M.C.V. Ramirez, H.F. de Campos Velho, N.J. Ferreira (2002): Artificial Neural Network Technique for Precipitation Forecasts Applied to the Sao Paulo Region, International Conference on Quantitive Precipitation Forecasting, 2-6 September, Reading, UK.

Abstract: Artificial Neural Network (ANN) technique is applied to construct the non-linear mapping between output data from regional Eta model, used by CPTEC-INPE, and surface precipitation observed data over eastern Sao Paulo (Brazil) region. The goal is to generate site-specific quantitative forecasts for daily precipitation. The paper shows the method of network structure construction, input/output data preparing and the sequence of the training. Model variables are the input data and precipitation data, from rain gauge, are output data. The period of the study is December and January 1997-2001. With the trained networks, the developed system gives the rainfall forecast for the next 3 hours. The performance of the ANN is illustrated for three gauges in eastern São Paulo. Statistical analysis results show the premise precipitation forecasts for the Sao Paulo region.