基于贝叶斯网络和GIS的热带气旋灾害风险评估  

Assessment of tropical cyclone disaster risk based on the Bayesian network and GIS

作　　者：田城 黎鑫 杜洋 李明[1] 谢勇[2] 夏际炉 TIAN Cheng;LI Xin;DU Yang;LI Ming;XIE Yong;XIA Jilu(College of Meteorology and Oceanography,National University of Defense Technology,Changsha 410005,China;Jiangxi Meteorological Bureau,Nanchang 330008,China;95903 Troop Meteorological Observatory,Wuhan 430000,China)

机构地区：[1]国防科技大学气象海洋学院,湖南长沙410005 [2]江西省气象局,江西南昌330038 [3]95903部队气象台,湖北武汉430000

出　　处：《热带海洋学报》2023年第5期17-29,共13页Journal of Tropical Oceanography

基　　金：国家自然科学基金项目(41605051、41976188);国防科技大学重点科研计划项目(ZK17-02-010)。

摘　　要：针对热带气旋灾害的复杂性和不确定性,文章基于贝叶斯网络和地理信息系统(geographic information system,GIS)提出了一种新的热带气旋灾害风险评估模型。该模型能够从客观历史数据中自动挖掘灾害影响因素间的因果关系,并以概率形式进行表达和推理,从而对不确定灾害风险进行评估预测。基于1980—2016年中国东南沿海三省(广东、福建、浙江)的热带气旋灾害历史数据进行风险评估实验,选取致灾因子危险性、孕灾环境敏感性、承灾体脆弱性3个方面共计12个评估指标作为模型输入,直接经济损失量化为灾害风险等级作为模型输出,构建基于贝叶斯网络的风险评估模型。然后利用2017—2021年热带气旋灾害数据进行模型检验,评估预测的准确率为80.75%。模型预测的极低、低、中、高和极高风险的相对误差分别为27.72%、8.45%、18.58%、16.52%和19.12%,风险预测值的区划结果在空间形态上与实际灾害损失分布高度一致。此外,还将评估模型构建方法应用于“莫兰蒂”台风灾害个例的风险评估。结果表明,模型评估出的灾害高风险和极高风险区域与实际灾情报告基本一致。由此可见,本研究建立的热带气旋灾害风险评估模型具有较高的准确率和可信度,为热带气旋灾害风险评估提供了一种新的方法途径和技术支撑。To address the complexity and uncertainty of tropical cyclone disaster,this study proposes a new tropical cyclone disaster risk assessment model based on the Bayesian network and geographic information system(GIS).The model can automatically explore the causal relationships among disaster influencing factors from objective historical data,and express them in the form of probabilities to assess and predict uncertain disaster risks.Based on the historical data of tropical cyclone disaster in three southeastern coastal provinces(Guangdong,Fujian,and Zhejiang)of China from 1980 to 2016 for risk assessment experiments,a total of 12 assessment indicators in three aspects,i.e.,hazard of disaster-causing factors,sensitivity of disaster-inducing environment,and vulnerability of disaster-bearing bodies,were selected as model inputs,and direct economic losses were quantified as disaster risk levels as model outputs to construct a Bayesian network-based risk assessment model.The model was then tested against cyclone disaster data from 2017 to 2021,and the accuracy of the assessment prediction was 80.75%.The relative errors of very low,low,medium,high and very high risks predicted by the model were 27.72%,8.45%,18.58%,16.52%and 19.12%,respectively,and the zonal results of risk prediction values were highly consistent with the actual disaster loss distribution in terms of spatial patterns.In addition,the assessment construction method was applied to the risk assessment of individual cases of Typhoon“Meranti”.The results showed that the high and very high risk areas assessed by the model were basically consistent with the actual disaster reports.Thus,the tropical cyclone disaster risk assessment model established in this study has high accuracy and credibility,and provides a new methodological approach and technical support for tropical cyclone disaster risk assessment.

关 键 词：热带气旋灾害 风险评估 东南沿海三省 贝叶斯网络 地理信息系统 

分 类 号：P732.33[天文地球—海洋科学]