Assessing land use/cover dynamics and exploring drivers in the Amazon's arc of deforestation through a hierarchical, multi-scale and multi-temporal classification approach

Autor(es)

Garcia, Andrea S. ; Vilela, Vivian M. de F. N. ; Rizzo, Rodnei ; West, Paul ; Gerber, James S. ; Engstrom, Peder M. ; Ballester, Maria Victoria R.

• Tipo de documento: Artigo Científico
• Fonte: REMOTE SENSING APPLICATIONS-SOCIETY AND ENVIRONMENT; v. 15, p. 14-pg., 2019-08-01.

Resumo

Land use and land cover (LULC) are intrinsically tied to ecological and social dynamics. Still, classifying LULC in ecotones, where landscapes are commonly heterogeneous and have a wide range of physiognomies, remains a challenge. Here we present a three-level hierarchical classification approach, using both Landsat and MODIS images, and both pixels and objects as units of information. We applied this multi-temporal and -spatial approach to classify land use in the Upper Xingu River Basin (similar to 170,000 km(2)), located in the arc of deforestation of the Brazilian Amazon. The first level includes five classes and differentiates managed land from native vegetation with high overall accuracy (93%). The second level has 11 classes (overall accuracy= 86%) and separates main land uses and native vegetation domains. The third level has 16 classes (overall accuracy= 83%) and addresses productivity of both managed and natural systems. We find that this new method presented here is more efficient than existing regional and global land cover products. Applying this approach to assess land cover transitions in the basin from 1985 to 2015, we find that agricultural production increased, yet manifested itself differently in the northern (Amazon biome) and southern (Cerrado biome) portions of the basin. Analyzing land use change in different levels, we identify that agricultural intensification occurred mainly in the Amazon while the Cerrado has undergone an expansion in agricultural area. The method presented here can be adapted to other regions, improving efficiency and accuracy of classifying land cover in heterogeneous landscapes. (AU)

• Processo FAPESP: 13/20377-1 - Desenvolvimento do mapa de água virtual da soja na Bacia do Alto Xingu, MT - Brasil
• Beneficiário: Rodnei Rizzo
• Modalidade de apoio: Bolsas no Brasil - Doutorado
• Processo FAPESP: 15/05103-8 - Dinâmica do uso e da cobertura do solo na fronteira agrícola da Amazônia Brasileira: forçantes de mudanças e futuros cenários
• Beneficiário: Andrea Santos Garcia
• Modalidade de apoio: Bolsas no Brasil - Doutorado
• Processo FAPESP: 17/12787-6 - Dinâmica da intensificação do uso da terra na fronteira agrícola da Amazônia brasileira
• Beneficiário: Andrea Santos Garcia
• Modalidade de apoio: Bolsas no Exterior - Estágio de Pesquisa - Doutorado
• Processo FAPESP: 17/12567-6 - Avaliação do balanço hídrico no sudeste amazônico nas últimas duas décadas: empregando metodologia baseada em sensores remotos para descrever os recursos hídricos regionais
• Beneficiário: Rodnei Rizzo
• Modalidade de apoio: Bolsas no Exterior - Estágio de Pesquisa - Doutorado
• Processo FAPESP: 13/50180-5 - Xingu: integrando o planejamento do uso da terra e a governança da água na Amazônia: em busca da melhoria da segurança hídrica na fronteira agrícola do Mato Grosso
• Beneficiário: Alex Vladimir Krusche
• Modalidade de apoio: Auxílio à Pesquisa - Programa de Pesquisa sobre Mudanças Climáticas Globais - Temático