自然资源学报 ›› 1998, Vol. 13 ›› Issue (2): 169-174.doi: 10.11849/zrzyxb.1998.02.011

• 论文 • 上一篇    下一篇

人工神经网络结构对径流预报精度的影响分析

冯国章1, 李佩成2   

  1. 1. 西北农业大学农业水土工程研究所;
    2. 西安工程学院水文地质与工程地质系
  • 收稿日期:1997-07-24 修回日期:1997-11-14 出版日期:1998-06-25 发布日期:1998-06-25
  • 作者简介:冯国章,男,1950年生,博士,副教授。1977年毕业于西北农业大学水工建筑专业并留校任教至今; 1988~1989年在加拿大国立水文研究所进修;1998年在西北农业大学获工学博士学位。长期从事水文学和 水资源学教学与科研工作。主要研究方向为水资源水文学、水资源调控理论与技术及新技术在水文、水资源 中的应用。发表论文40多篇。
  • 基金资助:

    陕西省自然科学基金,国家“九五”攻关项目

AN ANALYSIS OF EFFECTS OF ARTIFICIAL NEURALNETWORK STRUCTURES ON PRECISION OFSTREAM FLOW FORECASTING

FENG Guozhang1, Li Peicheng2   

  1. 1. Institute of Agricultural Water Soil Engineering,Northwestern Agricultural University, Yangling 712100;
    2. Department of Hydrogeology and Engineering Geology, Xi'an Institute of Engineering, Xi'an 710054
  • Received:1997-07-24 Revised:1997-11-14 Online:1998-06-25 Published:1998-06-25

摘要: 建立了基于径流形成机理的以时段降水量与前期径流量为预报因子的前向多层人工神经网络径流预报模型;分析了网络结构对月径流预报精度的影响,发现随网络结构的复杂化,网络训练误差减小,模型评定的确定性系数增大,并均趋于稳定,预报检验的确定性系数总趋势是减小;发现影响模型精度的决定因素是网络输入单元数,亦即径流影响因素;提出了以模型评定与预报检验共同高效或等效的模型选择的折衷方法,以及按模型适宜预报域进行多模型组合预报的最佳预报域组合法。

关键词: 人工神经网络, 径流预报, 网络结构影响, 确定性系数, 最佳预报域组合法

Abstract: A stream flow forecasting model of feed forward multi layer artificial neural network(ANN), in which current precipitation and antecedent flow are considered as the model inputs according to runoff generation mechanism, is introduced. The deterministic coefficient is adopted as a norm to control ANN training error and precision of model calibration and verification. It is shown through the study that ANN training error is decreased and the coefficient of model calibration is increased, and meanwhile the coefficient of model verification is persistently decreased, with increase of complexity of ANN structures. It is also recognized that the key factor affecting the model precision is the number of neurons in the input layer, i e., the number of flow effecting factors. A method to select models for operational application, and to combine optimal forecasting ranges is proposed.

Key words: artificial neural network, mid term and long term flow forecasting, network structure effect, deterministic coefficient, combination of optimal forecasting range