Wetland Mapping with Multitemporal Sentinel Radar Remote Sensing in the Southeast Region of Brazil

J. B.G. Salinas; M. K.P. Eggerth; M. E. Miller; R. R.B. Meza; J. T.A. Chacaltana; J. R. Acuna; G. F. Barroso

doi:10.1109/LAGIRS48042.2020.9165593

Wetland Mapping with Multitemporal Sentinel Radar Remote Sensing in the Southeast Region of Brazil

J. B.G. Salinas, M. K.P. Eggerth, M. E. Miller, R. R.B. Meza, J. T.A. Chacaltana, J. R. Acuna, G. F. Barroso

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

A classification method with multi-temporal images of synthetic aperture radar (SAR) combined with Geographic information system, geoinformation data, and field validation, was applied for wetland mapping accuracy and typology. Wetland mapping is vital for management and conservation, particularly under environmental pressures such as wetland drainage and land reclamation. The aim of this study is to develop an accurate mapping of wetlands and open water systems of the Lower Doce River Valley - LDRV (Southeastern Brazil) with Synthetic Aperture Radar (SAR) imagery, using multitemporal classification techniques and ground truth validation. Sentinel-1B SAR imagery from 2016 and 2019 was processed with Google Earth Engine (GEE). Monthly median imagery condition for the rainy season was obtained and K-means unsupervised classification was applied. The study yields 4,157 wetlands, 262.27 km2 with predominant small patches. Fieldwork revealed three main wetlands categories: coastal wetlands, inland wetlands and artificial wetlands. The results have shown an overall accuracy of 81.9% and a Kappa coefficient of 0.71. Wetlands, non-wetlands, and open waters classes present accuracy of 50, 80 and 95%, respectively.

Original language	English
Title of host publication	2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	669-674
Number of pages	6
ISBN (Electronic)	9781728143507
DOIs	https://doi.org/10.1109/LAGIRS48042.2020.9165593
State	Published - Mar 2020
Externally published	Yes
Event	2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020 - Santiago, Chile Duration: 21 Mar 2020 → 26 Mar 2020

Publication series

Name	2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020 - Proceedings

Conference

Conference	2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020
Country/Territory	Chile
City	Santiago
Period	21/03/20 → 26/03/20

Bibliographical note

Funding Information:
The authors would like to thanks CAPES (Federal Agency for Graduate Capacity Building) for scholarships and PROAP-UFES for the financial support financial support for fieldwork. We also want to thanks Dr. Fábio Pavan Piccolli (LABESUL) for his support in the field.

Keywords

Classification
Multitemporal
SAR
Sentinel-1
Wetlands

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/LAGIRS48042.2020.9165593

Cite this

Salinas, J. B. G., Eggerth, M. K. P., Miller, M. E., Meza, R. R. B., Chacaltana, J. T. A., Acuna, J. R., & Barroso, G. F. (2020). Wetland Mapping with Multitemporal Sentinel Radar Remote Sensing in the Southeast Region of Brazil. In 2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020 - Proceedings (pp. 669-674). [9165593] (2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/LAGIRS48042.2020.9165593

Salinas, J. B.G. ; Eggerth, M. K.P. ; Miller, M. E. et al. / Wetland Mapping with Multitemporal Sentinel Radar Remote Sensing in the Southeast Region of Brazil. 2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 669-674 (2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020 - Proceedings).

@inproceedings{51da51cd374249209b76171bb02561cb,

title = "Wetland Mapping with Multitemporal Sentinel Radar Remote Sensing in the Southeast Region of Brazil",

abstract = "A classification method with multi-temporal images of synthetic aperture radar (SAR) combined with Geographic information system, geoinformation data, and field validation, was applied for wetland mapping accuracy and typology. Wetland mapping is vital for management and conservation, particularly under environmental pressures such as wetland drainage and land reclamation. The aim of this study is to develop an accurate mapping of wetlands and open water systems of the Lower Doce River Valley - LDRV (Southeastern Brazil) with Synthetic Aperture Radar (SAR) imagery, using multitemporal classification techniques and ground truth validation. Sentinel-1B SAR imagery from 2016 and 2019 was processed with Google Earth Engine (GEE). Monthly median imagery condition for the rainy season was obtained and K-means unsupervised classification was applied. The study yields 4,157 wetlands, 262.27 km2 with predominant small patches. Fieldwork revealed three main wetlands categories: coastal wetlands, inland wetlands and artificial wetlands. The results have shown an overall accuracy of 81.9% and a Kappa coefficient of 0.71. Wetlands, non-wetlands, and open waters classes present accuracy of 50, 80 and 95%, respectively. ",

keywords = "Classification, Multitemporal, SAR, Sentinel-1, Wetlands",

author = "Salinas, {J. B.G.} and Eggerth, {M. K.P.} and Miller, {M. E.} and Meza, {R. R.B.} and Chacaltana, {J. T.A.} and Acuna, {J. R.} and Barroso, {G. F.}",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; 2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020 ; Conference date: 21-03-2020 Through 26-03-2020",

