Remote sensing mapping of macroalgal farms by modifying thresholds in the classification tree

Handle URI:
http://hdl.handle.net/10754/627905
Title:
Remote sensing mapping of macroalgal farms by modifying thresholds in the classification tree
Authors:
Zheng, Yuhan; Duarte, Carlos M. ( 0000-0002-1213-1361 ) ; Chen, Jiang; Li, Dan; Lou, Zhaohan; Wu, Jiaping
Abstract:
Remote sensing is the main approach used to classify and map aquatic vegetation, and classification tree (CT) analysis is superior to various classification methods. Based on previous studies, modified CT can be developed from traditional CT by adjusting the thresholds based on the statistical relationship between spectral features to classify different images without ground-truth data. However, no studies have yet employed this method to resolve marine vegetation. In this study, three Gao-Fen 1 satellite images obtained with the same sensor on January 30, 2014, November 5, 2014, and January 21, 2015 were selected, and two features were then employed to extract macroalgae from aquaculture farms from the seawater background. Besides, object-based classification and other image analysis methods were adopted to improve the classification accuracy in this study. Results show that the overall accuracies of traditional CTs for three images are 92.0%, 94.2% and 93.9%, respectively, whereas the overall accuracies of the two corresponding modified CTs for images obtained on January 21, 2015 and November 5, 2014 are 93.1% and 89.5%, respectively. This indicates modified CTs can help map macroalgae with multi-date imagery and monitor the spatiotemporal distribution of macroalgae in coastal environments.
KAUST Department:
Biological and Environmental Sciences and Engineering (BESE) Division; Marine Science Program; Red Sea Research Center (RSRC)
Citation:
Zheng Y, Duarte CM, Chen J, Li D, Lou Z, et al. (2018) Remote sensing mapping of macroalgal farms by modifying thresholds in the classification tree. Geocarto International: 1–18. Available: http://dx.doi.org/10.1080/10106049.2018.1474272.
Publisher:
Informa UK Limited
Journal:
Geocarto International
Issue Date:
7-May-2018
DOI:
10.1080/10106049.2018.1474272
Type:
Article
ISSN:
1010-6049; 1752-0762
Sponsors:
Acknowledgement This research was partially funded by the State Oceanic Administration (Grant # 529105-T21702, Strategy and Implementation of Blue Carbon Program in China, and Grant # 529105-T01603, Sino-Australian joint research on measures and strategies of ocean eutrophication control).
Additional Links:
https://www.tandfonline.com/doi/abs/10.1080/10106049.2018.1474272
Appears in Collections:
Articles; Red Sea Research Center (RSRC); Marine Science Program; Biological and Environmental Sciences and Engineering (BESE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorZheng, Yuhanen
dc.contributor.authorDuarte, Carlos M.en
dc.contributor.authorChen, Jiangen
dc.contributor.authorLi, Danen
dc.contributor.authorLou, Zhaohanen
dc.contributor.authorWu, Jiapingen
dc.date.accessioned2018-05-17T06:24:05Z-
dc.date.available2018-05-17T06:24:05Z-
dc.date.issued2018-05-07en
dc.identifier.citationZheng Y, Duarte CM, Chen J, Li D, Lou Z, et al. (2018) Remote sensing mapping of macroalgal farms by modifying thresholds in the classification tree. Geocarto International: 1–18. Available: http://dx.doi.org/10.1080/10106049.2018.1474272.en
dc.identifier.issn1010-6049en
dc.identifier.issn1752-0762en
dc.identifier.doi10.1080/10106049.2018.1474272en
dc.identifier.urihttp://hdl.handle.net/10754/627905-
dc.description.abstractRemote sensing is the main approach used to classify and map aquatic vegetation, and classification tree (CT) analysis is superior to various classification methods. Based on previous studies, modified CT can be developed from traditional CT by adjusting the thresholds based on the statistical relationship between spectral features to classify different images without ground-truth data. However, no studies have yet employed this method to resolve marine vegetation. In this study, three Gao-Fen 1 satellite images obtained with the same sensor on January 30, 2014, November 5, 2014, and January 21, 2015 were selected, and two features were then employed to extract macroalgae from aquaculture farms from the seawater background. Besides, object-based classification and other image analysis methods were adopted to improve the classification accuracy in this study. Results show that the overall accuracies of traditional CTs for three images are 92.0%, 94.2% and 93.9%, respectively, whereas the overall accuracies of the two corresponding modified CTs for images obtained on January 21, 2015 and November 5, 2014 are 93.1% and 89.5%, respectively. This indicates modified CTs can help map macroalgae with multi-date imagery and monitor the spatiotemporal distribution of macroalgae in coastal environments.en
dc.description.sponsorshipAcknowledgement This research was partially funded by the State Oceanic Administration (Grant # 529105-T21702, Strategy and Implementation of Blue Carbon Program in China, and Grant # 529105-T01603, Sino-Australian joint research on measures and strategies of ocean eutrophication control).en
dc.publisherInforma UK Limiteden
dc.relation.urlhttps://www.tandfonline.com/doi/abs/10.1080/10106049.2018.1474272en
dc.rightsArchived with thanks to Geocarto Internationalen
dc.subjectmacroalgaeen
dc.subjectmodified classification treeen
dc.subjectGF-1en
dc.subjectclassification accuracyen
dc.titleRemote sensing mapping of macroalgal farms by modifying thresholds in the classification treeen
dc.typeArticleen
dc.contributor.departmentBiological and Environmental Sciences and Engineering (BESE) Divisionen
dc.contributor.departmentMarine Science Programen
dc.contributor.departmentRed Sea Research Center (RSRC)en
dc.identifier.journalGeocarto Internationalen
dc.eprint.versionPost-printen
dc.contributor.institutionKey Laboratory of Ocean Observation-Imaging Testbed of Zhejiang Province, Zhejiang University, Zhoushan, Chinaen
dc.contributor.institutionOcean College, Zhejiang University, Zhoushan, Chinaen
dc.contributor.institutionThe University of Western Australia, Oceans Institute, 35 Stirling Hwy, Crawley, WA 6009, Australiaen
dc.contributor.institutionCollege of Environment and Natural Resources, Zhejiang University, Hangzhou, Chinaen
kaust.authorDuarte, Carlos M.en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.