Combining multiscale filtering and neural networks for local rainfall forecast

Resumen

Rainfall is one of the most important events of human life and society. Some rainfall phenomena like floods or hailstone are a threat to agriculture, business and even life. Predicting the weather has emerged as one of the most important areas of scientific endeavour. Nowadays, there is a big effort and great developments in long and mid-term rainfall forecasts, where qualitative improvements have been obtained both in forecasts and verification. This work proposes a diverse local rainfall forecasting system, using a long term local measurements registry. The forecast is performed estimating pressure time series and processing them with multispectral wavelet analysis and Neural Networks. The aim of the study is to provide complementary criteria based on the observed pressure wave pattern repetition. This method was proposed by expert meteorologists after observing these events during 40 years.