<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Conference Proceedings">
		<site>marte2.sid.inpe.br 802</site>
		<identifier>8JMKD3MGP6W34M/3U6L23S</identifier>
		<repository>sid.inpe.br/marte2/2019/10.04.16.43</repository>
		<lastupdate>2019:10.04.16.43.23 dpi.inpe.br/marte2/2013/05.17.15.03.06 administrator</lastupdate>
		<metadatarepository>sid.inpe.br/marte2/2019/10.04.16.43.23</metadatarepository>
		<metadatalastupdate>2020:01.06.12.30.35 dpi.inpe.br/marte2/2013/05.17.15.03.06 administrator {D 2019}</metadatalastupdate>
		<isbn>978-85-17-00097-3</isbn>
		<citationkey>SouzaAdVaSiFePoGo:2019:ClUsCo</citationkey>
		<title>Classificação de uso e cobertura da terra em áreas de não floresta do sudeste paraense através da plataforma Google Earth Engine (GEE)</title>
		<format>Internet</format>
		<year>2019</year>
		<secondarytype>PRE CN</secondarytype>
		<numberoffiles>1</numberoffiles>
		<size>1139 KiB</size>
		<author>Souza, Larisse Fernanda Pereira de,</author>
		<author>Adami, Marcos,</author>
		<author>Vale, Jones Remo Barbosa,</author>
		<author>Silva, Igor dos Santos e,</author>
		<author>Ferreira Neto, Luiz Cortinhas,</author>
		<author>Porto, Ingrid Cásslia Lima,</author>
		<author>Gomes, Alessandra Rodrigues,</author>
		<group></group>
		<group>CRCRA-COCRE-INPE-MCTIC-GOV-BR</group>
		<group></group>
		<group></group>
		<group></group>
		<group></group>
		<group>CRCRA-COCRE-INPE-MCTIC-GOV-BR</group>
		<affiliation>Universidade Federal do Pará (UFPA)</affiliation>
		<affiliation>Instituto Nacional de Pesquisas Espaciais (INPE)</affiliation>
		<affiliation>Universidade Federal Rural da Amazônia (UFRA)</affiliation>
		<affiliation>Universidade Federal Rural da Amazônia (UFRA)</affiliation>
		<affiliation>Universidade Federal do Pará (UFPA)</affiliation>
		<affiliation>Universidade Federal do Pará (UFPA)</affiliation>
		<affiliation>Instituto Nacional de Pesquisas Espaciais (INPE)</affiliation>
		<electronicmailaddress>larisse.souza14@gmail.com</electronicmailaddress>
		<electronicmailaddress>marcos.adami@inpe.br</electronicmailaddress>
		<electronicmailaddress>jonesremo@hotmail.com</electronicmailaddress>
		<electronicmailaddress>igorssilva20@gmail.com</electronicmailaddress>
		<electronicmailaddress>luizcf14@gmail.com</electronicmailaddress>
		<electronicmailaddress>ingrid.cassia@gmail.com</electronicmailaddress>
		<electronicmailaddress>alessandra.gomes@inpe.br</electronicmailaddress>
		<editor>Gherardi, Douglas Francisco Marcolino,</editor>
		<editor>Sanches, Ieda DelArco,</editor>
		<editor>Aragão, Luiz Eduardo Oliveira e Cruz de,</editor>
		<conferencename>Simpósio Brasileiro de Sensoriamento Remoto, 19 (SBSR)</conferencename>
		<conferencelocation>Santos</conferencelocation>
		<date>14-17 abril 2019</date>
		<publisher>Instituto Nacional de Pesquisas Espaciais (INPE)</publisher>
		<publisheraddress>São José dos Campos</publisheraddress>
		<pages>2642-2645</pages>
		<booktitle>Anais</booktitle>
		<tertiarytype>full paper</tertiarytype>
		<organization>Instituto Nacional de Pesquisas Espaciais (INPE)</organization>
		<transferableflag>1</transferableflag>
		<keywords>Classificação supervisionada Random Forest, Google Earth Engine, Supervised classification, Random Forest, Google Earth Engine.</keywords>
		<abstract>Este trabalho tem como objetivo apresentar um método de mapeamento da formação NF localizada no sudeste paraense a partir da base de dados da plataforma Google Earth Engine (GEE). Para a realização do mapeamento foram utilizados imagens do satélite Landsat 5,7, 8 e do MODIS para os anos de 2001, 2010 e 2017. O mapeamento foi realizado através da classificação supervisionada com o algoritmo Random Forest, obteve-se uma precisão global de 68%, no qual a classe a classe Savana Arborizada teve um alto índice de omissão, correspondendo a 0,94. A classe de pastagem foi confundida com a classe de savana apresentando o maior erro de inclusão. Portanto, o GEE através do algoritmo Random Forest mostrou-se uma ferramenta eficaz no mapeamento e classificação do uso da terra em áreas de NF. ABSTRACT: The objective of this paper is to present a method of mapping NF formation located in southeastern Pará from the database of the Google Earth Engine (GEE) platform. In order to perform the mapping, the Landsat 5,7, 8 and MODIS satellite images were used for the years 2001, 2010 and 2017. The mapping was performed through the supervised classification with the Randon Florest algorithm, obtaining an overall accuracy of 68%, in which the wooded savanna class had a high omission rate, corresponding to 0.94. The pasture class was confused with the savannah class presenting the largest inclusion error. Therefore, GEE using the Random Forest algorithm has proved to be an effective tool in the mapping and classification of land use in NF areas.</abstract>
		<area>SRE</area>
		<type>Mudança de uso e cobertura da Terra</type>
		<language>pt</language>
		<targetfile>97750.pdf</targetfile>
		<usergroup>simone</usergroup>
		<visibility>shown</visibility>
		<copyright>urlib.net/www/2012/11.12.15.19</copyright>
		<rightsholder>originalauthor yes</rightsholder>
		<documentstage>not transferred</documentstage>
		<mirrorrepository>urlib.net/www/2011/03.29.20.55</mirrorrepository>
		<nexthigherunit>8JMKD3MGP6W34M/3UCAT7H</nexthigherunit>
		<nexthigherunit>8JMKD3MGPCW/3EUAE4H</nexthigherunit>
		<citingitemlist>sid.inpe.br/bibdigital/2013/10.03.18.52 1</citingitemlist>
		<citingitemlist>sid.inpe.br/marte2/2019/11.08.12.52 1</citingitemlist>
		<hostcollection>dpi.inpe.br/marte2/2013/05.17.15.03.06</hostcollection>
		<username>simone</username>
		<lasthostcollection>dpi.inpe.br/marte2/2013/05.17.15.03.06</lasthostcollection>
		<url>http://marte2.sid.inpe.br/rep-/sid.inpe.br/marte2/2019/10.04.16.43</url>
	</metadata>
</metadatalist>