@Article{ShimabukuroArDuDuCaSaHo:2020:DiLaUs,
               author = "Shimabukuro, Yosio Edemir and Arai, Eg{\'{\i}}dio and Duarte, 
                         Valdete and Dutra, Andeise Cerqueira and Cassol, Henrique Luis 
                         Godinho and Sano, Edson Eyji and Hoffmann, T{\^a}nia Beatriz",
          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 {Empresa Brasileira de Pesquisa Agropecu{\'a}ria 
                         (EMBRAPA)} and {Instituto Nacional de Pesquisas Espaciais 
                         (INPE)}",
                title = "Discriminating land use and land cover classes in Brazil based on 
                         the annual PROBA-V 100 m time series",
              journal = "IEEE Journal of Selected Topics in Applied Earth Observations and 
                         Remote Sensing",
                 year = "2020",
               volume = "13",
                pages = "3409--3420",
             keywords = "—Fraction images, image processing, linear spectral mixing model 
                         (LSMM), random forest (RF).",
             abstract = "Brazil, with more than 8 million km2, presents six different 
                         biomes, ranging from natural grasslands (Pampa biome) to tropical 
                         rainfall forests (Amaz{\^o}nia biome), with different land-use 
                         types (mostly pasturelands and croplands) and pressures (mainly in 
                         the Cerrado biome). The objective of this article is to present a 
                         new method to discriminate the most representative land use and 
                         land cover (LULC) classes of Brazil, based on the PROBA-V images. 
                         The images were converted into vegetation, soil, and shade 
                         fraction images by applying the linear spectral mixing model. 
                         Then, the pixel-based, highest proportion, annual mosaics of the 
                         fraction images, and their corresponding standard deviation images 
                         were derived and classified using the random forest algorithm. The 
                         following LULC classes were considered: forestlands, shrublands, 
                         grasslands, croplands, pasturelands, water bodies, and others. An 
                         agreement analysis was conducted with two available LULC maps 
                         derived from the Landsat satellite, the MapBiomas, and the Finer 
                         Resolution Observation and Monitoring-Global Land Cover (FROM-GLC) 
                         projects. Forestlands (412 million ha) and pasturelands (242 
                         million ha) were the two most representative LULC classes; and 
                         croplands accounted for 30 million ha. The results presented an 
                         overall agreement of 69% and 58% with the MapBiomas and FROM-GLC 
                         projects, respectively. The proposed method is a good alternative 
                         to support operational projects of LULC map production that are 
                         important for planning biodiversity conservation or 
                         environmentally sustainable land occupation.",
                  doi = "10.1109/JSTARS.2020.2994893",
                  url = "http://dx.doi.org/10.1109/JSTARS.2020.2994893",
                 issn = "1939-1404 and 2151-1535",
             language = "en",
           targetfile = "shimabukuro_discriminating.pdf",
        urlaccessdate = "27 abr. 2024"
}