<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Journal Article">
		<site>plutao.sid.inpe.br 800</site>
		<holdercode>{isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S}</holdercode>
		<identifier>8JMKD3MGP3W/3TEP936</identifier>
		<repository>sid.inpe.br/plutao/2019/06.10.13.42.13</repository>
		<lastupdate>2019:06.13.11.28.17 dpi.inpe.br/plutao@80/2008/08.19.15.01 simone</lastupdate>
		<metadatarepository>sid.inpe.br/plutao/2019/06.10.13.42.14</metadatarepository>
		<metadatalastupdate>2024:01.23.15.43.58 dpi.inpe.br/plutao@80/2008/08.19.15.01 simone {D 2019}</metadatalastupdate>
		<doi>10.1002/rse2.111</doi>
		<issn>2056-3485</issn>
		<label>lattes: 5174466549126882 9 WagnerSTLFAGPA:2019:UsUnCo</label>
		<citationkey>WagnerSTLFAGPA:2019:UsUnCo</citationkey>
		<title>Using the U-net convolutional network to map forest types and disturbance in the Atlantic rainforest with very high resolution images</title>
		<year>2019</year>
		<typeofwork>journal article</typeofwork>
		<secondarytype>PRE PI</secondarytype>
		<numberoffiles>1</numberoffiles>
		<size>2438 KiB</size>
		<author>Wagner, Fabien Hubert,</author>
		<author>Sanchez, Alber,</author>
		<author>Tarabalka, Yuliya,</author>
		<author>Lotte, Rodolfo Georjute,</author>
		<author>Ferreira, Matheus Pinheiro,</author>
		<author>Aidar, Marcos P. M.,</author>
		<author>Gloor, Emanuel,</author>
		<author>Phillips, Oliver L.,</author>
		<author>Aragão, Luiz Eduardo Oliveira e Cruz de,</author>
		<group>DIDSR-CGOBT-INPE-MCTIC-GOV-BR</group>
		<group>COCST-COCST-INPE-MCTIC-GOV-BR</group>
		<group></group>
		<group>CGCEA-CGCEA-INPE-MCTIC-GOV-BR</group>
		<group>SER-SRE-SESPG-INPE-MCTIC-GOV-BR</group>
		<group></group>
		<group></group>
		<group></group>
		<group>DIDSR-CGOBT-INPE-MCTIC-GOV-BR</group>
		<affiliation>Instituto Nacional de Pesquisas Espaciais (INPE)</affiliation>
		<affiliation>Instituto Nacional de Pesquisas Espaciais (INPE)</affiliation>
		<affiliation>Inria Sophia Antipo</affiliation>
		<affiliation>Instituto Nacional de Pesquisas Espaciais (INPE)</affiliation>
		<affiliation>Instituto Nacional de Pesquisas Espaciais (INPE)</affiliation>
		<affiliation>Institute of Botany</affiliation>
		<affiliation>University of Leeds</affiliation>
		<affiliation>University of Leeds</affiliation>
		<affiliation>Instituto Nacional de Pesquisas Espaciais (INPE)</affiliation>
		<electronicmailaddress>wagner.h.fabien@gmail.com</electronicmailaddress>
		<electronicmailaddress>alber.ipia@inpe.br</electronicmailaddress>
		<electronicmailaddress></electronicmailaddress>
		<electronicmailaddress>rodolfo.lotte@inpe.br</electronicmailaddress>
		<electronicmailaddress></electronicmailaddress>
		<electronicmailaddress></electronicmailaddress>
		<electronicmailaddress></electronicmailaddress>
		<electronicmailaddress></electronicmailaddress>
		<electronicmailaddress>luiz.aragao@inpe.br</electronicmailaddress>
		<journal>Remote Sensing in Ecology and Conservation</journal>
		<volume>2019</volume>
		<pages>1</pages>
		<transferableflag>1</transferableflag>
		<contenttype>External Contribution</contenttype>
		<versiontype>publisher</versiontype>
		<keywords>Deep learning, Image segmentation, Keras, Rstudio, Tensorflow, Tree crown delineation, Tree species detection, Vegetation type detection, WorldView-3 image.</keywords>
		<abstract>Mapping forest types and tree species at regional scales to provide information for ecologists and forest managers is a new challenge for the remote sensing community. Here, we assess the potential of a U-net convolutional network, a recent deep learning algorithm, to identify and segment (1) natural forests and eucalyptus plantations, and (2) an indicator of forest disturbance, the tree species Cecropia hololeuca, in very high resolution images (0.3 m) from the WorldView-3 satellite in the Brazilian Atlantic rainforest region. The networks for forest types and Cecropia trees were trained with 7611 and 1568 red-greenblue (RGB) images, respectively, and their dense labeled masks. Eighty per cent of the images were used for training and 20% for validation. The U-net network segmented forest types with an overall accuracy >95% and an intersection over union (IoU) of 0.96. For C. hololeuca, the overall accuracy was 97% and the IoU was 0.86. The predictions were produced over a 1600 km2 region using WorldView-3 RGB bands pan-sharpened at 0.3 m. Natural and eucalyptus forests compose 79 and 21% of the regions total forest cover (82 250 ha). Cecropia crowns covered 1% of the natural forest canopy. An index to describe the level of disturbance of the natural forest fragments based on the spatial distribution of Cecropia trees was developed. Our work demonstrates how a deep learning algorithm can support applications such as vegetation, tree species distributions and disturbance mapping on a regional scale.</abstract>
		<area>SRE</area>
		<language>en</language>
		<targetfile>Wagner_et_al_Unet_2019.pdf</targetfile>
		<usergroup>lattes</usergroup>
		<readergroup>administrator</readergroup>
		<readergroup>lattes</readergroup>
		<readergroup>simone</readergroup>
		<visibility>shown</visibility>
		<readpermission>deny from all and allow from 150.163</readpermission>
		<documentstage>not transferred</documentstage>
		<nexthigherunit>8JMKD3MGPCW/3ER446E</nexthigherunit>
		<nexthigherunit>8JMKD3MGPCW/3EU2FR5</nexthigherunit>
		<nexthigherunit>8JMKD3MGPCW/3F3NU5S</nexthigherunit>
		<nexthigherunit>8JMKD3MGPCW/3F3T29H</nexthigherunit>
		<citingitemlist>sid.inpe.br/bibdigital/2013/10.18.22.34 1</citingitemlist>
		<dissemination>WEBSCI; PORTALCAPES; SCOPUS.</dissemination>
		<hostcollection>dpi.inpe.br/plutao@80/2008/08.19.15.01</hostcollection>
		<notes>Prêmio CAPES Elsevier 2023 - ODS 15: Vida terrestre</notes>
		<username>simone</username>
		<lasthostcollection>dpi.inpe.br/plutao@80/2008/08.19.15.01</lasthostcollection>
		<url>http://plutao.sid.inpe.br/rep-/sid.inpe.br/plutao/2019/06.10.13.42.13</url>
	</metadata>
</metadatalist>