In particular, most previous studies mainly focused individual models, which ignore the significance of reduction and optimization. Therefore, to bridge the research gap in current studies, a novel direct economic loss forecasting system for storm surge disasters is proposed in this study, which includes reduction module, forecasting module and evaluation module. In this system, a forecasting module based on improved machine learning technique is proposed, which improves the system’s generalization ability and robustness. In addition, the key attributes and samples are selected by the newly proposed reduction module to further improve the forecasting performance from two innovative perspectives. Moreover, the evaluation module is incorporated to evaluate the superiority of the developed forecasting system comprehensively. Data of storm surge disasters from three typical provinces are utilized in case study, and the performance of the proposed forecasting system is analyzed and compared with eight comparison models. Experimental results prove that the performance of the novel forecasting system proposed in this paper is superior to other compared models, and it is suitable for the direct economic losses forecasting of storm surge disasters.