@InProceedings{SilvaASSHDMD:2022:BuArLa,
               author = "Silva, Gabriel M{\'a}ximo da and Arai, Egidio and Shimabukuro, 
                         Yosio Edemir and Souza, Anielli Rosane de and Hoffmann, Tania 
                         Beatriz and Dutra, Andeise Cerqueira and Martini, Paulo Roberto 
                         and Duarte, Valdete",
          affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto 
                         Nacional de Pesquisas Espaciais (INPE)} and {Instituto Nacional de 
                         Pesquisas Espaciais (INPE)} and {Instituto Nacional de Pesquisas 
                         Espaciais (INPE)} and {Instituto Nacional de Pesquisas Espaciais 
                         (INPE)} and {Instituto Nacional de Pesquisas Espaciais (INPE)} and 
                         {Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto 
                         Nacional de Pesquisas Espaciais (INPE)}",
                title = "Burned Area in Land Use and Land Cover Classes in Sao Paulo State, 
                         Brazil",
            booktitle = "Proceedings...",
                 year = "2022",
         organization = "IEEE International Geoscience and Remote Sensing Symposium (IGARSS 
                         )",
            publisher = "IEEE",
             keywords = "Burned area, Image classification, Linear Spectral Mixing Model, 
                         LULC, Random Forest.",
             abstract = "This article presents a land use and land cover (LULC) 
                         classification map using Random Forest algorithm in the S{\~a}o 
                         Paulo State (Brazil), and an assessment of burned areas using two 
                         products (MCD64A1 and MapBiomas Fire). The method uses Landsat 
                         Operational Land Imager (OLI) time series images from January to 
                         December of 2020. We performed the classification class by class 
                         considering: water, urban area, forest formation, sugarcane, 
                         agriculture, forest plantation and pasture. For each class, we 
                         used different spectral bands and image fraction according to the 
                         best response for the class. For 2020, the top three areas mapped 
                         in S{\~a}o Paulo State were pasture (40.49%), sugarcane (24.74%) 
                         and forest formation (20.60%). Comparing the two burned area 
                         products, MCD64A1 mapped more burned areas as it uses MODIS images 
                         combined with 1 km active fire observations with higher temporal 
                         resolution than MapBiomas Fire. About 60% of the burned areas 
                         mapped in 2020 occurred in the sugarcane class. The results show 
                         the importance of land use and land cover classification for 
                         better understanding fire-prone classes given the spatial 
                         distribution. It turns as an environmental tool for environmental 
                         strategies of planning and monitoring burned area assessment over 
                         regional scales.",
  conference-location = "Kuala Lampur",
      conference-year = "17-22 July 2022",
                  doi = "10.1109/IGARSS46834.2022.9883049",
                  url = "http://dx.doi.org/10.1109/IGARSS46834.2022.9883049",
                 isbn = "978-166542792-0",
             language = "en",
           targetfile = "
                         
                         Burned_Area_in_Land_Use_and_Land_Cover_Classes_in_Sao_Paulo_State_Brazil.pdf",
        urlaccessdate = "17 maio 2024"
}