基于模糊回归模型的洪水灾害分级评估方法研究  

Research on Flood Disaster Classification Evaluation Based on Fuzzy Regression Model

作　　者：龚艳冰 向林 刘高峰 GONG Yan bing;XIANG Lin;LIU Gao feng(Institute of Hydraulic Information Statistic and Management, Hohai University, Changzhou 213022, China;Jiangsu Provincial Collaborative Innovation Center of World Water Valley and Water Ecological Civilization, Nanjing 211100, China)

机构地区：[1]河海大学水利信息统计与管理研究所,江苏常州213022 [2]江苏省"世界水谷"与水生态文明协同创新中心,江苏南京211100

出　　处：《统计与信息论坛》2018年第5期80-85,共6页Journal of Statistics and Information

基　　金：国家自然科学基金项目<城市极端雨洪灾害预警与应急管理研究>(71303074);江苏省社会科学基金项目<基于极值理论和云模型的苏北地区季节性旱灾风险预测和评价研究>(14GLC004)

摘　　要：高效、准确评估自然灾害事件的级别,是应急管理中有效控制灾害和制定减灾防灾对策的重要保证。针对洪水灾害等级评估中存在的模糊不确定特征,提出基于模糊多元回归模型的洪水灾害分级评估方法。首先,提出一种基于可能性均值-标准差距离的模糊多元回归模型的参数估计方法;然后,将洪水灾害等级和影响因素看成是模糊因变量和自变量,通过求解模糊回归方法得到模糊回归影响系数,这样能够较好地解决分级过程中存在的模糊性问题;最后,以45个洪水灾害事件为例,实例结果表明,模糊回归模型应用于自然灾害事件分级是可行且有效的,能够较好地解决灾害事件等级评估中的模糊性。Efficient and accurate assessment the level of natural disasters events is an important guarantee for effective control,and actively responds to disaster emergency management.According to the fuzzy uncertainty characteristics of flood disaster grade evaluation,a method of flood disaster classification evaluation based on fuzzy multiple regression model is proposed.Firstly,aparameter estimation method of fuzzy regression model is proposed based on possibilistic mean and standard deviation distance.Then,the flood disaster grade and influence factors as fuzzy dependent and independent variables,fuzzy regression method is obtained by solving the fuzzy regression coefficient,which can solve the fuzzy problem existing in the classification process better.Finally,45 cases of flood events are taken as an example.The results show that the fuzzy regression model is feasible and effective for natural disaster events classification,and can be used to solve the fuzziness in the assessment of disaster events.

关 键 词：模糊回归 洪水灾害 等级评估 

分 类 号：O159[理学—数学]