基于支持向量机的小型水库风险等级模型研究  

Model for risk rate of small reservoirs based on support vector machine

作　　者：张可[1,2,3] 崔敬浩 黄华爱[1,5] 丰景春 左媛[1,4] ZHANG Ke;CUI Jinghao;HUANG Huaai;FENG Jingchun;ZUO Yuan(Business School,Hohai University,Nanjing 211100,China;International River Research Center,Nanjing 211100,China;Jiangsu Provincial Collaborative Innovation Center of World Water Valley and Water Ecological Civilization,Nanjing 211100,China;Project Management Institute of Hohai University,Nanjing 211100,China;Office of Guangxi Flood Control and Drought Control Headquarters,Nanning 530023,China)

机构地区：[1]河海大学商学院,江苏南京211100 [2]国际河流研究中心,江苏南京211100 [3]江苏省“世界水谷”与水生态文明协同创新中心,江苏南京211100 [4]河海大学项目管理研究所,江苏南京211100 [5]广西壮族自治区防汛抗旱指挥部办公室,广西南宁530023

出　　处：《水利经济》2021年第3期69-74,88,共7页Journal of Economics of Water Resources

基　　金：江苏省研究生科研与实践创新计划(中央高校基本科研业务费(学生项目))(KYCX17_0511);国家社会科学基金(17BGL156);贵州省水利科技计划(KT201601)。

摘　　要：根据小型水库现状,研究得到小型水库安全风险的主要影响因子。在此基础上,利用机器学习方法,建立小型水库安全风险等级评价模型。通过实例分析,验证了模型的正确性和适用性。研究表明,基于支持向量机的小型水库安全风险等级评估在小水库安全风险识别上具有一定的适用性,能够有效解决小型水库安全风险等级评价中存在的数据样本较少的问题,该研究成果可以为小型水库下游区域山洪预警提供新的思路。According to their current situations,the main influencing factors for the safety risks of small reservoirs are obtained.On this basis,a model for evaluating the safety risks of small reservoirs is established by using the machine learning method.The correctness and applicability of this model are verified through example analysis.The research shows that the evaluation of risk rates of small reservoirs based on the support vector machine has a certain applicability and can effectively solve the problem of short of data samples in their evaluation of safety rates.The research results may provide new ideas for the early warning of mountainous floods in the downstream regions of small reservoirs.

关 键 词：小型水库 风险评估 山洪 预警系统 支持向量机 

分 类 号：TV697[水利工程—水利水电工程]