Abstract
Widespread in the subtropics and tropics of the Southern Hemisphere, savannas are highly heterogeneous and seasonal natural vegetation types, which makes change detection (natural vs. anthropogenic) a challenging task. The Brazilian Cerrado represents the largest savanna in South America, and the most threatened biome in Brazil owing to agricultural expansion. To assess the native Cerrado vegetation (NV) areas most susceptible to natural and anthropogenic change over time, we classified 33 years (1985–2017) of Landsat imagery available in the Google Earth Engine (GEE) platform. The classification strategy used combined empirical and statistical decision trees to generate reference maps for machine learning classification and a novel annual dataset of the predominant Cerrado NV types (forest, savanna, and grassland). We obtained annual NV maps with an average overall accuracy ranging from 87% (at level 1 NV classification) to 71% over the time series, distinguishing the three main NV types. This time series was then used to generate probability maps for each NV class. The native vegetation in the Cerrado biome declined at an average rate of 0.5% per year (748,687 ha yr−1), mostly affecting forests and savannas. From 1985 to 2017, 24.7 million hectares of NV were lost, and now only 55% of the NV original distribution remains. Of the remnant NV in 2017 (112.6 million hectares), 65% has been stable over the years, while 12% changed among NV types, and 23% was converted to other land uses but is now in some level of secondary NV. Our results were fundamental in indicating areas with higher rates of change in a long time series in the Brazilian Cerrado and to highlight the challenges of mapping distinct NV types in a highly seasonal and heterogeneous savanna biome.
Highlights
Widespread in the subtropics and tropics of the Southern Hemisphere, savannas cover approximately 20% of the Earth’s terrestrial surface—around 65% of Africa, 60% of Australia, and 45% of South America [1,2]
The machine learning approach used here, which combined the statistical decision tree (SDT) based on randomly selected samples in areas previously classified by the empirical decision tree (EDT) as stable over the first time series (2000–2016), increased accuracy at Level 1 by 4%: accuracy at Level 1 for the EDT alone was 83%, while accuracy for the final SDT classification was 87%
This study was the first to apply a combination of EDT and SDT classification techniques for mapping different types of native vegetation in the Cerrado biome, using a long time series of satellite data (1985–2017)
Summary
Widespread in the subtropics and tropics of the Southern Hemisphere, savannas cover approximately 20% of the Earth’s terrestrial surface—around 65% of Africa, 60% of Australia, and 45% of South America [1,2] They are naturally heterogeneous in terms of climate, soil, biodiversity, and threats posed by human activities and land occupation [3]. Mainly distributed in the central part of Brazil, the Cerrado presents a large latitudinal and longitudinal variation, resulting in different ecoregions [6] It is formed by a mosaic of open grasslands, shrublands, savanna woodlands, deciduous or semi-deciduous forests, and evergreen riparian forests [7]. The rate of conversion of native Cerrado vegetation (NV) is up to two times the conversion observed in the Amazon in the past five years [12], and most of the native vegetation conversion tends to occur in areas with dense vegetation (favorable climate and soil conditions) and flat terrains (suitable for mechanized farming) [13]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