year = "2020",

month = mar,

doi = "10.1109/LAGIRS48042.2020.9165593",

language = "Ingl{\'e}s",

series = "2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "669--674",

booktitle = "2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020 - Proceedings",

address = "Estados Unidos",

}

Salinas, JBG, Eggerth, MKP, Miller, ME, Meza, RRB, Chacaltana, JTA, Acuna, JR & Barroso, GF 2020, Wetland Mapping with Multitemporal Sentinel Radar Remote Sensing in the Southeast Region of Brazil. in 2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020 - Proceedings., 9165593, 2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 669-674, 2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020, Santiago, Chile, 21/03/20. https://doi.org/10.1109/LAGIRS48042.2020.9165593

Wetland Mapping with Multitemporal Sentinel Radar Remote Sensing in the Southeast Region of Brazil. / Salinas, J. B.G.; Eggerth, M. K.P.; Miller, M. E. et al.
2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. p. 669-674 9165593 (2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Wetland Mapping with Multitemporal Sentinel Radar Remote Sensing in the Southeast Region of Brazil

AU - Salinas, J. B.G.

AU - Eggerth, M. K.P.

AU - Miller, M. E.

AU - Meza, R. R.B.

AU - Chacaltana, J. T.A.

AU - Acuna, J. R.

AU - Barroso, G. F.

PY - 2020/3

Y1 - 2020/3

N2 - A classification method with multi-temporal images of synthetic aperture radar (SAR) combined with Geographic information system, geoinformation data, and field validation, was applied for wetland mapping accuracy and typology. Wetland mapping is vital for management and conservation, particularly under environmental pressures such as wetland drainage and land reclamation. The aim of this study is to develop an accurate mapping of wetlands and open water systems of the Lower Doce River Valley - LDRV (Southeastern Brazil) with Synthetic Aperture Radar (SAR) imagery, using multitemporal classification techniques and ground truth validation. Sentinel-1B SAR imagery from 2016 and 2019 was processed with Google Earth Engine (GEE). Monthly median imagery condition for the rainy season was obtained and K-means unsupervised classification was applied. The study yields 4,157 wetlands, 262.27 km2 with predominant small patches. Fieldwork revealed three main wetlands categories: coastal wetlands, inland wetlands and artificial wetlands. The results have shown an overall accuracy of 81.9% and a Kappa coefficient of 0.71. Wetlands, non-wetlands, and open waters classes present accuracy of 50, 80 and 95%, respectively.

AB - A classification method with multi-temporal images of synthetic aperture radar (SAR) combined with Geographic information system, geoinformation data, and field validation, was applied for wetland mapping accuracy and typology. Wetland mapping is vital for management and conservation, particularly under environmental pressures such as wetland drainage and land reclamation. The aim of this study is to develop an accurate mapping of wetlands and open water systems of the Lower Doce River Valley - LDRV (Southeastern Brazil) with Synthetic Aperture Radar (SAR) imagery, using multitemporal classification techniques and ground truth validation. Sentinel-1B SAR imagery from 2016 and 2019 was processed with Google Earth Engine (GEE). Monthly median imagery condition for the rainy season was obtained and K-means unsupervised classification was applied. The study yields 4,157 wetlands, 262.27 km2 with predominant small patches. Fieldwork revealed three main wetlands categories: coastal wetlands, inland wetlands and artificial wetlands. The results have shown an overall accuracy of 81.9% and a Kappa coefficient of 0.71. Wetlands, non-wetlands, and open waters classes present accuracy of 50, 80 and 95%, respectively.

KW - Classification

KW - Multitemporal

KW - SAR

KW - Sentinel-1

KW - Wetlands

UR - http://www.scopus.com/inward/record.url?scp=85091628553&partnerID=8YFLogxK

U2 - 10.1109/LAGIRS48042.2020.9165593

DO - 10.1109/LAGIRS48042.2020.9165593

M3 - Contribución a la conferencia

AN - SCOPUS:85091628553

T3 - 2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020 - Proceedings

SP - 669

EP - 674

BT - 2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020

Y2 - 21 March 2020 through 26 March 2020

ER -

Salinas JBG, Eggerth MKP, Miller ME, Meza RRB, Chacaltana JTA, Acuna JR et al. Wetland Mapping with Multitemporal Sentinel Radar Remote Sensing in the Southeast Region of Brazil. In 2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. p. 669-674. 9165593. (2020 IEEE Latin American GRSS and ISPRS Remote Sensing Conference, LAGIRS 2020 - Proceedings). doi: 10.1109/LAGIRS48042.2020.9165593

Wetland Mapping with Multitemporal Sentinel Radar Remote Sensing in the Southeast Region of Brazil

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this