Analyzing the Uncertainties of Ground Validation for Remote Sensing Land Cover Mapping in the Era of Big Geographic Data

Bo Sun; Xi Chen; Qiming Zhou

doi:10.1007/978-981-10-4424-3_3

Analyzing the Uncertainties of Ground Validation for Remote Sensing Land Cover Mapping in the Era of Big Geographic Data

Bo Sun^*, Xi Chen, Qiming Zhou

^*Corresponding author for this work

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

9 Citations (Scopus)

Abstract

Ground validation and accuracy assessment on remote sensing land cover classification is a vital process before the product may be used by the end-user. The common approach towards the validation is based on field investigation and manual or automatic image interpretation using the original or higher-resolution images. The ground reference, which is often regarded as “ground truth”, however, contains errors, especially when a large amount of such ground references is expected with the speculation of coming era of big geographic data. In this study, we aim to analyze the uncertainties in the process of ground validation. By taking accuracy assessment of land cover mapping in Central Asia as an example, a two-tier sampling scheme with a collection of more than 27 thousand samples was adopted. Ground references were sampled by manual image interpretation as well as by field investigation. The reference data were then cross-validated. Misclassification and scale issues are highlighted in the analysis. Result indicates that misclassification of ground reference data by image interpretation is common and the errors in the reference data would make misleading accuracy assessment on remote sensing classification. A new evaluation system of data quality is therefore required.

Original language	English
Title of host publication	Spatial Data Handling in Big Data Era
Subtitle of host publication	Select Papers from the 17th IGU Spatial Data Handling Symposium 2016
Editors	Chenghu Zhou, Fenzhen Su, Francis Harvey, Jun Xu
Publisher	Springer Singapore
Pages	31-38
Number of pages	8
Edition	1
ISBN (Electronic)	978-981-10-4424-3
ISBN (Print)	978-981-10-4423-6, 978-981-13-5133-4
DOIs	https://doi.org/10.1007/978-981-10-4424-3_3
Publication status	Published - 4 May 2017
Event	17th International Symposium on Spatial Data Handling, SDH 2016 - Beijing, China Duration: 18 Aug 2016 → 20 Aug 2016

Publication series

Name	Advances in Geographic Information Science
ISSN (Print)	1867-2434
ISSN (Electronic)	1867-2442

Conference

Conference	17th International Symposium on Spatial Data Handling, SDH 2016
Country/Territory	China
City	Beijing
Period	18/08/16 → 20/08/16

User-Defined Keywords

Accuracy assessment
Central Asia
Error propagation
Ground reference data
Remote sensing

Access to Document

10.1007/978-981-10-4424-3_3

Cite this

Sun, B., Chen, X., & Zhou, Q. (2017). Analyzing the Uncertainties of Ground Validation for Remote Sensing Land Cover Mapping in the Era of Big Geographic Data. In C. Zhou, F. Su, F. Harvey, & J. Xu (Eds.), Spatial Data Handling in Big Data Era: Select Papers from the 17th IGU Spatial Data Handling Symposium 2016 (1 ed., pp. 31-38). (Advances in Geographic Information Science). Springer Singapore. https://doi.org/10.1007/978-981-10-4424-3_3

Sun, Bo ; Chen, Xi ; Zhou, Qiming. / Analyzing the Uncertainties of Ground Validation for Remote Sensing Land Cover Mapping in the Era of Big Geographic Data. Spatial Data Handling in Big Data Era: Select Papers from the 17th IGU Spatial Data Handling Symposium 2016. editor / Chenghu Zhou ; Fenzhen Su ; Francis Harvey ; Jun Xu. 1. ed. Springer Singapore, 2017. pp. 31-38 (Advances in Geographic Information Science).

