Comparative analysis of Worldview-2 and Landsat 8 for coastal saltmarsh mapping accuracy assessment

Sikdar M. M. Rasel; Hsing Chung Chang; Israt Jahan Diti; Tim Ralph; Neil Saintilan

doi:10.1117/12.2222960

Comparative analysis of Worldview-2 and Landsat 8 for coastal saltmarsh mapping accuracy assessment

Sikdar M. M. Rasel, Hsing Chung Chang, Israt Jahan Diti, Tim Ralph, Neil Saintilan

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

3 Citations (Scopus)

Abstract

Coastal saltmarsh and their constituent components and processes are of an interest scientifically due to their ecological function and services. However, heterogeneity and seasonal dynamic of the coastal wetland system makes it challenging to map saltmarshes with remotely sensed data. This study selected four important saltmarsh species Pragmitis australis, Sporobolus virginicus, Ficiona nodosa and Schoeloplectus sp. as well as a Mangrove and Pine tree species, Avecinia and Casuarina sp respectively. High Spatial Resolution Worldview-2 data and Coarse Spatial resolution Landsat 8 imagery were selected in this study. Among the selected vegetation types some patches ware fragmented and close to the spatial resolution of Worldview-2 data while and some patch were larger than the 30 meter resolution of Landsat 8 data. This study aims to test the effectiveness of different classifier for the imagery with various spatial and spectral resolutions. Three different classification algorithm, Maximum Likelihood Classifier (MLC), Support Vector Machine (SVM) and Artificial Neural Network (ANN) were tested and compared with their mapping accuracy of the results derived from both satellite imagery. For Worldview-2 data SVM was giving the higher overall accuracy (92.12%, kappa =0.90) followed by ANN (90.82%, Kappa 0.89) and MLC (90.55%, kappa = 0.88). For Landsat 8 data, MLC (82.04%) showed the highest classification accuracy comparing to SVM (77.31%) and ANN (75.23%). The producer accuracy of the classification results were also presented in the paper.

Original language	English
Title of host publication	Sensing for agriculture and food quality and safety VIII
Editors	Moon S. Kim, Kuanglin Chao, Bryan A. Chin
Place of Publication	Washington, D.C.
Publisher	SPIE
Pages	1-13
Number of pages	13
ISBN (Electronic)	9781510601055
DOIs	https://doi.org/10.1117/12.2222960
Publication status	Published - 2016
Event	Sensing for Agriculture and Food Quality and Safety VIII - Baltimore, United States Duration: 20 Apr 2016 → 21 Apr 2016

Publication series

Name	Proceedings of SPIE
Publisher	SPIE
Volume	9864
ISSN (Print)	0277-786X

Other

Other	Sensing for Agriculture and Food Quality and Safety VIII
Country/Territory	United States
City	Baltimore
Period	20/04/16 → 21/04/16

Keywords

ANN
Assessment
Classification
Landsat 8 OLI
MLC
Saltmarsh
SVM
Worldview-2

Access to Document

10.1117/12.2222960

Cite this

Rasel, S. M. M., Chang, H. C., Diti, I. J., Ralph, T., & Saintilan, N. (2016). Comparative analysis of Worldview-2 and Landsat 8 for coastal saltmarsh mapping accuracy assessment. In M. S. Kim, K. Chao, & B. A. Chin (Eds.), Sensing for agriculture and food quality and safety VIII (pp. 1-13). Article 986409 (Proceedings of SPIE; Vol. 9864). SPIE. https://doi.org/10.1117/12.2222960

@inproceedings{0a0f4047b2bd4f0ebcfa6685bc90247c,

title = "Comparative analysis of Worldview-2 and Landsat 8 for coastal saltmarsh mapping accuracy assessment",

abstract = "Coastal saltmarsh and their constituent components and processes are of an interest scientifically due to their ecological function and services. However, heterogeneity and seasonal dynamic of the coastal wetland system makes it challenging to map saltmarshes with remotely sensed data. This study selected four important saltmarsh species Pragmitis australis, Sporobolus virginicus, Ficiona nodosa and Schoeloplectus sp. as well as a Mangrove and Pine tree species, Avecinia and Casuarina sp respectively. High Spatial Resolution Worldview-2 data and Coarse Spatial resolution Landsat 8 imagery were selected in this study. Among the selected vegetation types some patches ware fragmented and close to the spatial resolution of Worldview-2 data while and some patch were larger than the 30 meter resolution of Landsat 8 data. This study aims to test the effectiveness of different classifier for the imagery with various spatial and spectral resolutions. Three different classification algorithm, Maximum Likelihood Classifier (MLC), Support Vector Machine (SVM) and Artificial Neural Network (ANN) were tested and compared with their mapping accuracy of the results derived from both satellite imagery. For Worldview-2 data SVM was giving the higher overall accuracy (92.12%, kappa =0.90) followed by ANN (90.82%, Kappa 0.89) and MLC (90.55%, kappa = 0.88). For Landsat 8 data, MLC (82.04%) showed the highest classification accuracy comparing to SVM (77.31%) and ANN (75.23%). The producer accuracy of the classification results were also presented in the paper.",

keywords = "ANN, Assessment, Classification, Landsat 8 OLI, MLC, Saltmarsh, SVM, Worldview-2",

author = "Rasel, {Sikdar M. M.} and Chang, {Hsing Chung} and Diti, {Israt Jahan} and Tim Ralph and Neil Saintilan",

year = "2016",

doi = "10.1117/12.2222960",

language = "English",

series = "Proceedings of SPIE",

publisher = "SPIE",

pages = "1--13",

editor = "Kim, {Moon S.} and Kuanglin Chao and Chin, {Bryan A.}",

booktitle = "Sensing for agriculture and food quality and safety VIII",

address = "United States",

note = "Sensing for Agriculture and Food Quality and Safety VIII ; Conference date: 20-04-2016 Through 21-04-2016",

