Land-cover Mapping in the Brazilian Amazon Using SPOT-4 Vegetation Data and Machine Learning Classification Methods
The main objective of this study is to evaluate the feasibility of deriving a land-cover map of the state of Mato Grosso, Brazil, for the year 2000, using data from the 1 km SPOT-4 VEGETATION (VGT) sensor. For this purpose we used a VGT temporal series of 12 monthly composite images, which were furt...
Gespeichert in:
| Veröffentlicht in: | Photogrammetric engineering and remote sensing 2006-08, Vol.72 (8), p.897-910 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 910 |
|---|---|
| container_issue | 8 |
| container_start_page | 897 |
| container_title | Photogrammetric engineering and remote sensing |
| container_volume | 72 |
| creator | Carreiras, João M.B. Pereira, José M.C. Shimabukuro, Yosio E. |
| description | The main objective of this study is to evaluate the feasibility of deriving a land-cover map of the state of Mato Grosso, Brazil, for the year 2000, using data from the 1 km SPOT-4 VEGETATION (VGT) sensor. For this purpose we used a VGT temporal series of 12 monthly composite images,
which were further transformed to physical-meaningful fraction images of vegetation, soil, and shade. Classification of fraction images was implemented using several recent machine learning developments, namely, filtering input training data and probability bagging in a classification tree
approach.A 10-fold cross validation accuracy assessment indicates that filtering and probability bagging are effective at increasing overall and class-specific accuracy. Overall accuracy and mean probability of class membership were 0.88 and 0.80, respectively. The map of probability
of class membership indicates that the larger errors are associated with cerrado savanna and semi-deciduous forest. |
| doi_str_mv | 10.14358/PERS.72.8.897 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_ingen</sourceid><recordid>TN_cdi_proquest_miscellaneous_28926788</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ingid>asprs/pers/2006/00000072/00000008/art00001</ingid><sourcerecordid>28801432</sourcerecordid><originalsourceid>FETCH-LOGICAL-c568t-5af5a2e325fa52ebfc882d4a5bec43e0333a33d8c2e9a2609cf342af00d4b3673</originalsourceid><addsrcrecordid>eNqNkcFv0zAUhyMEEmVw5ZwL3FLs5yR2jlvZYFKnTmzjar06L62n1Am2O4n-9ThkEqdJ-GBb9vc-W--XZR85W_JSVOrL7eWPu6WEpVqqRr7KFiBkWSgmm9fZgrGmKTjn8DZ7F8IjY4JXXC6ysEbXFmZ4Ip_f4Dhat8uty-Oe8guPJ9tbdPn5AU-Dyx_CdHt3u7kvyvwn7ShitOn8K0bMkyYJzN46yteE3k3sqscQbGfNDN5Q3A9teJ-96bAP9OF5Pcseri7vV9-L9ebb9ep8XZiqVrGosKsQSEDVYQW07YxS0JZYbcmUgpgQAoVolQFqEGrWmE6UgB1jbbkVtRRn2efZO_rh15FC1AcbDPU9OhqOQYNqoJZK_QeoWGoxJHA5g8YPIXjq9OjtAf1vzZn-G4KeQtAStNIphFTw6dmMwWDfeXTGhn9VMjFcTtxm5lLXyEXUj8PRu9QcbY3GMPqgpwSnAPWTBKc0MOBMQXoWRK1b6vDYRx3R691JB56MFy8YZ91IaQLG6iSeRvryvGFKo4_Thos_oXC3Sg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>28801432</pqid></control><display><type>article</type><title>Land-cover Mapping in the Brazilian Amazon Using SPOT-4 Vegetation Data and Machine Learning Classification Methods</title><source>IngentaConnect</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Carreiras, João M.B. ; Pereira, José M.C. ; Shimabukuro, Yosio E.</creator><creatorcontrib>Carreiras, João M.B. ; Pereira, José M.C. ; Shimabukuro, Yosio E.</creatorcontrib><description>The main objective of this study is to evaluate the feasibility of deriving a land-cover map of the state of Mato Grosso, Brazil, for the year 2000, using data from the 1 km SPOT-4 VEGETATION (VGT) sensor. For this purpose we used a VGT temporal series of 12 monthly composite images,
which were further transformed to physical-meaningful fraction images of vegetation, soil, and shade. Classification of fraction images was implemented using several recent machine learning developments, namely, filtering input training data and probability bagging in a classification tree
approach.A 10-fold cross validation accuracy assessment indicates that filtering and probability bagging are effective at increasing overall and class-specific accuracy. Overall accuracy and mean probability of class membership were 0.88 and 0.80, respectively. The map of probability
