<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Journal Article">
		<site>mtc-m21d.sid.inpe.br 808</site>
		<holdercode>{isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S}</holdercode>
		<identifier>8JMKD3MGP3W34T/48EG228</identifier>
		<repository>sid.inpe.br/mtc-m21d/2023/01.27.12.28</repository>
		<lastupdate>2023:01.27.12.28.32 urlib.net/www/2021/06.04.03.40 simone</lastupdate>
		<metadatarepository>sid.inpe.br/mtc-m21d/2023/01.27.12.28.32</metadatarepository>
		<metadatalastupdate>2024:01.02.17.16.39 urlib.net/www/2021/06.04.03.40 administrator {D 2023}</metadatalastupdate>
		<doi>10.3390/rs15020521</doi>
		<issn>2072-4292</issn>
		<citationkey>WagnerSSCRHOS:2023:MaTrFo</citationkey>
		<title>Mapping Tropical Forest Cover and Deforestation with Planet NICFI Satellite Images and Deep Learning in Mato Grosso State (Brazil) from 2015 to 2021</title>
		<year>2023</year>
		<month>Jan.</month>
		<typeofwork>journal article</typeofwork>
		<secondarytype>PRE PI</secondarytype>
		<numberoffiles>1</numberoffiles>
		<size>19366 KiB</size>
		<author>Wagner, Fabien Hubert,</author>
		<author>Silva, Ricardo Dalagnol da,</author>
		<author>Silva-Junior, Celso Henrique Leite,</author>
		<author>Carter, Griffina,</author>
		<author>Ritz, Alison L.,</author>
		<author>Hirye, Mayumi C. M.,</author>
		<author>Ometto, Jean Pierre Henry Balbaud,</author>
		<author>Saatchi, Sassan,</author>
		<orcid></orcid>
		<orcid></orcid>
		<orcid>0000-0002-1052-5551</orcid>
		<orcid></orcid>
		<orcid></orcid>
		<orcid></orcid>
		<orcid>0000-0002-4221-1039</orcid>
		<group></group>
		<group></group>
		<group></group>
		<group></group>
		<group></group>
		<group></group>
		<group>DIPE3-COGPI-INPE-MCTI-GOV-BR</group>
		<affiliation>University of California</affiliation>
		<affiliation>University of California</affiliation>
		<affiliation>University of California</affiliation>
		<affiliation>University of California</affiliation>
		<affiliation>CTREES, Pasadena</affiliation>
		<affiliation>Universidade de São Paulo (USP)</affiliation>
		<affiliation>Instituto Nacional de Pesquisas Espaciais (INPE)</affiliation>
		<affiliation>University of California</affiliation>
		<electronicmailaddress>fhwagner@ucla.edu</electronicmailaddress>
		<electronicmailaddress>ricds@hotmail.com</electronicmailaddress>
		<electronicmailaddress></electronicmailaddress>
		<electronicmailaddress></electronicmailaddress>
		<electronicmailaddress></electronicmailaddress>
		<electronicmailaddress></electronicmailaddress>
		<electronicmailaddress>jean.ometto@inpe.br</electronicmailaddress>
		<journal>Remote Sensing</journal>
		<volume>15</volume>
		<number>2</number>
		<pages>e521</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>land-cover and land-use, semantic segmentation, TensorFlow 2, tropical forests, U-net.</keywords>
		<abstract>Monitoring changes in tree cover for assessment of deforestation is a premise for policies to reduce carbon emission in the tropics. Here, a U-net deep learning model was used to map monthly tropical tree cover in the Brazilian state of Mato Grosso between 2015 and 2021 using 5 m spatial resolution Planet NICFI satellite images. The accuracy of the tree cover model was extremely high, with an F1-score >0.98, further confirmed by an independent LiDAR validation showing that 95% of tree cover pixels had a height >5 m while 98% of non-tree cover pixels had a height <5 m. The biannual map of deforestation was then built from the monthly tree cover map. The deforestation map showed relatively consistent agreement with the official deforestation map from Brazil (67.2%) but deviated significantly from Global Forest Change (GFC)s year of forest loss, showing that our product is closest to the product made by visual interpretation. Finally, we estimated that 14.8% of Mato Grossos total area had undergone clear-cut logging between 2015 and 2021, and that deforestation was increasing, with December 2021, the last date, being the highest. High-resolution imagery from Planet NICFI in conjunction with deep learning techniques can significantly improve the mapping of deforestation extent in tropical regions.</abstract>
		<area>CST</area>
		<language>en</language>
		<targetfile>remotesensing-15-00521.pdf</targetfile>
		<usergroup>simone</usergroup>
		<readergroup>administrator</readergroup>
		<readergroup>simone</readergroup>
		<visibility>shown</visibility>
		<archivingpolicy>allowpublisher allowfinaldraft</archivingpolicy>
		<documentstage>not transferred</documentstage>
		<nexthigherunit>8JMKD3MGPCW/46L2FGP</nexthigherunit>
		<citingitemlist>sid.inpe.br/bibdigital/2022/04.04.04.47 2</citingitemlist>
		<dissemination>WEBSCI; PORTALCAPES; MGA; COMPENDEX; SCOPUS.</dissemination>
		<hostcollection>urlib.net/www/2021/06.04.03.40</hostcollection>
		<username>simone</username>
		<agreement>agreement.html .htaccess .htaccess2</agreement>
		<lasthostcollection>urlib.net/www/2021/06.04.03.40</lasthostcollection>
		<url>http://mtc-m21d.sid.inpe.br/rep-/sid.inpe.br/mtc-m21d/2023/01.27.12.28</url>
	</metadata>
</metadatalist>