<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Conference Proceedings">
		<site>marte2.sid.inpe.br 802</site>
		<holdercode>{isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S}</holdercode>
		<identifier>8JMKD3MGP6W34M/3JM4BFG</identifier>
		<repository>sid.inpe.br/marte2/2015/06.15.15.24.32</repository>
		<lastupdate>2015:06.15.15.24.32 dpi.inpe.br/marte2/2013/05.17.15.03.06 banon</lastupdate>
		<metadatarepository>sid.inpe.br/marte2/2015/06.15.15.24.33</metadatarepository>
		<metadatalastupdate>2018:06.06.03.21.37 dpi.inpe.br/marte2/2013/05.17.15.03.06 administrator {D 2015}</metadatalastupdate>
		<isbn>978-85-17-0076-8</isbn>
		<label>640</label>
		<citationkey>AntunesLampRodr:2015:MaCuCa</citationkey>
		<title>Mapeamento do cultivo da cana-de-açúcar por meio da classificação de séries temporais de dados MODIS</title>
		<format>Internet</format>
		<year>2015</year>
		<secondarytype>PRE CN</secondarytype>
		<numberoffiles>1</numberoffiles>
		<size>642 KiB</size>
		<author>Antunes, João Francisco Gonçalves,</author>
		<author>Lamparelli, Rubens Augusto Camargo,</author>
		<author>Rodrigues, Luiz Henrique Antunes,</author>
		<electronicmailaddress>joao.antunes@embrapa.br</electronicmailaddress>
		<editor>Gherardi, Douglas Francisco Marcolino,</editor>
		<editor>Aragão, Luiz Eduardo Oliveira e Cruz de,</editor>
		<e-mailaddress>wanderf@dsr.inpe.br</e-mailaddress>
		<conferencename>Simpósio Brasileiro de Sensoriamento Remoto, 17 (SBSR)</conferencename>
		<conferencelocation>João Pessoa</conferencelocation>
		<date>25-29 abr. 2015</date>
		<publisher>Instituto Nacional de Pesquisas Espaciais (INPE)</publisher>
		<publisheraddress>São José dos Campos</publisheraddress>
		<pages>3237-3244</pages>
		<booktitle>Anais</booktitle>
		<organization>Instituto Nacional de Pesquisas Espaciais (INPE)</organization>
		<transferableflag>1</transferableflag>
		<abstract>MODIS (Moderate Resolution Imaging Spectroradiometer) data provide coverage of large areas and high periodicity. These characteristics are fundamental to analyze strategic agricultural crops in Brazil, such as sugarcane. The harmonic analysis can be used for the study of time-series of remote sensing data in order to evaluate the temporal behavior of vegetation indices. New approaches to artificial intelligence combining neural networks and fuzzy logic to the pattern recognition for the classification of time-series satellite imagery prove to be a timely, viable and innovative alternative. In this context, the objective of this study was to map the sugarcane cultivation through the classification based on neuro-fuzzy networks using MODIS vegetation indices time-series, in São Paulo State, throughout crop years from 2004/2005 to 2011/2012. The results showed the potential of harmonic analysis on the decomposition of MODIS vegetation indices time-series, whose understanding was important to evidence changes in the sugarcane development and to reveal patterns of temporal dynamics for the task of image classification. The maps generated by the Fuzzy ARTMAP classification models achieved high accuracy and low disagreement. The Fuzzy ARTMAP classifier using the harmonics terms of the EVI and NDVI time-series was efficient for sugarcane cultivation mapping, it produced classification models of great quality thematic and reliable for the purpose of agricultural statistics.</abstract>
		<area>SRE</area>
		<type>Produção e previsão agrícola</type>
		<language>pt</language>
		<targetfile>p0640.pdf</targetfile>
		<usergroup>banon</usergroup>
		<visibility>shown</visibility>
		<mirrorrepository>urlib.net/www/2011/03.29.20.55</mirrorrepository>
		<nexthigherunit>8JMKD3MGP6W34M/3JJLLP2</nexthigherunit>
		<citingitemlist>sid.inpe.br/marte2/2015/05.31.21.54 5</citingitemlist>
		<hostcollection>dpi.inpe.br/marte2/2013/05.17.15.03.06</hostcollection>
		<username>banon</username>
		<lasthostcollection>dpi.inpe.br/marte2/2013/05.17.15.03.06</lasthostcollection>
		<url>http://marte2.sid.inpe.br/rep-/sid.inpe.br/marte2/2015/06.15.15.24.32</url>
	</metadata>
</metadatalist>