An efficient feature optimization for wetland mapping by synergistic use of SAR intensity, interferometry, and polarimetry data

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autorschaft

  • Fariba Mohammadimanesh
  • Bahram Salehi
  • Masoud Mahdianpari
  • Mahdi Motagh
  • Brian Brisco

Externe Organisationen

  • Memorial University of Newfoundland
  • Helmholtz-Zentrum Potsdam Deutsches GeoForschungsZentrum (GFZ)
  • Canada Center for Mapping and Earth Observation (CCMEO)
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Seiten (von - bis)450-462
Seitenumfang13
FachzeitschriftInternational Journal of Applied Earth Observation and Geoinformation
Jahrgang73
Frühes Online-Datum21 Juli 2018
PublikationsstatusVeröffentlicht - Dez. 2018

Abstract

Wetlands are home to a great variety of flora and fauna species and provide several unique environmental services. Knowledge of wetland species distribution is critical for sustainable management and resource assessment. In this study, multi-temporal single- and full-polarized RADARSAT-2 and single-polarized TerraSAR-X data were applied to characterize the wetland extent of a test site located in the north east of Newfoundland and Labrador, Canada. The accuracy and information content of wetland maps using remote sensing data depend on several factors, such as the type of data, input features, classification algorithms, and ecological characteristics of wetland classes. Most previous wetland studies examined the efficiency of one or two feature types, including intensity and polarimetry. Fewer investigations have examined the potential of interferometric coherence for wetland mapping. Thus, we evaluated the efficiency of using multiple feature types, including intensity, interferometric coherence, and polarimetric scattering for wetland mapping in multiple classification scenarios. An ensemble classifier, namely Random Forest (RF), and a kernel-based Support Vector Machine (SVM) were also used to determine the effect of the classifier. In all classification scenarios, SVM outperformed RF by 1.5-5%. The classification results demonstrated that the intensity features had a higher accuracy relative to coherence and polarimetric features. However, an inclusion of all feature types improved the classification accuracy for both RF and SVM classifiers. We also optimized the type and number of input features using an integration of RF variable importance and Spearman's rank-order correlation. The results of this analysis found that, of 81 input features, 22 were the most important uncorrelated features for classification. An overall classification accuracy of 85.4% was achieved by incorporating these 22 important uncorrelated features based on the proposed classification framework.

ASJC Scopus Sachgebiete

Zitieren

An efficient feature optimization for wetland mapping by synergistic use of SAR intensity, interferometry, and polarimetry data. / Mohammadimanesh, Fariba; Salehi, Bahram; Mahdianpari, Masoud et al.
in: International Journal of Applied Earth Observation and Geoinformation, Jahrgang 73, 12.2018, S. 450-462.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Mohammadimanesh, F, Salehi, B, Mahdianpari, M, Motagh, M & Brisco, B 2018, 'An efficient feature optimization for wetland mapping by synergistic use of SAR intensity, interferometry, and polarimetry data', International Journal of Applied Earth Observation and Geoinformation, Jg. 73, S. 450-462. https://doi.org/10.1016/j.jag.2018.06.005
Mohammadimanesh, F., Salehi, B., Mahdianpari, M., Motagh, M., & Brisco, B. (2018). An efficient feature optimization for wetland mapping by synergistic use of SAR intensity, interferometry, and polarimetry data. International Journal of Applied Earth Observation and Geoinformation, 73, 450-462. https://doi.org/10.1016/j.jag.2018.06.005
Mohammadimanesh F, Salehi B, Mahdianpari M, Motagh M, Brisco B. An efficient feature optimization for wetland mapping by synergistic use of SAR intensity, interferometry, and polarimetry data. International Journal of Applied Earth Observation and Geoinformation. 2018 Dez;73:450-462. Epub 2018 Jul 21. doi: 10.1016/j.jag.2018.06.005
Mohammadimanesh, Fariba ; Salehi, Bahram ; Mahdianpari, Masoud et al. / An efficient feature optimization for wetland mapping by synergistic use of SAR intensity, interferometry, and polarimetry data. in: International Journal of Applied Earth Observation and Geoinformation. 2018 ; Jahrgang 73. S. 450-462.
Download
@article{8673c0a2c5784359949926122a9579bb,
title = "An efficient feature optimization for wetland mapping by synergistic use of SAR intensity, interferometry, and polarimetry data",
abstract = "Wetlands are home to a great variety of flora and fauna species and provide several unique environmental services. Knowledge of wetland species distribution is critical for sustainable management and resource assessment. In this study, multi-temporal single- and full-polarized RADARSAT-2 and single-polarized TerraSAR-X data were applied to characterize the wetland extent of a test site located in the north east of Newfoundland and Labrador, Canada. The accuracy and information content of wetland maps using remote sensing data depend on several factors, such as the type of data, input features, classification algorithms, and ecological characteristics of wetland classes. Most previous wetland studies examined the efficiency of one or two feature types, including intensity and polarimetry. Fewer investigations have examined the potential of interferometric coherence for wetland mapping. Thus, we evaluated the efficiency of using multiple feature types, including intensity, interferometric coherence, and polarimetric scattering for wetland mapping in multiple classification scenarios. An ensemble classifier, namely Random Forest (RF), and a kernel-based Support Vector Machine (SVM) were also used to determine the effect of the classifier. In all classification scenarios, SVM outperformed RF by 1.5-5%. The classification results demonstrated that the intensity features had a higher accuracy relative to coherence and polarimetric features. However, an inclusion of all feature types improved the classification accuracy for both RF and SVM classifiers. We also optimized the type and number of input features using an integration of RF variable importance and Spearman's rank-order correlation. The results of this analysis found that, of 81 input features, 22 were the most important uncorrelated features for classification. An overall classification accuracy of 85.4% was achieved by incorporating these 22 important uncorrelated features based on the proposed classification framework.",
keywords = "Interferometric coherence, Random Forest, Support Vector Machine, Wetland",
author = "Fariba Mohammadimanesh and Bahram Salehi and Masoud Mahdianpari and Mahdi Motagh and Brian Brisco",
note = "{\textcopyright} 2018 Elsevier B.V. All rights reserved.",
year = "2018",
month = dec,
doi = "10.1016/j.jag.2018.06.005",
language = "English",
volume = "73",
pages = "450--462",

