摘要
针对水资源承载力评价预测涉及多因素综合指标的问题,采取粒子群算法对支持向量机模型中影响较大的训练参数惩罚因子C和核参数σ进行优化,建立了基于PSO-SVM的水资源承载力预测模型,根据指标等级标准构造训练集数据,对黑龙江省2017年水资源承载力进行评价。结果表明,黑龙江省2017年水资源承载力指数位于0.4234~0.7092之间,部分地区水资源承载力处于Ⅱ级,承载能力较弱,仍有较大提升空间。
Aiming at the problem that the evaluation and prediction of water resources carrying capacity involves multi-factor comprehensive indicators, particle swarm optimization algorithm was used to optimize the training parameter penalty factor C and kernel parameter σ in the support vector machine model, and a water resources carrying capacity prediction model was established based on PSO-SVM. According to the index grade standard, the training set data was constructed to evaluate the water resources carrying capacity of Heilongjiang Province in 2017. The results show that the water resources carrying capacity index of Heilongjiang Province in 2017 is between 0.423 4 and 0.709 2. The water resources carrying capacity in some areas is at level II, the carrying capacity is weak, and there is still much room for improvement.
作者
王涛
李治军
WANG Tao;LI Zhi-jun(College of Water Resources and Electric Engineering,Heilongjiang University,Harbin 150080,China;Cold Groundwater Research Institute,Heilongjiang University,Harbin 150080,China)
出处
《水电能源科学》
北大核心
2023年第1期30-33,共4页
Water Resources and Power
基金
“十二五”国家科技支撑计划课题(2014BAD12B01-03)。
关键词
水资源承载力
支持向量机
粒子群算法
黑龙江省
water resources carrying capacity
support vector machine
particle swarm optimization algorithm
Heilongjiang Province