River flow forecasting using recurrent neural networks

被引:161
作者
Nagesh Kumar D. [1 ]
Srinivasa Raju K. [2 ]
Sathish T. [3 ]
机构
[1] Department of Civil Engineering, Indian Institute of Science, Bangalore
[2] Civil Engineering Department, Birla Institute of Technology/Sci., Pilani
[3] Department of Civil Engineering, Indian Institute of Technology, Kharagpur
关键词
Forecasting; Hydrologic time series; Recurrent neural networks; River flows;
D O I
10.1023/B:WARM.0000024727.94701.12
中图分类号
学科分类号
摘要
Forecasting a hydrologic time series has been one of the most complicated tasks owing to the wide range of data, the uncertainties in the parameters influencing the time series and also due to the non availability of adequate data. Recently, Artificial Neural Networks (ANNs) have become quite popular in time series forecasting in various fields. This paper demonstrates the use of ANNs to forecast monthly river flows. Two different networks, namely the feed forward network and the recurrent neural network, have been chosen. The feed forward network is trained using the conventional back propagation algorithm with many improvements and the recurrent neural network is trained using the method of ordered partial derivatives. The selection of architecture and the training procedure for both the networks are presented. The selected ANN models were used to train and forecast the monthly flows of a river in India, with a catchment area of 5189 km2 up to the gauging site. The trained networks are used for both single step ahead and multiple step ahead forecasting. A comparative study of both networks indicates that the recurrent neural networks performed better than the feed forward networks. In addition, the size of the architecture and the training time required were less for the recurrent neural networks. The recurrent neural network gave better results for both single step ahead and multiple step ahead forecasting. Hence recurrent neural networks are recommended as a tool for river flow forecasting. © 2004 Kluwer Academic Publishers.
引用
收藏
页码:143 / 161
页数:18
相关论文
共 28 条
[1]  
Almeida L.B., Backpropagation in perceptrons with feedback, Neural Computers, pp. 199-208, (1988)
[2]  
Anmala J., Zhang B., Govindaraju R.S., Comparison of ANNs and empirical approaches for predicting watershed runoff, J. Water Resour. Plann. Manage., ASCE, 126, 3, pp. 156-166, (2000)
[3]  
Artificial neural networks in hydrology. I: Preliminary concepts, J. Hydrol. Engineer ASCE, 5, 2, pp. 115-123, (2000)
[4]  
Artificial neural networks in hydrology. II: Hydrologic applications, J. Hydrol. Engineer., ASCE, 5, 2, pp. 124-137, (2000)
[5]  
Bishop C.M., Neural Networks for Pattern Recognition, (1995)
[6]  
Box G.E.P., Jenkins G.M., Time Series Analysis: Forecasting and Control, (1976)
[7]  
Carling A., Introduction to Neural Networks, (1995)
[8]  
Chow T.W.S., Cho S.Y., Development of a recurrent sigma-P neural network rainfall forecasting system in Hong Kong, Neural Comput. Appl., 5, 2, pp. 66-75, (1997)
[9]  
Fahlman S.E., Lebiere C., The Cascaded-Correlation Learning Architecture, (1990)
[10]  
Gong N., Denoeux T., Bertrand Krajewski J.L., Neural networks for solid transport modeling in sewer systems during storm events, Water Sci. Technol., 33, 9, pp. 85-92, (1996)