基于Elman动态神经网络的降雨—径流模拟研究  

Application of rainfall-runoff simulation based on Elman recurrent dynamic neural network model

作　　者：邵月红[1] 林炳章[1] 叶金印[2] 刘永和[3] 

机构地区：[1]南京信息工程大学应用水文气象研究院,江苏南京210044 [2]淮河流域气象中心,安徽蚌埠233040 [3]河南理工大学资源环境学院,河南焦作454000

出　　处：《大气科学学报》2014年第2期223-228,共6页Transactions of Atmospheric Sciences

基　　金：公益性行业(水文)科研专项(GYHY201001047);江苏省高校自然科学基金项目(13KJB170017);淮河流域气象开放研究基金项目(HRM201205);国家自然科学基金资助项目(41105074)

摘　　要：采用Elman动态神经网络对沂沭河流域上游临沂子流域日径流量进行模拟。为了更好地检验该网络估测径流的精度,同时采用陆面水文过程模型TOPX进行对比分析。确定性线系数、相关系数、平均相对误差和平均相对均方根误差四个统计指数及流域径流过程。结果表明,Elman动态神经网络能够对日径流量进行较好的模拟,较好地捕捉洪峰流量和出现时间,为降雨径流模拟提供了一种有效可靠的方法。An Elman recurrent neural network model （ENN） is constructed and applied to the daily runoff forecast in the Linyi sub-catchment of upper Yishu river basin in this paper.In order to further evaluate the performance of ENN,land surface hydrological model TOPX is applied as a comparison at the same time in the study region.Based on analysis indexes such as Nash-Sutcliffe coefficient, correlation coefficient, mean relative error and root mean relative square error, the results of daily runoff and flooding processes indicated that ENN presents high accuracy in hydrological simulations on the rainfall-run- off dynamic process, the peak flow and peak occurrence time.It is feasible to take it as a promising and efficient method to simulate the daily runoff.

关 键 词：ELMAN神经网络 TOPX 降雨一径流 

分 类 号：P333[天文地球—水文科学]