@InProceedings{CoelhoBittMoreSant:2022:MéClÁr,
               author = "Coelho, Marcelly Homem and Bittencourt, Olga Oliveira and Morelli, 
                         Fabiano and Santos, Rafael Duarte Coelho dos",
          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)}",
                title = "M{\'e}todo para a Classifica{\c{c}}{\~a}o de {\'A}reas 
                         Queimadas Baseado em Aprendizado de M{\'a}quina Automatizado",
            booktitle = "Anais...",
                 year = "2022",
                pages = "029",
         organization = "Computer on the Beach",
             keywords = "Burnt areas, Automated machine learning, Classification,, 
                         Supervised learning, Remote sensing.",
             abstract = "Forest fires burn large areas of native vegetation and it causes 
                         impacts in the social, economic and ecological scope. Burnt areas 
                         classification can help understand fires occurrence and support 
                         public policies. This work aims to develop a method of automatic 
                         burnt areas classification. The method is based on the application 
                         of Automated Machine Learning in data sets, from the Landsat8/OLI 
                         satellite images of 2018 and 2019. We intend to answer the 
                         following research question: Is it possible to automate the choice 
                         of machine learning models and maintain quality levels in the 
                         classification of burnt areas?. The contribution of this research 
                         is to determine whether a predictive model, trained with validated 
                         samples from 2018, is capable of classifying fires occurrences in 
                         2019. For the performance evaluation, the following metrics were 
                         analyzed: precision, probability of detection and average success 
                         rate. The results indicate that the method has a high potential to 
                         classify burnt areas.",
  conference-location = "Itaja{\'{\i}}, SC",
      conference-year = "05-07 maio 2022",
                  doi = "10.14210/cotb.v13.p029-036",
                  url = "http://dx.doi.org/10.14210/cotb.v13.p029-036",
                label = "lattes: 0096913881679975 4 
                         HomemCoelhoOlivMoreSant:2022:M{\'e}Cl{\'A}r",
             language = "pt",
           targetfile = "029.pdf",
        urlaccessdate = "16 maio 2024"
}