}

Rasel, SMM, Chang, HC, Diti, IJ, Ralph, T & Saintilan, N 2016, Comparative analysis of Worldview-2 and Landsat 8 for coastal saltmarsh mapping accuracy assessment. in MS Kim, K Chao & BA Chin (eds), Sensing for agriculture and food quality and safety VIII., 986409, Proceedings of SPIE, vol. 9864, SPIE, Washington, D.C., pp. 1-13, Sensing for Agriculture and Food Quality and Safety VIII, Baltimore, United States, 20/04/16. https://doi.org/10.1117/12.2222960

Comparative analysis of Worldview-2 and Landsat 8 for coastal saltmarsh mapping accuracy assessment. / Rasel, Sikdar M. M.; Chang, Hsing Chung; Diti, Israt Jahan et al.
Sensing for agriculture and food quality and safety VIII. ed. / Moon S. Kim; Kuanglin Chao; Bryan A. Chin. Washington, D.C.: SPIE, 2016. p. 1-13 986409 (Proceedings of SPIE; Vol. 9864).

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

TY - GEN

T1 - Comparative analysis of Worldview-2 and Landsat 8 for coastal saltmarsh mapping accuracy assessment

AU - Rasel, Sikdar M. M.

AU - Chang, Hsing Chung

AU - Diti, Israt Jahan

AU - Ralph, Tim

AU - Saintilan, Neil

PY - 2016

Y1 - 2016

N2 - Coastal saltmarsh and their constituent components and processes are of an interest scientifically due to their ecological function and services. However, heterogeneity and seasonal dynamic of the coastal wetland system makes it challenging to map saltmarshes with remotely sensed data. This study selected four important saltmarsh species Pragmitis australis, Sporobolus virginicus, Ficiona nodosa and Schoeloplectus sp. as well as a Mangrove and Pine tree species, Avecinia and Casuarina sp respectively. High Spatial Resolution Worldview-2 data and Coarse Spatial resolution Landsat 8 imagery were selected in this study. Among the selected vegetation types some patches ware fragmented and close to the spatial resolution of Worldview-2 data while and some patch were larger than the 30 meter resolution of Landsat 8 data. This study aims to test the effectiveness of different classifier for the imagery with various spatial and spectral resolutions. Three different classification algorithm, Maximum Likelihood Classifier (MLC), Support Vector Machine (SVM) and Artificial Neural Network (ANN) were tested and compared with their mapping accuracy of the results derived from both satellite imagery. For Worldview-2 data SVM was giving the higher overall accuracy (92.12%, kappa =0.90) followed by ANN (90.82%, Kappa 0.89) and MLC (90.55%, kappa = 0.88). For Landsat 8 data, MLC (82.04%) showed the highest classification accuracy comparing to SVM (77.31%) and ANN (75.23%). The producer accuracy of the classification results were also presented in the paper.

AB - Coastal saltmarsh and their constituent components and processes are of an interest scientifically due to their ecological function and services. However, heterogeneity and seasonal dynamic of the coastal wetland system makes it challenging to map saltmarshes with remotely sensed data. This study selected four important saltmarsh species Pragmitis australis, Sporobolus virginicus, Ficiona nodosa and Schoeloplectus sp. as well as a Mangrove and Pine tree species, Avecinia and Casuarina sp respectively. High Spatial Resolution Worldview-2 data and Coarse Spatial resolution Landsat 8 imagery were selected in this study. Among the selected vegetation types some patches ware fragmented and close to the spatial resolution of Worldview-2 data while and some patch were larger than the 30 meter resolution of Landsat 8 data. This study aims to test the effectiveness of different classifier for the imagery with various spatial and spectral resolutions. Three different classification algorithm, Maximum Likelihood Classifier (MLC), Support Vector Machine (SVM) and Artificial Neural Network (ANN) were tested and compared with their mapping accuracy of the results derived from both satellite imagery. For Worldview-2 data SVM was giving the higher overall accuracy (92.12%, kappa =0.90) followed by ANN (90.82%, Kappa 0.89) and MLC (90.55%, kappa = 0.88). For Landsat 8 data, MLC (82.04%) showed the highest classification accuracy comparing to SVM (77.31%) and ANN (75.23%). The producer accuracy of the classification results were also presented in the paper.

KW - ANN

KW - Assessment

KW - Classification

KW - Landsat 8 OLI

KW - MLC

KW - Saltmarsh

KW - SVM

KW - Worldview-2

UR - http://www.scopus.com/inward/record.url?scp=84987936735&partnerID=8YFLogxK

U2 - 10.1117/12.2222960

DO - 10.1117/12.2222960

M3 - Conference proceeding contribution

AN - SCOPUS:84987936735

T3 - Proceedings of SPIE

SP - 1

EP - 13

BT - Sensing for agriculture and food quality and safety VIII

A2 - Kim, Moon S.

A2 - Chao, Kuanglin

A2 - Chin, Bryan A.

PB - SPIE

CY - Washington, D.C.

T2 - Sensing for Agriculture and Food Quality and Safety VIII

Y2 - 20 April 2016 through 21 April 2016

ER -

Comparative analysis of Worldview-2 and Landsat 8 for coastal saltmarsh mapping accuracy assessment

Abstract

Publication series

Other

Keywords

Access to Document

Other files and links

Fingerprint

Cite this