<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Journal Article">
		<site>mtc-m21c.sid.inpe.br 806</site>
		<holdercode>{isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S}</holdercode>
		<identifier>8JMKD3MGP3W34R/428S2R5</identifier>
		<repository>sid.inpe.br/mtc-m21c/2020/04.01.10.44</repository>
		<lastupdate>2020:04.01.10.44.01 urlib.net/www/2017/11.22.19.04 simone</lastupdate>
		<metadatarepository>sid.inpe.br/mtc-m21c/2020/04.01.10.44.01</metadatarepository>
		<metadatalastupdate>2024:01.23.16.31.51 urlib.net/www/2017/11.22.19.04 simone {D 2020}</metadatalastupdate>
		<doi>10.3390/rs12060910</doi>
		<issn>2072-4292</issn>
		<citationkey>AdarmeFeiHapAlmGom:2020:EvDeLe</citationkey>
		<title>Evaluation of deep learning techniques for deforestation detection in the brazilian amazon and cerrado biomes from remote sensing imagery</title>
		<year>2020</year>
		<month>Mar.</month>
		<secondarytype>PRE PI</secondarytype>
		<numberoffiles>1</numberoffiles>
		<size>20666 KiB</size>
		<author>Adarme, Mabel Ortega,</author>
		<author>Feitosa, Raul Queiroz,</author>
		<author>Happ, Patrick Nigri,</author>
		<author>Almeida, Cláudio Aparecido de,</author>
		<author>Gomes, Alessandra Rodrigues,</author>
		<orcid>0000-0002-4106-0291</orcid>
		<orcid>0000-0001-8344-5096</orcid>
		<orcid>0000-0003-3280-5471</orcid>
		<orcid>0000-0002-1032-6966</orcid>
		<group></group>
		<group></group>
		<group></group>
		<group>COAMZ-CGOBT-INPE-MCTIC-GOV-BR</group>
		<group>CRCRA-COCRE-INPE-MCTIC-GOV-BR</group>
		<affiliation>Pontifícia Universidade Católica do Rio de Janeiro (PUC-Rio)</affiliation>
		<affiliation>Pontifícia Universidade Católica do Rio de Janeiro (PUC-Rio)</affiliation>
		<affiliation>Pontifícia Universidade Católica do Rio de Janeiro (PUC-Rio)</affiliation>
		<affiliation>Instituto Nacional de Pesquisas Espaciais (INPE)</affiliation>
		<affiliation>Instituto Nacional de Pesquisas Espaciais (INPE)</affiliation>
		<electronicmailaddress>mortega@ele.puc-rio.br</electronicmailaddress>
		<electronicmailaddress>raul@ele.puc-rio.br</electronicmailaddress>
		<electronicmailaddress>patrick@ele.puc-rio.br</electronicmailaddress>
		<electronicmailaddress>claudio.almeida@inpe.br</electronicmailaddress>
		<electronicmailaddress>alessandra.gomes@inpe.br</electronicmailaddress>
		<journal>Remote Sensing</journal>
		<volume>12</volume>
		<number>6</number>
		<pages>e910</pages>
		<secondarymark>B3_GEOGRAFIA B3_ENGENHARIAS_I B4_GEOCIÊNCIAS B4_CIÊNCIAS_AMBIENTAIS B5_CIÊNCIAS_AGRÁRIAS_I</secondarymark>
		<transferableflag>1</transferableflag>
		<contenttype>External Contribution</contenttype>
		<versiontype>publisher</versiontype>
		<keywords>deforestation detection, Brazilian biomes, deep learning, optical imagery.</keywords>
		<abstract>Deforestation is one of the major threats to natural ecosystems. This process has a substantial contribution to climate change and biodiversity reduction. Therefore, the monitoring and early detection of deforestation is an essential process for preservation. Techniques based on satellite images are among the most attractive options for this application. However, many approaches involve some human intervention or are dependent on a manually selected threshold to identify regions that suffer deforestation. Motivated by this scenario, the present work evaluates Deep Learning-based strategies for automatic deforestation detection, namely, Early Fusion (EF), Siamese Network (SN), and Convolutional Support Vector Machine (CSVM) as well as Support Vector Machine (SVM), used as the baseline. The target areas are two regions with different deforestation patterns: the Amazon and Cerrado biomes in Brazil. The experiments used two co-registered Landsat 8 images acquired at different dates. The strategies based on Deep Learning achieved the best performance in our analysis in comparison with the baseline, with SN and EF superior to CSVM and SVM. In the same way, a reduction of the salt-and-pepper effect in the generated probabilistic change maps was noticed as the number of training samples increased. Finally, the work assesses how the methods can reduce the time invested in the visual inspection of deforested areas.</abstract>
		<area>SRE</area>
		<language>en</language>
		<targetfile>adarmel_evaluation.pdf</targetfile>
		<usergroup>simone</usergroup>
		<readergroup>administrator</readergroup>
		<readergroup>simone</readergroup>
		<visibility>shown</visibility>
		<archivingpolicy>allowpublisher allowfinaldraft</archivingpolicy>
		<documentstage>not transferred</documentstage>
		<nexthigherunit>8JMKD3MGPCW/3ETL435</nexthigherunit>
		<nexthigherunit>8JMKD3MGPCW/3EUAE4H</nexthigherunit>
		<citingitemlist>sid.inpe.br/bibdigital/2013/10.03.18.52 2</citingitemlist>
		<citingitemlist>sid.inpe.br/bibdigital/2013/09.29.19.53 1</citingitemlist>
		<dissemination>WEBSCI; PORTALCAPES; MGA; COMPENDEX; SCOPUS.</dissemination>
		<hostcollection>urlib.net/www/2017/11.22.19.04</hostcollection>
		<notes>Prêmio CAPES Elsevier 2023 - ODS 15: Vida terrestre</notes>
		<username>simone</username>
		<agreement>agreement.html .htaccess .htaccess2</agreement>
		<url>http://mtc-m21c.sid.inpe.br/rep-/sid.inpe.br/mtc-m21c/2020/04.01.10.44</url>
	</metadata>
</metadatalist>