%0 Conference Proceedings
%4 sid.inpe.br/mtc-m16c/2017/12.01.20.04
%2 sid.inpe.br/mtc-m16c/2017/12.01.20.04.55
%@issn 2179-4820
%T Comparison of machine learning techniques for the estimation of climate missing data in the state of Minas Gerais, Brazil
%D 2017
%A Bayma, Lucas O.,
%A Pereira, Marconi A.,
%@affiliation Universidade Federal de São João Del Rei (UFSJ)
%@affiliation Universidade Federal de São João Del Rei (UFSJ)
%E Davis Jr., Clodoveu A. (UFMG),
%E Queiroz, Gilberto R. de (INPE),
%B Simpósio Brasileiro de Geoinformática, 18 (GEOINFO)
%C Salvador
%8 04-06 dez. 2017
%I Instituto Nacional de Pesquisas Espaciais (INPE)
%J São José dos Campos
%P 283-294
%S Anais
%X Climatepredictionisarelevantactivityforhumanityand,forthesuc- cess of the climate forecast, a good historical database is necessary. However, because of several factors, large historical data gaps are found at different me- teorological stations, and studies to determine such missing weather values are still scarce. This paper describes a study of a combination of several machine learning techniques to determine missing climatic values. This study produced a computational framework, formed by four different methods: linear regres- sion, neural networks, support vector machines and regression bagged trees. A statistical study is conducted to compare these four methods. The study statis- tically demonstrated that the regression bagged trees technique was successful in obtaining missing climatic values for the state of Minas Gerais and can be widely used by the responsible agencies to improve their historical databases, consequently, their climate forecasts.
%@language pt
%3 36bayma_pereira.pdf