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

Yuhan Zheng, Carlos M. Duarte, Jiang Chen, Dan Li, Zhaohan Lou, Jiaping Wu

Research output: Contribution to journalArticle

Abstract

Remote sensing is the main approach to map aquatic vegetation, and classification tree (CT) 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 on 30 January 2014, 5 November 2014 and 21 January 2015 were selected, and two features were then employed to extract macroalgae farms. Results show that the overall accuracies of traditional CTs for three images are 92.0, 94.2 and 93.9%, respectively, whereas those of the two corresponding modified CTs for images obtained on 21 January 2015 and 5 November 2014 are 93.1 and 89.5%, respectively. This indicates modified CTs can map macroalgae with multi-date imagery and monitor their spatiotemporal distribution in coastal environments.

Original languageEnglish
Pages (from-to)1-11
Number of pages11
JournalGeocarto International
DOIs
Publication statusE-pub ahead of print - 4 Jun 2018

Fingerprint

farm
remote sensing
vegetation
fen
coastal zone
imagery
method

Cite this

Zheng, Yuhan ; Duarte, Carlos M. ; Chen, Jiang ; Li, Dan ; Lou, Zhaohan ; Wu, Jiaping. / Remote sensing mapping of macroalgal farms by modifying thresholds in the classification tree. In: Geocarto International. 2018 ; pp. 1-11.
@article{883c060432674c3590f2bafe5036dee5,
title = "Remote sensing mapping of macroalgal farms by modifying thresholds in the classification tree",
abstract = "Remote sensing is the main approach to map aquatic vegetation, and classification tree (CT) 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 on 30 January 2014, 5 November 2014 and 21 January 2015 were selected, and two features were then employed to extract macroalgae farms. Results show that the overall accuracies of traditional CTs for three images are 92.0, 94.2 and 93.9{\%}, respectively, whereas those of the two corresponding modified CTs for images obtained on 21 January 2015 and 5 November 2014 are 93.1 and 89.5{\%}, respectively. This indicates modified CTs can map macroalgae with multi-date imagery and monitor their spatiotemporal distribution in coastal environments.",
keywords = "classification accuracy, GF-1, Macroalgae, modified classification tree",
author = "Yuhan Zheng and Duarte, {Carlos M.} and Jiang Chen and Dan Li and Zhaohan Lou and Jiaping Wu",
year = "2018",
month = "6",
day = "4",
doi = "10.1080/10106049.2018.1474272",
language = "English",
pages = "1--11",
journal = "Geocarto International",
issn = "1010-6049",
publisher = "Taylor & Francis",

}

Remote sensing mapping of macroalgal farms by modifying thresholds in the classification tree. / Zheng, Yuhan; Duarte, Carlos M.; Chen, Jiang; Li, Dan; Lou, Zhaohan; Wu, Jiaping.

In: Geocarto International, 04.06.2018, p. 1-11.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Remote sensing mapping of macroalgal farms by modifying thresholds in the classification tree

AU - Zheng, Yuhan

AU - Duarte, Carlos M.

AU - Chen, Jiang

AU - Li, Dan

AU - Lou, Zhaohan

AU - Wu, Jiaping

PY - 2018/6/4

Y1 - 2018/6/4

N2 - Remote sensing is the main approach to map aquatic vegetation, and classification tree (CT) 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 on 30 January 2014, 5 November 2014 and 21 January 2015 were selected, and two features were then employed to extract macroalgae farms. Results show that the overall accuracies of traditional CTs for three images are 92.0, 94.2 and 93.9%, respectively, whereas those of the two corresponding modified CTs for images obtained on 21 January 2015 and 5 November 2014 are 93.1 and 89.5%, respectively. This indicates modified CTs can map macroalgae with multi-date imagery and monitor their spatiotemporal distribution in coastal environments.

AB - Remote sensing is the main approach to map aquatic vegetation, and classification tree (CT) 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 on 30 January 2014, 5 November 2014 and 21 January 2015 were selected, and two features were then employed to extract macroalgae farms. Results show that the overall accuracies of traditional CTs for three images are 92.0, 94.2 and 93.9%, respectively, whereas those of the two corresponding modified CTs for images obtained on 21 January 2015 and 5 November 2014 are 93.1 and 89.5%, respectively. This indicates modified CTs can map macroalgae with multi-date imagery and monitor their spatiotemporal distribution in coastal environments.

KW - classification accuracy

KW - GF-1

KW - Macroalgae

KW - modified classification tree

UR - http://www.scopus.com/inward/record.url?scp=85048019994&partnerID=8YFLogxK

U2 - 10.1080/10106049.2018.1474272

DO - 10.1080/10106049.2018.1474272

M3 - Article

SP - 1

EP - 11

JO - Geocarto International

JF - Geocarto International

SN - 1010-6049

ER -