@InProceedings{BaymaPere:2017:CoMaLe,
               author = "Bayma, Lucas O. and Pereira, Marconi A.",
          affiliation = "{Universidade Federal de S{\~a}o Jo{\~a}o Del Rei (UFSJ)} and 
                         {Universidade Federal de S{\~a}o Jo{\~a}o Del Rei (UFSJ)}",
                title = "Comparison of machine learning techniques for the estimation of 
                         climate missing data in the state of Minas Gerais, Brazil",
            booktitle = "Anais...",
                 year = "2017",
               editor = "Davis Jr., Clodoveu A. (UFMG) and Queiroz, Gilberto R. de (INPE)",
                pages = "283--294",
         organization = "Simp{\'o}sio Brasileiro de Geoinform{\'a}tica, 18. (GEOINFO)",
            publisher = "Instituto Nacional de Pesquisas Espaciais (INPE)",
              address = "S{\~a}o Jos{\'e} dos Campos",
             abstract = "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.",
  conference-location = "Salvador",
      conference-year = "04-06 dez. 2017",
                 issn = "2179-4820",
             language = "pt",
                  ibi = "8JMKD3MGPDW34P/3Q5DQ6H",
                  url = "http://urlib.net/ibi/8JMKD3MGPDW34P/3Q5DQ6H",
           targetfile = "36bayma_pereira.pdf",
        urlaccessdate = "27 abr. 2024"
}