Kernel Smoothing of Rainfall Data in the Northeast

Northeast Brazil has a very complex climate diversity. The rainfall regime is considered seasonal because it behaves more intensely over three internal zones of the region. In addition, rainfall is highly influenced by the incidence of El Niño, La Niña and other phenomena acting on the basins of the Tropical Pacific and Atlantic Oceans. In this study, the mathematical-computational technique of Kernel Smoothing interpolation was applied to rainfall data collected from meteorological stations throughout the Northeast of Brazil, covering almost one hundred years of observations. To carry out this study, the ＂Cluster Neumann＂ GPU of the Graduate Program in Biometrics and Applied Statistics of the Department of Statistics and Informatics of the Federal Rural University of Pernambuco was used. According to the interpolations carried out, it was possible to detect the wettest and driest seasons, as well as peculiar characteristics of the rainfall regime in the Northeast region of Brazil.