Mapping Deforestation Using Fractions Indices and the Non-Seasonal PVts-β Detection Approach

This letter focuses on the mapping of deforestation between 2008 and 2018 in a small region in Brazil through time series. Vegetation indices as variables that are strongly influenced by seasonality were used. Whereas to reduce seasonality in the time series, dense series of fraction indices obtained from the physical spectral mixture analysis (SMA) model were used. Both the indices were obtained from Landsat images. Then, changes were detected through a non-seasonal detection approach (called PVts-
$\beta $
approach). To evaluate the detections obtained, true ground reference data of the study area were used. Results showed that the quantifications obtained with fraction indices had an overall accuracy (OA) of 90.00% higher than vegetation indices. Additionally, the different atmospheric correction algorithms strongly influenced the values of the fraction indices. This study focuses on the basis for future work to implement the PVts-
$\beta $
approach on platforms such as Google Earth engine (GEE).