考虑预报因子选择的神经网络降雨径流模型

被引：7

作者：

卢韦伟

周建中

陈璐

叶磊

机构：

[1] 华中科技大学水电与数字化工程学院

来源：

水电能源科学 | 2013年 / 31卷 / 06期

关键词：

神经网络模型选取; 水文预报; 预报因子选择; Copula熵;

D O I：

暂无

中图分类号：

P338 [水文预报];

学科分类号：

081501 ;

摘要：

为优化神经网络模型的应用效果,研究了基于神经网络的降雨-径流模型,根据Copula熵法确定预报因子,并与传统的线性相关法进行比较分析,采用BP、RBF、GRNN三种神经网络建立降雨-径流模型,应用均方根误差、合格率、确定性系数三个指标为模型选取评价准则。通过对金沙江流域的径流预报,发现基于Copula熵法的BP模型预报结果更接近实测值,精度更高。

引用

页码：21 / 25

页数：5

共 10 条

[1]

Non-linear Varia-ble Selection for Artificial Neural Networks UsingPartial Mutual Information. May R J,Maier H R,Dandy G C. Environmental Modelling&Software . 2008

[2]

Selection of input variables for data driven models:an average shifted histogram partial mutual information estimator approach. Fernando T M K G,Maier H R,Dandy G C. Journal of Hydronautics . 2009

[3]

Seasonal to interannual rainfall probabilistic forecasts for improved water supplymanagement: Part1-A strategy for system predictor identification. Sharma A. Journal of Hydronautics . 2000

[4]

Generalized regression neural network in monthly flow forecasting. Cigizoglu,Hikmet Kerem. Civil Engineering . 2005

[5]

Seasonal to interannual rainfall probabilistic forecasts for improved water supply management: Part 1 — A strategy for system predictor identification[J] . A. Sharma. &nbspJournal of Hydrology . 2000 (1)

[6] 串联水库洪水预报模型影响因素及精度分析 [J].

徐晨光 ;

李春静 ;

赵麦换 .

人民黄河, 2008, (07) :34-35

[7] 基于BP神经网络的旬降雨径流相关预报模型 [J].

梁国华 ;

习树峰 ;

王本德 .

水力发电, 2009, 35 (08) :10-12+39

[8] Mutual Information Is Copula Entropy [J].

马健 ;

孙增圻 .

TsinghuaScienceandTechnology, 2011, 16 (01) :51-54

[9]

Using mutual information for selecting features in supervised neural net learning. Roberto Battiti. IEEE Transactions on Neural Networks . 1994

[10]

Input Deter-mination for Neural Network Models in Water Re-sources Applications.Part 2.Case Study:Forecas-ting Salinity in a River. Bowden G J,Maierb H R,Dandy G C. Journal of Hydronautics . 2005

← 1 →