@InProceedings{PujattiPereSilv:2022:ToPrGr,
               author = "Pujatti, Mario Arthur Sclafani and Pereira, Marconi de Arruda and 
                         Silvestre, Leonardo Jos{\'e}",
          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)} and 
                         {Universidade Federal do Esp{\'{\i}}rito Santo (UFES)}",
                title = "A tool to predict the growth of urban regions based on 
                         QGIS/MOLUSCE using MapBiomas image time series",
            booktitle = "Anais...",
                 year = "2022",
               editor = "Rosim, Sergio (INPE) and Santos, Leonardo Bacelar Lima (CEMADEN) 
                         and Pereira, Marconi de Arruda (UFSJ)",
         organization = "Simp{\'o}sio Brasileiro de Geoinform{\'a}tica, 23. (GEOINFO)",
            publisher = "Instituto Nacional de Pesquisas Espaciais (INPE)",
              address = "S{\~a}o Jos{\'e} dos Campos",
             abstract = "This paper presents a method to generate future scenarios of Land- 
                         Use and Land-Cover (LULC) classification images by implementing an 
                         artificial neural network that can be used to predict urban 
                         growth. In this study, LULC data from 1985 to 2020 with annual 
                         intervals, obtained through MapBiomas, were used. These data were 
                         inserted into a neural network integrated with the MOLUSCE plugin 
                         from QGIS to model the possible spatio-temporal changes to 
                         simulate the evolution of LULC. MapBiomas is a powerful tool, that 
                         uses data from time series from Landsat Satellites and machine 
                         learning algorithms to provide reliable products. Our analysis 
                         focused on cities that have expanded greatly over the past two 
                         decades according to studies made by IBGE. The results obtained 
                         were better than those presented in related works, obtaining a 
                         kappa value of 0.74 and an accuracy value of at least 80% in all 
                         tests performed.",
  conference-location = "On-line",
      conference-year = "28 a 30 nov. 2022",
                 issn = "2179-4847",
             language = "en",
                  ibi = "8JMKD3MGPDW34P/487M2LE",
                  url = "http://urlib.net/ibi/8JMKD3MGPDW34P/487M2LE",
           targetfile = "86-98_Pujatti_Tool.pdf",
        urlaccessdate = "16 maio 2024"
}