GA-NN模型在保定市水环境承载力评价中的应用
Application of GA-NN Model in Evaluation of Water Environment Carrying Capacity in Baoding City
投稿时间:2019-02-22  修订日期:2019-05-17
DOI:
中文关键词:  水环境承载力  相关性分析  主成分分析  遗传算法  BP神经网络
英文关键词:Water Environmental Carrying Capacity  correlation analysis  principal component analysis  genetic algorithm  BP neural network
基金项目:
作者单位E-mail
张彦 河北省保定水文水资源勘测局 jackyhero2008@163.com 
李明然 河北省保定水文水资源勘测局  
摘要点击次数: 74
全文下载次数: 0
中文摘要:
      水环境承载力评价对于区域的水环境与人类社会经济的健康可持续发展具有重要的意义。为研究保定市水环境承载力状况,应用相关性分析和主成分分析相结合的方法筛选出10个评价指标,建立了遗传算法(GA)优化BP神经网络(BP-NN)的GA-NN评价模型,并与BP-NN评价模型对比,最后应用评价模型进行评价。结果显示:2001年~2016年保定市水环境承载力呈现提高趋势,虽然水环境承载力水平有所提高,但仍处于较弱承载水平。与未经优化的BP-NN相比,GA-NN评价模型的拟合精度更高,拟合误差更加稳定,泛化能力更强,可作为一种简洁有效的水环境承载力评价方法。
英文摘要:
      The assessment of water environmental carrying capacity(WECC) is of great significance to the healthy and sustainable development of regional water environment and human society and economy.In order to study the water environment carrying capacity of Baoding City, 10 evaluation indexes were selected by the combination of correlation analysis and principal component analysis (PCA). A GA-NN evaluation model of back-propagation neural network(BP-NN) optimized by genetic algorithm (GA) was established and compared with BPNN evaluation model. Finally, the evaluation model was applied for evaluation. The results showed that from 2001 to 2016, the WECC of Baoding City showed an increasing trend. Although the carrying capacity of water environment increased, it was still at a weak level. Compared with the unoptimized BPNN, the GA-NN evaluation model has higher fitting accuracy, more stable fitting error and stronger generalization ability, and it can be used as a simple and effective method for evaluating the WECC.
  查看/发表评论  下载PDF阅读器