• 全国中文核心期刊
  • 中国科技核心期刊
  • 美国工程索引(EI)收录期刊

LI Rong, LI Yi-tian. Application of the Neural Network Theory to the Flood Prediction[J]. Advances in Water Science, 2000, 11(4): 427-431.
Citation: LI Rong, LI Yi-tian. Application of the Neural Network Theory to the Flood Prediction[J]. Advances in Water Science, 2000, 11(4): 427-431.

Application of the Neural Network Theory to the Flood Prediction

Funds:  The project is supported by National Natural Science Fund of China (No.59890200).
  • Received Date: 1999-06-25
  • Rev Recd Date: 1999-11-29
  • Publish Date: 2000-10-25
  • Flood evolution exhibits a complicated non-linear dynamical process.The neural network possesses the capability of dealing with complexnon-linear dynamical systems,this paper demonstates howit can be used in flood prediction as a new approach considering the non-linear relation ship between flood evolution and its factors such as discharge,channel deformation,and so on.Based on it,the neural network approach is applied to the flow prediction of Yangtze Riverat Luoshan station.The preliminary results suggest that the phenomenon of small discharge with high level in middle reaches of Yangtse River recently,especially in 1998,is related to the downstream aggregation.And the quantitative relations between the water level variation of Luoshan station and the downstream aggregation are obtained.
  • [1] N Karunanithi,et al.Neural Network for River Flow Prediction[J].J of Computer Civil Engneering.1994,8(2):201-220.
    [2] Knanina E D.A Simple Procedure for Pruning Back-Propagation Trained Neural Networks[J].IEEE Trans.On Neural Networks.1990 1(2):239-242.
    [3] 焦李成.神经网络系统理论[M].西安:西安电子科技大学出版社,1990.35-50.
    [4] 胡铁松.神经网络预测与优化[M].大连:大连海事大学出版社,1997.45-52.
  • 加载中
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Article Metrics

Article views(120) PDF downloads(517) Cited by()

Proportional views
Related

Application of the Neural Network Theory to the Flood Prediction

Funds:  The project is supported by National Natural Science Fund of China (No.59890200).

Abstract: Flood evolution exhibits a complicated non-linear dynamical process.The neural network possesses the capability of dealing with complexnon-linear dynamical systems,this paper demonstates howit can be used in flood prediction as a new approach considering the non-linear relation ship between flood evolution and its factors such as discharge,channel deformation,and so on.Based on it,the neural network approach is applied to the flow prediction of Yangtze Riverat Luoshan station.The preliminary results suggest that the phenomenon of small discharge with high level in middle reaches of Yangtse River recently,especially in 1998,is related to the downstream aggregation.And the quantitative relations between the water level variation of Luoshan station and the downstream aggregation are obtained.

LI Rong, LI Yi-tian. Application of the Neural Network Theory to the Flood Prediction[J]. Advances in Water Science, 2000, 11(4): 427-431.
Citation: LI Rong, LI Yi-tian. Application of the Neural Network Theory to the Flood Prediction[J]. Advances in Water Science, 2000, 11(4): 427-431.
Reference (4)

Catalog

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return