A comparison between neural-network forecasting techniques-case study: river flow forecasting

• Published in: IEEE transactions on neural networks Vol. 10; no. 2; pp. 402 - 409
• Main Authors: Atiya, A.F., El-Shoura, S.M., Shaheen, S.I., El-Sherif, M.S.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.03.1999; Institute of Electrical and Electronics Engineers
• Subjects: Applied sciences; Backpropagation; Data preprocessing; Economic forecasting; Electric, optical and optoelectronic circuits; Electronics; Estimating; Exact sciences and technology; Floods; Forecasting; Fourier series; Load forecasting; Neural networks; Partitions; Postal services; Protection; Recursive methods; Rivers; Shortages; Case study; Direct method; Backpropagation; Water management; Multistep method; Recursive method; Neural network; Forecast model; Fourier series; River water
• ISSN: 1045-9227; 1941-0093
• DOI: 10.1109/72.750569

Estimating the flows of rivers can have significant economic impact, as this can help in agricultural water management and in protection from water shortages and possible flood damage. The first goal of the paper is to apply neural networks to the problem of forecasting the flow of the River Nile in Egypt. The second goal of the paper is to utilize time series as a benchmark to compare between several neural-network forecasting methods. We compare four different methods to preprocess the inputs and outputs, including a novel method proposed here based on discrete Fourier series. We also compare three different methods for the multistep ahead forecast problem: the direct method, the recursive method, and the recursive method trained using a backpropagation through time scheme. We also include a theoretical comparison between these three methods. The final comparison is between different methods to perform a longer horizon forecast, and that includes ways to partition the problem into several subproblems of forecasting K steps ahead.