of class membership indicates that the larger errors are associated with cerrado savanna and semi-deciduous forest.</description><identifier>ISSN: 0099-1112</identifier><identifier>EISSN: 2374-8079</identifier><identifier>DOI: 10.14358/PERS.72.8.897</identifier><identifier>CODEN: PERSDV</identifier><language>eng</language><publisher>Bethesda, MD: American Society for Photogrammetry and Remote Sensing</publisher><subject>Animal, plant and microbial ecology ; Applied geophysics ; Biological and medical sciences ; Earth sciences ; Earth, ocean, space ; Exact sciences and technology ; Fundamental and applied biological sciences. Psychology ; General aspects. Techniques ; Internal geophysics ; Teledetection and vegetation maps</subject><ispartof>Photogrammetric engineering and remote sensing, 2006-08, Vol.72 (8), p.897-910</ispartof><rights>2006 INIST-CNRS</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c568t-5af5a2e325fa52ebfc882d4a5bec43e0333a33d8c2e9a2609cf342af00d4b3673</citedby><cites>FETCH-LOGICAL-c568t-5af5a2e325fa52ebfc882d4a5bec43e0333a33d8c2e9a2609cf342af00d4b3673</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>289,314,777,781,27905,27906</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=17973177$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Carreiras, João M.B.</creatorcontrib><creatorcontrib>Pereira, José M.C.</creatorcontrib><creatorcontrib>Shimabukuro, Yosio E.</creatorcontrib><title>Land-cover Mapping in the Brazilian Amazon Using SPOT-4 Vegetation Data and Machine Learning Classification Methods</title><title>Photogrammetric engineering and remote sensing</title><description>The main objective of this study is to evaluate the feasibility of deriving a land-cover map of the state of Mato Grosso, Brazil, for the year 2000, using data from the 1 km SPOT-4 VEGETATION (VGT) sensor. For this purpose we used a VGT temporal series of 12 monthly composite images,
which were further transformed to physical-meaningful fraction images of vegetation, soil, and shade. Classification of fraction images was implemented using several recent machine learning developments, namely, filtering input training data and probability bagging in a classification tree
approach.A 10-fold cross validation accuracy assessment indicates that filtering and probability bagging are effective at increasing overall and class-specific accuracy. Overall accuracy and mean probability of class membership were 0.88 and 0.80, respectively. The map of probability
of class membership indicates that the larger errors are associated with cerrado savanna and semi-deciduous forest.</description><subject>Animal, plant and microbial ecology</subject><subject>Applied geophysics</subject><subject>Biological and medical sciences</subject><subject>Earth sciences</subject><subject>Earth, ocean, space</subject><subject>Exact sciences and technology</subject><subject>Fundamental and applied biological sciences. Psychology</subject><subject>General aspects. Techniques</subject><subject>Internal geophysics</subject><subject>Teledetection and vegetation maps</subject><issn>0099-1112</issn><issn>2374-8079</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2006</creationdate><recordtype>article</recordtype><recordid>eNqNkcFv0zAUhyMEEmVw5ZwL3FLs5yR2jlvZYFKnTmzjar06L62n1Am2O4n-9ThkEqdJ-GBb9vc-W--XZR85W_JSVOrL7eWPu6WEpVqqRr7KFiBkWSgmm9fZgrGmKTjn8DZ7F8IjY4JXXC6ysEbXFmZ4Ip_f4Dhat8uty-Oe8guPJ9tbdPn5AU-Dyx_CdHt3u7kvyvwn7ShitOn8K0bMkyYJzN46yteE3k3sqscQbGfNDN5Q3A9teJ-96bAP9OF5Pcseri7vV9-L9ebb9ep8XZiqVrGosKsQSEDVYQW07YxS0JZYbcmUgpgQAoVolQFqEGrWmE6UgB1jbbkVtRRn2efZO_rh15FC1AcbDPU9OhqOQYNqoJZK_QeoWGoxJHA5g8YPIXjq9OjtAf1vzZn-G4KeQtAStNIphFTw6dmMwWDfeXTGhn9VMjFcTtxm5lLXyEXUj8PRu9QcbY3GMPqgpwSnAPWTBKc0MOBMQXoWRK1b6vDYRx3R691JB56MFy8YZ91IaQLG6iSeRvryvGFKo4_Thos_oXC3Sg</recordid><startdate>20060801</startdate><enddate>20060801</enddate><creator>Carreiras, João M.B.</creator><creator>Pereira, José M.C.</creator><creator>Shimabukuro, Yosio E.</creator><general>American Society for Photogrammetry and Remote Sensing</general><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>KR7</scope><scope>H8D</scope><scope>L7M</scope></search><sort><creationdate>20060801</creationdate><title>Land-cover Mapping in the Brazilian Amazon Using SPOT-4 Vegetation Data and Machine Learning Classification Methods</title><author>Carreiras, João M.B. ; Pereira, José M.C. ; Shimabukuro, Yosio E.