@inproceedings{842bb428b94245a2a50447cee300baa0,

title = "Analyzing the Uncertainties of Ground Validation for Remote Sensing Land Cover Mapping in the Era of Big Geographic Data",

abstract = "Ground validation and accuracy assessment on remote sensing land cover classification is a vital process before the product may be used by the end-user. The common approach towards the validation is based on field investigation and manual or automatic image interpretation using the original or higher-resolution images. The ground reference, which is often regarded as “ground truth”, however, contains errors, especially when a large amount of such ground references is expected with the speculation of coming era of big geographic data. In this study, we aim to analyze the uncertainties in the process of ground validation. By taking accuracy assessment of land cover mapping in Central Asia as an example, a two-tier sampling scheme with a collection of more than 27 thousand samples was adopted. Ground references were sampled by manual image interpretation as well as by field investigation. The reference data were then cross-validated. Misclassification and scale issues are highlighted in the analysis. Result indicates that misclassification of ground reference data by image interpretation is common and the errors in the reference data would make misleading accuracy assessment on remote sensing classification. A new evaluation system of data quality is therefore required.",

keywords = "Accuracy assessment, Central Asia, Error propagation, Ground reference data, Remote sensing",

author = "Bo Sun and Xi Chen and Qiming Zhou",

note = "Funding Information: The authors would like to thank the persons who assist in the interpretation of ground reference data based on high-resolution images. They are Ms. Liu Ping, Ms. Chen Huijuan, Ms. Yi Lin, and Mr. Li Jilin. The research is supported by the International Science & Technology Cooperation Program of China (2010DFA92720-24), Natural Science Foundation of China (NSFC) General Research Grant (41471340) and Shenzhen Basic Research Project (JCYJ20150630114942260). Land cover classification products are provided by Xinjiang Institute of Ecology and Geography (XIEG), Chinese Academy of Sciences (CAS). Publisher copyright: {\textcopyright} 2017 Springer Nature Singapore Pte Ltd.; 17th International Symposium on Spatial Data Handling, SDH 2016 ; Conference date: 18-08-2016 Through 20-08-2016",

year = "2017",

month = may,

day = "4",

doi = "10.1007/978-981-10-4424-3_3",

language = "English",

isbn = "978-981-10-4423-6",

series = "Advances in Geographic Information Science",

publisher = "Springer Singapore",

pages = "31--38",

editor = "Chenghu Zhou and Fenzhen Su and Francis Harvey and Jun Xu",

booktitle = "Spatial Data Handling in Big Data Era",

address = "Singapore",

edition = "1",

}

Sun, B, Chen, X & Zhou, Q 2017, Analyzing the Uncertainties of Ground Validation for Remote Sensing Land Cover Mapping in the Era of Big Geographic Data. in C Zhou, F Su, F Harvey & J Xu (eds), Spatial Data Handling in Big Data Era: Select Papers from the 17th IGU Spatial Data Handling Symposium 2016. 1 edn, Advances in Geographic Information Science, Springer Singapore, pp. 31-38, 17th International Symposium on Spatial Data Handling, SDH 2016, Beijing, China, 18/08/16. https://doi.org/10.1007/978-981-10-4424-3_3

Analyzing the Uncertainties of Ground Validation for Remote Sensing Land Cover Mapping in the Era of Big Geographic Data. / Sun, Bo; Chen, Xi; Zhou, Qiming.
Spatial Data Handling in Big Data Era: Select Papers from the 17th IGU Spatial Data Handling Symposium 2016. ed. / Chenghu Zhou; Fenzhen Su; Francis Harvey; Jun Xu. 1. ed. Springer Singapore, 2017. p. 31-38 (Advances in Geographic Information Science).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Analyzing the Uncertainties of Ground Validation for Remote Sensing Land Cover Mapping in the Era of Big Geographic Data

AU - Sun, Bo

AU - Chen, Xi

AU - Zhou, Qiming

N1 - Funding Information: The authors would like to thank the persons who assist in the interpretation of ground reference data based on high-resolution images. They are Ms. Liu Ping, Ms. Chen Huijuan, Ms. Yi Lin, and Mr. Li Jilin. The research is supported by the International Science & Technology Cooperation Program of China (2010DFA92720-24), Natural Science Foundation of China (NSFC) General Research Grant (41471340) and Shenzhen Basic Research Project (JCYJ20150630114942260). Land cover classification products are provided by Xinjiang Institute of Ecology and Geography (XIEG), Chinese Academy of Sciences (CAS). Publisher copyright: © 2017 Springer Nature Singapore Pte Ltd.

