Mining dense Landsat time series for separating cropland and pasture in a heterogeneous Brazilian savanna landscape

Abstract

Better spatial information on the global distribution of croplands and pastures is urgently needed. Without reliable cropland-pasture separation it will be impossible to retrieve high-quality information on agricultural expansion or land use intensification, and on related ecosystem service provision. In this context, the savanna biome is critically important, but information on land use and land cover (LULC) is notoriously inaccurate in these areas. This is due to pronounced spatial-temporal dynamics of agricultural land use and spectral similarities between cropland, pasture, and natural savanna vegetation. In this study, we investigated the potential to reliably separate cropland, pasture, natural savanna vegetation, and other relevant land cover classes employing Landsat-derived spectral-temporal variability metrics for a savanna landscape in the Brazilian Cerrado. In order to better understand the surplus value and limitations of spectral-temporal variability metrics for classification purposes, we analyzed four datasets of different temporal depth, using 344 Landsat scenes across four footprints between 2009 and 2012. Our results showed a reliable separation between cropland, pasture, and natural savanna vegetation achieving an adjusted overall accuracy of 93%. A similar accuracy and spatial consistency of LULC classification could not be achieved based on spectral information alone, indicating the high additional value of temporal information for identifying LULC classes in the complex land use systems of savanna landscapes. There is great potential for transferring our approach to other savanna systems which still suffer from inaccurate LULC information.