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c568t-5af5a2e325fa52ebfc882d4a5bec43e0333a33d8c2e9a2609cf342af00d4b3673</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2006</creationdate><topic>Animal, plant and microbial ecology</topic><topic>Applied geophysics</topic><topic>Biological and medical sciences</topic><topic>Earth sciences</topic><topic>Earth, ocean, space</topic><topic>Exact sciences and technology</topic><topic>Fundamental and applied biological sciences. Psychology</topic><topic>General aspects. Techniques</topic><topic>Internal geophysics</topic><topic>Teledetection and vegetation maps</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Carreiras, João M.B.</creatorcontrib><creatorcontrib>Pereira, José M.C.</creatorcontrib><creatorcontrib>Shimabukuro, Yosio E.</creatorcontrib><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>Civil Engineering Abstracts</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>Photogrammetric engineering and remote sensing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Carreiras, João M.B.</au><au>Pereira, José M.C.</au><au>Shimabukuro, Yosio E.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Land-cover Mapping in the Brazilian Amazon Using SPOT-4 Vegetation Data and Machine Learning Classification Methods</atitle><jtitle>Photogrammetric engineering and remote sensing</jtitle><date>2006-08-01</date><risdate>2006</risdate><volume>72</volume><issue>8</issue><spage>897</spage><epage>910</epage><pages>897-910</pages><issn>0099-1112</issn><eissn>2374-8079</eissn><coden>PERSDV</coden><abstract>The main objective of this study is to evaluate the feasibility of deriving a land-cover map of the state of Mato Grosso, Brazil, for the year 2000, using data from the 1 km SPOT-4 VEGETATION (VGT) sensor. For this purpose we used a VGT temporal series of 12 monthly composite images,
which were further transformed to physical-meaningful fraction images of vegetation, soil, and shade. Classification of fraction images was implemented using several recent machine learning developments, namely, filtering input training data and probability bagging in a classification tree
approach.A 10-fold cross validation accuracy assessment indicates that filtering and probability bagging are effective at increasing overall and class-specific accuracy. Overall accuracy and mean probability of class membership were 0.88 and 0.80, respectively. The map of probability
of class membership indicates that the larger errors are associated with cerrado savanna and semi-deciduous forest.</abstract><cop>Bethesda, MD</cop><pub>American Society for Photogrammetry and Remote Sensing</pub><doi>10.14358/PERS.72.8.897</doi><tpages>14</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0099-1112 |
| ispartof | Photogrammetric engineering and remote sensing, 2006-08, Vol.72 (8), p.897-910 |
| issn | 0099-1112 2374-8079 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_28926788 |
| source | IngentaConnect; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals |
| subjects | Animal, plant and microbial ecology Applied geophysics Biological and medical sciences Earth sciences Earth, ocean, space Exact sciences and technology Fundamental and applied biological sciences. Psychology General aspects. Techniques Internal geophysics Teledetection and vegetation maps |
| title | Land-cover Mapping in the Brazilian Amazon Using SPOT-4 Vegetation Data and Machine Learning Classification Methods |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T16%3A37%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ingen&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Land-cover%20Mapping%20in%20the%20Brazilian%20Amazon%20Using%20SPOT-4%20Vegetation%20Data%20and%20Machine%20Learning%20Classification%20Methods&rft.jtitle=Photogrammetric%20engineering%20and%20remote%20sensing&rft.au=Carreiras,%20Jo%C3%A3o%20M.B.&rft.date=2006-08-01&rft.volume=72&rft.issue=8&rft.spage=897&rft.epage=910&rft.pages=897-910&rft.issn=0099-1112&rft.eissn=2374-8079&rft.coden=PERSDV&rft_id=info:doi/10.14358/PERS.72.8.897&rft_dat=%3Cproquest_ingen%3E28801432%3C/proquest_ingen%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=28801432&rft_id=info:pmid/&rft_ingid=asprs/pers/2006/00000072/00000008/art00001&rfr_iscdi=true |