PY - 2017/5/4

Y1 - 2017/5/4

N2 - Ground validation and accuracy assessment on remote sensing land cover classification is a vital process before the product may be used by the end-user. The common approach towards the validation is based on field investigation and manual or automatic image interpretation using the original or higher-resolution images. The ground reference, which is often regarded as “ground truth”, however, contains errors, especially when a large amount of such ground references is expected with the speculation of coming era of big geographic data. In this study, we aim to analyze the uncertainties in the process of ground validation. By taking accuracy assessment of land cover mapping in Central Asia as an example, a two-tier sampling scheme with a collection of more than 27 thousand samples was adopted. Ground references were sampled by manual image interpretation as well as by field investigation. The reference data were then cross-validated. Misclassification and scale issues are highlighted in the analysis. Result indicates that misclassification of ground reference data by image interpretation is common and the errors in the reference data would make misleading accuracy assessment on remote sensing classification. A new evaluation system of data quality is therefore required.

AB - Ground validation and accuracy assessment on remote sensing land cover classification is a vital process before the product may be used by the end-user. The common approach towards the validation is based on field investigation and manual or automatic image interpretation using the original or higher-resolution images. The ground reference, which is often regarded as “ground truth”, however, contains errors, especially when a large amount of such ground references is expected with the speculation of coming era of big geographic data. In this study, we aim to analyze the uncertainties in the process of ground validation. By taking accuracy assessment of land cover mapping in Central Asia as an example, a two-tier sampling scheme with a collection of more than 27 thousand samples was adopted. Ground references were sampled by manual image interpretation as well as by field investigation. The reference data were then cross-validated. Misclassification and scale issues are highlighted in the analysis. Result indicates that misclassification of ground reference data by image interpretation is common and the errors in the reference data would make misleading accuracy assessment on remote sensing classification. A new evaluation system of data quality is therefore required.

KW - Accuracy assessment

KW - Central Asia

KW - Error propagation

KW - Ground reference data

KW - Remote sensing

UR - http://www.scopus.com/inward/record.url?scp=85028426442&partnerID=8YFLogxK

U2 - 10.1007/978-981-10-4424-3_3

DO - 10.1007/978-981-10-4424-3_3

M3 - Conference proceeding

AN - SCOPUS:85028426442

SN - 978-981-10-4423-6

SN - 978-981-13-5133-4

T3 - Advances in Geographic Information Science

SP - 31

EP - 38

BT - Spatial Data Handling in Big Data Era

A2 - Zhou, Chenghu

A2 - Su, Fenzhen

A2 - Harvey, Francis

A2 - Xu, Jun

PB - Springer Singapore

T2 - 17th International Symposium on Spatial Data Handling, SDH 2016

Y2 - 18 August 2016 through 20 August 2016

ER -

Sun B, Chen X, Zhou Q. Analyzing the Uncertainties of Ground Validation for Remote Sensing Land Cover Mapping in the Era of Big Geographic Data. In Zhou C, Su F, Harvey F, Xu J, editors, Spatial Data Handling in Big Data Era: Select Papers from the 17th IGU Spatial Data Handling Symposium 2016. 1 ed. Springer Singapore. 2017. p. 31-38. (Advances in Geographic Information Science). doi: 10.1007/978-981-10-4424-3_3

Analyzing the Uncertainties of Ground Validation for Remote Sensing Land Cover Mapping in the Era of Big Geographic Data

Abstract

Publication series

Conference

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this