Simultaneous hydrological prediction at multiple gauging stations using the NARX network for Kemaman catchment, Terengganu, Malaysia

• Main Authors: Lee, W.-K (Author), Tuan Resdi, T.A (Author)
• Format: Article
• Language: English
• Published: Taylor and Francis Ltd. 2016
• Subjects: artificial neural network; backwater; Backwater effects; basin analysis; catchment; Catchments; computer simulation; Field observations; Floods; Forecasting; Gauging stations; Hydrological prediction; hydrological regime; Input and outputs; Kemaman Basin; Kemaman catchment; Malaysia; Meteorological parameters; multiple gauging stations; NARX network; Neural network model; numerical model; one-step-ahead prediction; prediction; river flow; Runoff; Terengganu; tidal cycle; Time delay; West Malaysia
• Online Access: View Fulltext in Publisher; View in Scopus
• ISBN: 02626667 (ISSN)
• ISSN: 02626667 (ISSN)
• DOI: 10.1080/02626667.2016.1174333

This paper presents a neural network model capable of catchment-wide simultaneous prediction of river stages at multiple gauging stations. Thirteen meteorological parameters are considered in the input, which includes rainfall, temperature, mean relative humidity and evaporation. The NARX model is trained with a representative set of hourly data, with optimal time delay for both the input and output. The network trained using 120-day data is able to produce simulations that are in excellent agreement with field observations. We show that for application with one-step-ahead predictions, the loss in network performance is marginal. Inclusion of additional tidal observations does not improve predictions, suggesting that the river stage stations under consideration are not sensitive to tidal backwater effects despite the claim commonly made. EDITOR D. Koutsoyiannis ASSOCIATE EDITOR F. Pappenberger © 2016 IAHS.