中国农业科学院农业信息研究所 中国农学会
Agricultural Information Institute of CAAS China Association of Agricultural Science Societies
En
Ch
中国农业科学院农业信息研究所 中国农学会 主办

AI检索

订阅

返回顶部
当前位置: 首页 > 文章 > 基于模块神经网络的非线性降雨径流模拟研究 安徽农业科学 2014,42 (32) 11582-11584+11587
Position: Home > Articles > Modular Neural Network for Simulation of Nonlinear Rainfall-Runoff Journal of Anhui Agricultural Sciences 2014,42 (32) 11582-11584+11587

基于模块神经网络的非线性降雨径流模拟研究

作  者：
刘会;张建军;孙永涛
单  位：
西南石油大学理学院
关键词：
降雨径流;裂缝媒体;归一化;人工神经网络;模块神经网络;独立构架
摘  要：
针对流域水文系统的复杂性和非线性,利用人工神经网络(ANN)建立了一种混合非线性模型来精确模拟降雨径流。针对一般人工神经网络存在不能有效地处理先验知识和其他来源数据、处理较大数据集时耗时长、CPU消耗高以及处理较小数据集时精度低等问题,在多层感知器(MLP)的基础上引入模块神经网络(MNN)。模块神经网络具有独立的拓扑结构,可以有效地处理降雨径流中具有复杂空间关系的参数。结果表明,对比人工神经网络,模块神经网络模拟降雨径流耗时更短,精度更高。
译  名：
Modular Neural Network for Simulation of Nonlinear Rainfall-Runoff
作  者：
LIU Hui;ZHANG Jian-jun;SUN Yong-tao;College of Science,Southwest Petroleum University;
关键词：
Rainfall-runoff;;Fractured porous media;;Normalization;;Artificial neural network;;Modular neural network;;Independent architecture
摘  要：
According to the complexity and nonlinear hydrologic system,an approach for simulating groundwater flow is the combination of a linear and a nonlinear model that is created by the use of artificial neural network(ANN). The paper presents an attemption to create a productive interaction system between expert,mathematical model,MERO,and artificial neural networks( ANNs). In the present project,the first objective is to determine influencing parameters by the use of MERO model,which gave a good result in fractured porous media,and then introduce these parameters in artificial neural network( ANN). However,most of ANNs suffer from not using a prior knowledge and other source of data efficiently. Furthermore,artificial neural network(ANN) when deal with very large dataset is slow and CPU demanding and it missed its accuracy when a few data are available. The modular neural network(MNN) on the basis of the multilayer perception(MLP) was introduced. The network with special topological structure can effectively deal with parameters which have complex spatial relations. Compared with artificial neural network(ANN),modular neural network(MNN) give a better result in simulating rainfall-runoff and use less time.

相似文章

导出引用
计量
文章访问数: 12
HTML全文浏览量: 0
PDF下载量: 0

所属期刊

推荐期刊

友情链接Friendly link
农业信息研究所Agricultural information institute 农业智能知识服务平台Agricultural intelligent knowledge service platform 农业学术服务平台Agricultural Knowledge Service System 中国知网CNKI 维普网VIP 万方WANFANG DATA
联系我们Contact us

电话Tell：010-82109652-808

邮箱E-mail：agrijournal@caas.cn

服务Service
关于我们About us 意见建议Opinions and suggest
版权说明Copyright
单位：中国农业科学院农业信息研究所 中国农学会 © 2017中国农业科学院农业信息研究所 ICP备案号：京ICP备09089781号-46