Extracting Natech Reports from Large Databases: Development of a Semi-Intelligent Natech Identification Framework

作     者：Xiaolong Luo Ana Maria Cruz Dimitrios Tzioutzios Xiaolong Luo;Ana Maria Cruz;Dimitrios Tzioutzios

作者机构：Department of Urban ManagementGraduate School of EngineeringKyoto UniversityKyoto 615-8540Japan Disaster Prevention Research InstituteKyoto UniversityKyoto 611-0011Japan 

出 版 物：《International Journal of Disaster Risk Science》 (国际灾害风险科学学报（英文版）)

年 卷 期：2020年第11卷第6期

页      面：735-750页

核心收录：

学科分类：12[管理学] 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）] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 

基　　金：supported in part by the Japan Society for the Promotion of Science(Kaken Grant 17K01336,April 2017–March 2020) the China Scholarship Council(CSC No.201606620007) the Ministry of Education,Culture,Sports,Science,and Technology of Japan(Monbukagakusho:MEXT Scholarship No.171572,2017–2021) the Ministry of Education,Culture,Sports,Science,and Technology of Japan(Monbukagakusho:MEXT scholarship,2019–2022) 

主　　题：Data extraction method Machine learning Natechs Natural hazards NRC database 

摘      要：Natural hazard-triggered technological accidents(Natechs)refer to accidents involving releases of hazardous materials(hazmat)triggered by natural *** economic losses,as well as human health and environmental problems are caused by *** this regard,learning from previous Natechs is critical for risk ***,due to data scarcity and high uncertainty concerning such hazards,it becomes a serious challenge for risk managers to detect Natechs from large databases,such as the National Response Center(NRC)*** the largest database of hazmat release incidents,the NRC database receives hazmat release reports from citizens in the United ***,callers often have incomplete details about the incidents they are *** results in many records having incomplete ***,it is quite difficult to identify and extract Natechs accurately and *** this study,we introduce machine learning theory into the Natech retrieving research,and a Semi-Intelligent Natech Identification Framework(SINIF)is proposed in order to solve the *** tested the suitability of two supervised machine learning algorithms,namely the Long ShortTerm Memory(LSTM)and the Convolutional Neural Network(CNN),and selected the former for the development of the *** to the results,the SINIF is efficient(a total number of 826,078 records were analyzed)and accurate(the accuracy is over 0.90),while 32,841 Natech reports between 1990 and 2017 were extracted from the NRC ***,the majority of those Natech reports(97.85%)were related to meteorological phenomena,with hurricanes(24.41%),heavy rains(19.27%),and storms(18.29%)as the main causes of these reported ***,this study suggests that risk managers can benefit immensely from SINIF in analyzing Natech data from large databases efficiently.