%0 Journal Article
%4 sid.inpe.br/mtc-m21d/2022/01.10.14.05
%2 sid.inpe.br/mtc-m21d/2022/01.10.14.05.27
%@doi 10.3390/rs14010209
%@issn 2072-4292
%T Mapping Deforestation in Cerrado Based on Hybrid Deep Learning Architecture and Medium Spatial Resolution Satellite Time Series
%D 2022
%8 Jan.
%9 journal article
%A Matosak, Bruno Menini,
%A Fonseca, Leila Maria Garcia,
%A Taquary, Evandro Carrijo,
%A Maretto, Raian Vargas,
%A Bendini, Hugo do Nascimento,
%A Adami, Marcos,
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation University of Twente
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@electronicmailaddress bruno.matosak@inpe.br
%@electronicmailaddress leila.fonseca@inpe.br
%@electronicmailaddress evandro.taquary@inpe.br
%@electronicmailaddress r.v.maretto@utwente.nl
%@electronicmailaddress hugo.bendini@inpe.br
%@electronicmailaddress marcos.adami@inpe.br
%B Remote Sensing
%V 14
%N 1
%P e209
%K Brazilian savanna, Cerrado, Deforestation, Landsat, LSTM, Sentinel, Time series, U-Net.
%X Cerrado is the second largest biome in Brazil, covering about 2 million km2. This biome has experienced land use and land cover changes at high rates due to agricultural expansion so that more than 50% of its natural vegetation has already been removed. Therefore, it is crucial to provide technology capable of controlling and monitoring the Cerrado vegetation suppression in order to undertake the environmental conservation policies. Within this context, this work aims to develop a new methodology to detect deforestation in Cerrado through the combination of two Deep Learning (DL) architectures, Long Short-Term Memory (LSTM) and U-Net, and using Landsat and Sentinel image time series. In our proposed method, the LSTM evaluates the time series in relation to the time axis to create a deforestation probability map, which is spatially analyzed by the U-Net algorithm alongside the terrain slope to produce final deforestation maps. The method was applied in two different study areas, which better represent the main deforestation patterns present in Cerrado. The resultant deforestation maps based on cost-free Sentinel-2 images achieved high accuracy metrics, peaking at an overall accuracy of 99.81% ± 0.21 and F1-Score of 0.8795 ± 0.1180. In addition, the proposed method showed strong potential to automate the PRODES project, which provides the official Cerrado yearly deforestation maps based on visual interpretatio.
%@language en
%3 remotesensing-14-00209-v2.pdf