@Article{MarettoFoJaKöBePa:2021:SpDeLe,
               author = "Maretto, Raian Vargas and Fonseca, Leila Maria Garcia and Jacobs, 
                         Nathan and K{\"o}rting, Thales Sehn and Bendini, Hugo do 
                         Nascimento and Parente, Leandro L.",
          affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto 
                         Nacional de Pesquisas Espaciais (INPE)} and {} and {Instituto 
                         Nacional de Pesquisas Espaciais (INPE)} and {Instituto Nacional de 
                         Pesquisas Espaciais (INPE)}",
                title = "Spatio-Temporal Deep Learning Approach to Map Deforestation in 
                         Amazon Rainforest",
              journal = "IEEE Geoscience and Remote Sensing Letters",
                 year = "2021",
               volume = "18",
               number = "5",
                pages = "771--775",
                month = "May",
             keywords = "Task analysis, Forestry, Remote sensing, Training, Artificial 
                         satellites, Earth, Semantics, Convolutional neural networks 
                         (CNNs), deep learning (DL), deforestation, spatio-temporal 
                         analysis, U-Net.",
             abstract = "We address the task of mapping deforested areas in the Brazilian 
                         Amazon. Accurate maps are an important tool for informing 
                         effective deforestation containment policies. The main existing 
                         approaches to this task are largely manual, requiring significant 
                         effort by trained experts. To reduce this effort, we propose a 
                         fully automatic approach based on spatio-temporal deep 
                         convolutional neural networks. We introduce several 
                         domain-specific components, including approaches for: image 
                         preprocessing; handling image noise, such as clouds and shadow; 
                         and constructing the training data set. We show that our 
                         preprocessing protocol reduces the impact of noise in the training 
                         data set. Furthermore, we propose two spatio-temporal variations 
                         of the U-Net architecture, which make it possible to incorporate 
                         both spatial and temporal contexts. Using a large, real-world data 
                         set, we show that our method outperforms a traditional U-Net 
                         architecture, thus achieving approximately 95% accuracy.",
                  doi = "10.1109/LGRS.2020.2986407",
                  url = "http://dx.doi.org/10.1109/LGRS.2020.2986407",
                 issn = "1545-598X",
             language = "en",
           targetfile = "maretto_spatio.pdf",
        urlaccessdate = "20 maio 2024"
}