Author(s): C. A. S. Farias; K. Suzuki; A. B. Celeste; A. Kadota
Linked Author(s):
Keywords: No Keywords
Abstract: A feedforward Artificial Neural Network (ANN) model is applied for the multivariate forecast of daily groundwater levels and reservoir inflows up to five days ahead. The ANN forecasting model relates previous groundwater level, previous reservoir inflow and daily precipitation forecasts of five days ahead in order to estimate daily groundwater levels and reservoir inflows for these five days. The shortterm precipitation values are assumed to be deterministic since meteorological shortrange forecasts are generally available. The methodology is applied for the water supply system of Matsuyama City, in Japan. Scarcity of water is a periodical problem in this city and thus accurate forecasts of groundwater levels and reservoir inflows are very important to improve the water resources management in the region. The good accuracy obtained by the ANN forecasting model indicates that it is very reliable for short-term daily estimations. As a result, this multivariate model may generate consistent data for the application of optimization techniques to the sustainable management of Matsuyama City's water supply system.
Year: 2009