Abstract
Deforestation in the Amazon has important implications for biodiversity and climate change. However, land cover monitoring in this tropical forest is a challenge because it covers such a large area and the land cover change often occurs quickly, and sometimes cyclically. Here we adapt a method which eliminates the need to collect new training data samples for each update of an existing land cover map. We use the state-of-the-art probabilistic classifier Import Vector Machines and Landsat 8 Operational Land Imager (OLI) scenes of the area surrounding Novo Progresso, northern Brazil, to create an initial land cover map for 2013 with associated classification probabilities. We then conduct spectral change detection between 2013 and 2015 using a pair of Landsat images in order to identify the areas where land cover has changed between the two dates, and then reclassify these areas using a supervised classification algorithm, using pixels from the unchanged areas of the map as training data. In this study, we use the pixels with the highest classification probabilities to train the classifier for 2015 and compare the results to those obtained when pixels are chosen randomly. The use of probabilities in the selection of training samples improves the results compared to a random selection, with the highest overall accuracy achieved when 250 training samples with high probabilities are used. For training sample sizes greater than 1000, the differences in overall accuracy between the two approaches to training sample selection are reduced. The final updated 2015 map has an overall accuracy of 80.1%, compared to an overall accuracy of 82.5% for the 2013 map. The results show that this probabilistic method has potential to efficiently map the dynamic land cover change in the Amazon with limited training data, although some challenges remain.
NSTL
Elsevier