###
DOI:
本文二维码信息
基于随机森林的暴雨灾害人口损失预估模型及应用
刘扬, 王维国
(国家气象中心)
Assessing Model of Casualty Loss in Rainstorms Based on Random Forest and Its Application
Liu Yang, Wang Weiguo
(National Meteorological Center)
摘要
相似文献
本文已被:浏览 59次   下载 35
投稿时间:2019-04-29    修订日期:2019-10-04
中文摘要: 基于2009-2017年的广西县级暴雨灾情记录,综合考虑致灾因子、孕灾环境和承灾体因素选取7个解释变量,运用随机森林算法,构建暴雨灾害人口损失预估模型;并以精细化网格降水实况分析和预报产品驱动模型,预估是否发生人口损失。研究结果表明:模型训练样本及测试样本的分类准确率均在90%以上,致灾因子(降水情况)是最主要的解释变量,重要性从大到小依次是前10天降水距平百分率、过程最大日雨量、最大小时雨量和短时强降水频次。应用智能网格降水产品,对广西地区近两年的暴雨灾害过程进行回报试验,准确率超过70%。
Abstract:Based on historic casualty loss records of heavy rainfall occurred in Guangxi at county level from 2009 to 2017, seven factors were selected as explanatory variables by comprehensively considering the trigger factors, disaster formative environment and exposure units, and the prediction model of casualty loss caused by rainstorms was built up by using random forest algorithms. The refined grid precipitation analysis and forecast products were used to drive the model to predict loss of life. The results show that the classification accuracies of model are both above 90% in training and testing samples. Disaster-triggering factors (precipitation) are the most significant explanatory variables. The importance of these precipitation variables in turn are the anomaly percentage of accumulated precipitation over the previous 10 days, the maximum daily precipitation, the maximum hourly precipitation and the frequency of short-time heavy rainfall. By applying the intelligent grid precipitation products, several rainstorm processes in Guangxi in recent two years are used to verify the model, and the results show that prediction accuracies are above 70%.
文章编号:201904290185     中图分类号:    文献标志码:
基金项目:国家气象中心青年基金
引用文本:
刘扬,王维国,0.[en_title][J].Meteor Mon,():-.
Liu Yang,Wang Weiguo,0.Assessing Model of Casualty Loss in Rainstorms Based on Random Forest and Its Application[J].Meteor Mon,():-.