摘要
针对我国水资源安全评价问题,结合支持向量机(SVM)对小样本、非线性问题分类效果好的特点,用麻雀搜索算法(SSA)对支持向量机的惩罚因子(C)和核函数参数(g)进行优化,建立基于麻雀搜索算法优化的支持向量机模型(SSA-SVM)用于区域水资源安全评价,以洛阳市某区域为例进行研究。结果表明,SSA-SVM法与T-S模糊神经网络法得到的评价等级结果基本一致,SSA-SVM模型具有寻优速度快,不易陷入局部最优等特点,可用于区域水资源安全评价。
Aiming at the evaluation of water resources security in China,combined with the characteristics that support vector machine(SVM)has good classification effect on small samples and nonlinear problems,the sparrow search algorithm(SSA)was used to optimize the penalty factor(C)and kernel function parameters(g)of the SVM.The support vector machine model optimized by the sparrow search algorithm(SSA-SVM)was used for regional water resources security assessment.A case study was carried out in a certain area of Luoyang City.The results show that the evaluation grade obtained by SSA-SVM method and T-S fuzzy neural network method are basically consistent,the SSA-SVM model has the characteristics of fast searching speed,and not easy to fall into local optimum,which can be used for regional water resources security evaluation.
作者
曹敬椿
卢敏
CAO Jing-chun;LU Min(College of Water Resources and Hydraulic Engineering,Yunnan Agricultural University,Kunming 650201,China)
出处
《水电能源科学》
北大核心
2023年第5期52-54,129,共4页
Water Resources and Power
基金
国家自然科学基金项目(52069029)。
关键词
麻雀搜索算法
参数优化
水资源安全
支持向量机
sparrow search algorithm
parameter optimization
water resources security
support vector machine