}

Download

TY - JOUR

T1 - An efficient feature optimization for wetland mapping by synergistic use of SAR intensity, interferometry, and polarimetry data

AU - Mohammadimanesh, Fariba

AU - Salehi, Bahram

AU - Mahdianpari, Masoud

AU - Motagh, Mahdi

AU - Brisco, Brian

N1 - © 2018 Elsevier B.V. All rights reserved.

PY - 2018/12

Y1 - 2018/12

N2 - Wetlands are home to a great variety of flora and fauna species and provide several unique environmental services. Knowledge of wetland species distribution is critical for sustainable management and resource assessment. In this study, multi-temporal single- and full-polarized RADARSAT-2 and single-polarized TerraSAR-X data were applied to characterize the wetland extent of a test site located in the north east of Newfoundland and Labrador, Canada. The accuracy and information content of wetland maps using remote sensing data depend on several factors, such as the type of data, input features, classification algorithms, and ecological characteristics of wetland classes. Most previous wetland studies examined the efficiency of one or two feature types, including intensity and polarimetry. Fewer investigations have examined the potential of interferometric coherence for wetland mapping. Thus, we evaluated the efficiency of using multiple feature types, including intensity, interferometric coherence, and polarimetric scattering for wetland mapping in multiple classification scenarios. An ensemble classifier, namely Random Forest (RF), and a kernel-based Support Vector Machine (SVM) were also used to determine the effect of the classifier. In all classification scenarios, SVM outperformed RF by 1.5-5%. The classification results demonstrated that the intensity features had a higher accuracy relative to coherence and polarimetric features. However, an inclusion of all feature types improved the classification accuracy for both RF and SVM classifiers. We also optimized the type and number of input features using an integration of RF variable importance and Spearman's rank-order correlation. The results of this analysis found that, of 81 input features, 22 were the most important uncorrelated features for classification. An overall classification accuracy of 85.4% was achieved by incorporating these 22 important uncorrelated features based on the proposed classification framework.

AB - Wetlands are home to a great variety of flora and fauna species and provide several unique environmental services. Knowledge of wetland species distribution is critical for sustainable management and resource assessment. In this study, multi-temporal single- and full-polarized RADARSAT-2 and single-polarized TerraSAR-X data were applied to characterize the wetland extent of a test site located in the north east of Newfoundland and Labrador, Canada. The accuracy and information content of wetland maps using remote sensing data depend on several factors, such as the type of data, input features, classification algorithms, and ecological characteristics of wetland classes. Most previous wetland studies examined the efficiency of one or two feature types, including intensity and polarimetry. Fewer investigations have examined the potential of interferometric coherence for wetland mapping. Thus, we evaluated the efficiency of using multiple feature types, including intensity, interferometric coherence, and polarimetric scattering for wetland mapping in multiple classification scenarios. An ensemble classifier, namely Random Forest (RF), and a kernel-based Support Vector Machine (SVM) were also used to determine the effect of the classifier. In all classification scenarios, SVM outperformed RF by 1.5-5%. The classification results demonstrated that the intensity features had a higher accuracy relative to coherence and polarimetric features. However, an inclusion of all feature types improved the classification accuracy for both RF and SVM classifiers. We also optimized the type and number of input features using an integration of RF variable importance and Spearman's rank-order correlation. The results of this analysis found that, of 81 input features, 22 were the most important uncorrelated features for classification. An overall classification accuracy of 85.4% was achieved by incorporating these 22 important uncorrelated features based on the proposed classification framework.

KW - Interferometric coherence

KW - Random Forest

KW - Support Vector Machine

KW - Wetland

UR - http://www.scopus.com/inward/record.url?scp=85050486863&partnerID=8YFLogxK

U2 - 10.1016/j.jag.2018.06.005

DO - 10.1016/j.jag.2018.06.005

M3 - Article

AN - SCOPUS:85050486863

VL - 73

SP - 450

EP - 462

JO - International Journal of Applied Earth Observation and Geoinformation

JF - International Journal of Applied Earth Observation and Geoinformation

SN - 1569-8432

ER -