@Article{SilvaFonsKörtEsca:2020:SpBaNe,
               author = "Silva, Alexsandro C{\^a}ndido de Oliveira and Fonseca, Leila 
                         Maria Garcia and K{\"o}rting, Thales Sehn and Escada, Maria 
                         Isabel Sobral",
          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 = "A spatio-temporal Bayesian Network approach for deforestation 
                         prediction in an Amazon rainforest expansion frontier",
              journal = "Spatial Statistics",
                 year = "2020",
               volume = "35",
                pages = "e100393",
                month = "Mar.",
             keywords = "Bayesian Networks, Spatio-temporal modeling, Environmental 
                         modeling, Deforestation, Brazilian Amazon forest.",
             abstract = "In the last decade, Brazil has successfully managed to reduce 
                         deforestation in the Amazon forest. However, continued increases 
                         in annual deforestation rates call for environmental modeling to 
                         support short-term decision-making. This paper presents the 
                         functioning of a stepwise spatio-temporal Bayesian Network 
                         approach for spatially explicit analysis of deforestation risk 
                         based on observation data. The study area comprises a 
                         deforestation expansion frontier located in the southwest of 
                         Par{\'a} state, Brazil. The proposed approach has been successful 
                         in estimating deforestation risk over the years. Among the 
                         selected variables to compose the Bayesian Network model, distance 
                         from hot spots and distance from degraded areas present the 
                         highest contribution, while protected areas variable present a 
                         significant mitigation effect on the phenomenon. Accuracy 
                         assessment indices corroborate the agreement between deforestation 
                         events and predictions.",
                  doi = "10.1016/j.spasta.2019.100393",
                  url = "http://dx.doi.org/10.1016/j.spasta.2019.100393",
                 issn = "2211-6753",
             language = "en",
           targetfile = "silva_spatio.pdf",
        urlaccessdate = "28 abr. 2024"
}