摘要
水资源安全预警是新形势下实现水资源高效有序管理的一个有效途径,其关键是水资源安全临界状态的确定。对此,从水资源量的角度划分出了水资源安全的3种临界状态,即临界旱灾、临界安全和临界洪灾,并提出了一种基于主成分分析和支持向量机的临界状态解析方法。研究结果表明:①运用主成分分析,可以消除指标间的相关性;而采用支持向量机,可以进行水资源系统临界面的划分,进而可以根据临界状态的发展趋势实现水资源的预警。②进一步将该方法应用于洪水预警、干旱预警和水资源安全预警研究,分别得出了3种情况下的临界超平面方程,可将其作为预警对象的判断依据。研究成果对水资源安全预警具有一定的参考意义。
The early warning of water resources security is an effective way to achieve efficient and orderly management of water resources in the new situation,the key of which is to determine the critical state of water resources security.From the perspective of water resources quantity,three critical states of water resources security,namely,critical drought,critical security,and critical flood,are divided,and a critical state analysis method based on principal component analysis and support vector machine is proposed.The results show that the principal component analysis can be used to eliminate the correlation between the indicators,and the critical surface of the water resources system can be divided by the support vector machine,so that the early warning of water resources can be realized according to the development trend of the critical state.This method was applied to flood early warning,drought early warning and water resource security early warning,and the critical hyperplane equations in three cases were obtained to give basis for judging the early warning objects.The research results have certain reference significance.
作者
闫宝伟
江慧宁
霍磊
杨文发
张俊
YAN Baowei;JIANG Huining;HUO Lei;YANG Wenfa;ZHANG Jun(School of Civil and Hydraulic Engineering,Huazhong University of Science and Technology,Wuhan 430074,China;Bureau of Hydrology,Changjiang Water Resources Commission,Wuhan 430010,China)
出处
《人民长江》
北大核心
2021年第3期87-92,共6页
Yangtze River
基金
国家重点研发计划项目(2016YFC0402708)
国家自然科学基金项目(52079054)。
关键词
水资源安全
水资源预警
临界状态
主成分分析
支持向量机
water resources security
water resources early warning
critical state
principal component analysis
support vector machine
