Reconstructing Three Decades of Land Use and Land Cover Changes in Brazilian Biomes with Landsat Archive and Earth Engine

Abstract

Brazil has a monitoring system to track annual forest conversion in the Amazon and most recently to monitor the Cerrado biome. However, there is still a gap of annual land use and land cover (LULC) information in all Brazilian biomes in the country. Existing countrywide efforts to map land use and land cover lack regularly updates and high spatial resolution time-series data to better understand historical land use and land cover dynamics, and the subsequent impacts in the country biomes. In this study, we described a novel approach and the results achieved by a multi-disciplinary network called MapBiomas to reconstruct annual land use and land cover information between 1985 and 2017 for Brazil, based on random forest applied to Landsat archive using Google Earth Engine. We mapped five major classes: forest, non-forest natural formation, farming, non-vegetated areas, and water. These classes were broken into two sub-classification levels leading to the most comprehensive and detailed mapping for the country at a 30 m pixel resolution. The average overall accuracy of the land use and land cover time-series, based on a stratified random sample of 75,000 pixel locations, was 89% ranging from 73 to 95% in the biomes. The 33 years of LULC change data series revealed that Brazil lost 71 Mha of natural vegetation, mostly to cattle ranching and agriculture activities. Pasture expanded by 46% from 1985 to 2017, and agriculture by 172%, mostly replacing old pasture fields. We also identified that 86 Mha of the converted native vegetation was undergoing some level of regrowth. Several applications of the MapBiomas dataset are underway, suggesting that reconstructing historical land use and land cover change maps is useful for advancing the science and to guide social, economic and environmental policy decision-making processes in Brazil.

Hidden destruction of older forests threatens Brazil’s Atlantic Forest and challenges restoration programs

“…The MapBiomas initiative, a collaborative consortium of multiple organizations initiated in Brazil, has produced annual land use and land cover (LULC) time series based on 30-m-resolution Landsat data using random forests machine learning algorithm, in which native and exotic tree covers are differentiated and the age of native forests is estimated ( 21 ). This novel methodological approach offers valuable opportunities for mapping native forests’ restoration and conservation dynamics ( 22 , 23 ), which have a critical role in tracking the progress of ambitious restoration and tree planting commitments such as the Bonn Challenge and the 1t.org of the World Economic Forum, as well as the upcoming United Nations’ Decade on Ecosystem Restoration (2021–2030).…”

Assessing Land Use and Land Cover Changes in the Direct Influence Zone of the Braço Norte Hydropower Complex, Brazilian Amazonia

“…This algorithm classifies targets using the spectral response of each Brazilian biome from the database, automatically classifying areas with the same spectral pattern [37]. The applied method, fully described in MapBiomas 2020b and in Souza Junior et al 2020 [26,36], distinguishes 22 LULC classes in the most detailed classification level (level 3).…”

“…With the advance of remote sensing, image processing, and machine learning techniques, novel approaches have been developed to complement the Brazilian official monitoring system to track annual deforestation in the Amazon. These efforts are highlighted in the MapBiomas project, which consists of a multi-disciplinary network responsible for providing annual LULC maps for the entire Brazilian territory since the 1980s using the Landsat Archive and the Google Earth Engine platform [25,26], allowing the analysis of LULCC for long time periods.…”

An improved rainfall-threshold approach for robust prediction and warning of flood and flash flood hazards

“…Generally, Long-term (1950Long-term ( -1990) mean annual rainfall obtained from the meteorological stations used by Alvares et al (2013). f Landsatbased land use and land cover map for 2017 provided by the MapBiomas Project (Souza et al 2020) April and September are the driest months in São Paulo State (Fig. 2).…”