@Article{UeharaCoQuKöDuDa:2020:CoAmAr,
               author = "Uehara, Tatiana Dias Tardelli and Corr{\^e}a, Sabrina Paes Leme 
                         Passos and Quevedo, Renata Pacheco and K{\"o}rting, Thales Sehn 
                         and Dutra, Luciano Vieira and Daleles Renn{\'o}, Camilo",
          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)}",
                title = "Landslide scars detection using remote sensing and pattern 
                         recognition techniques: comparison among artificial neural 
                         networks, gaussian maximum likelihood, random forest, and support 
                         vector machine classifiers",
              journal = "Revista Brasileira de Cartografia",
                 year = "2020",
               volume = "72",
               number = "4",
                pages = "665--680",
             keywords = "mass movement, hazard, supervised classification, pattern 
                         recognition, Movimentos de Massa, Perigo.",
             abstract = "Landslide inventory is an essential tool to support disaster risk 
                         mitigation. The inventory is usually obtained via conventional 
                         methods, as visual interpretation of remote sensing images, or 
                         semi-automaticmethods,through pattern recognition.In this study, 
                         four classification algorithms are compared to detect 
                         landslidesscars: Artificial Neural Network (ANN), Maximum 
                         Likelihood (ML), Random Forest (RF) and Support Vector Machine 
                         (SVM). From Sentinel-2A imageryandSRTMsDigital Elevation 
                         Model(DEM), vegetation indices and slope featureswere extracted 
                         and selected for two areas at the Rolante River Catchment, in 
                         Brazil.The classification products showed that the ML and the RF 
                         presented superior resultswithOA values above 92% for both study 
                         areas. These best accuracys results were identified in 
                         classifications using all attributes as input, so without previous 
                         feature selection.",
                  doi = "10.14393/rbcv72n4-54037",
                  url = "http://dx.doi.org/10.14393/rbcv72n4-54037",
                 issn = "0560-4613 and 1808-0936",
                label = "lattes: 9425692453156168 1 UeharaCoQuK{\"o}DuRe:2020:CoAmAr",
             language = "fr",
           targetfile = "uehara_landslide.pdf",
                  url = "http://www.seer.ufu.br/index.php/revistabrasileiracartografia/article/view/54037/30208",
        urlaccessdate = "27 abr. 2024"
}