A semi-automatic cropland mapping approach using GEOBIA and random forests on black-and-white aerial photography

M.F.A. Vogels; S.M. de Jong; G. Sterk; E.A. Addink

doi:10.3990/2.462

A semi-automatic cropland mapping approach using GEOBIA and random forests on black-and-white aerial photography

M.F.A. Vogels^*, S.M. de Jong, G. Sterk, E.A. Addink

^*Corresponding author for this work

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

7 Downloads (Pure)

Abstract

For decades land-use and land-cover (LULC) conversions have had an important impact on land- and ecosystem degradation, accordingly (historical) LULC information is important for the assessment of such impacts. This information can be derived from black-and-white (B&W) aerial photography. Such photography is often visually interpreted, which is a very time-consuming approach. This study shows that machine learning can be applied on only brightness to derive LULC information. Cropland acreage is semi-automatically mapped by means of Geographic Object-Based Image Analysis (GEOBIA) and Random Forest classification in two study sites in Ethiopia and in The Netherlands. The result is a thematic map with two classes: 1) agricultural cropland and 2) other types of land cover. Overall mapping accuracies attained are 90 % and 96 % for the two study areas respectively. This mapping method increases the timeline at which historical cropland expansion can be mapped purely from brightness information in B&W photography up to the 1930s.

Original language	English
Title of host publication	Proceedings of GEOBIA 2016 : Solutions and synergies, 14-16 September 2016, Enschede, Netherlands
Editors	N. Kerle, M. Gerke, S. Lefevre
Place of Publication	Enschede
Publisher	University of Twente, Faculty of Geo-Information Science and Earth Observation (ITC)
Number of pages	2
ISBN (Print)	978-90-365-4201-2
DOIs	https://doi.org/10.3990/2.462
Publication status	Published - 2016
Externally published	Yes
Event	6th International Conference on Geographic Object-Based Image Analysis, GEOBIA 2016: Solutions & Synergies - University of Twente Faculty of Geo-Information and Earth Observation (ITC), Enschede, Netherlands Duration: 14 Sept 2016 → 16 Sept 2016 Conference number: 6 https://www.geobia2016.com/

Conference

Conference	6th International Conference on Geographic Object-Based Image Analysis, GEOBIA 2016
Abbreviated title	GEOBIA
Country/Territory	Netherlands
City	Enschede
Period	14/09/16 → 16/09/16
Internet address	https://www.geobia2016.com/

UN SDGs

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

Access to Document

10.3990/2.462

ArticleFinal published version, 24.8 KB

1 Book

GEOBIA 2016 : Solutions and Synergies., 14-16 September 2016, University of Twente Faculty of Geo-Information and Earth Observation (ITC): open access e-book
Kerle, N. (ed.), Gerke, M. (ed.) & Lefèvre, S. (ed.), 2016, Enschede: University of Twente, Faculty of Geo-Information Science and Earth Observation (ITC).
Research output: Book/Report › Book › Academic

Open Access
File

59 Downloads (Pure)

Cite this

Vogels, M. F. A., de Jong, S. M., Sterk, G., & Addink, E. A. (2016). A semi-automatic cropland mapping approach using GEOBIA and random forests on black-and-white aerial photography. In N. Kerle, M. Gerke, & S. Lefevre (Eds.), Proceedings of GEOBIA 2016 : Solutions and synergies, 14-16 September 2016, Enschede, Netherlands University of Twente, Faculty of Geo-Information Science and Earth Observation (ITC). https://doi.org/10.3990/2.462

Vogels, M.F.A. ; de Jong, S.M. ; Sterk, G. et al. / A semi-automatic cropland mapping approach using GEOBIA and random forests on black-and-white aerial photography. Proceedings of GEOBIA 2016 : Solutions and synergies, 14-16 September 2016, Enschede, Netherlands. editor / N. Kerle ; M. Gerke ; S. Lefevre. Enschede : University of Twente, Faculty of Geo-Information Science and Earth Observation (ITC), 2016.

@inproceedings{f886946a7f3b42b796dc4ea60a48e900,

title = "A semi-automatic cropland mapping approach using GEOBIA and random forests on black-and-white aerial photography",

abstract = "For decades land-use and land-cover (LULC) conversions have had an important impact on land- and ecosystem degradation, accordingly (historical) LULC information is important for the assessment of such impacts. This information can be derived from black-and-white (B&W) aerial photography. Such photography is often visually interpreted, which is a very time-consuming approach. This study shows that machine learning can be applied on only brightness to derive LULC information. Cropland acreage is semi-automatically mapped by means of Geographic Object-Based Image Analysis (GEOBIA) and Random Forest classification in two study sites in Ethiopia and in The Netherlands. The result is a thematic map with two classes: 1) agricultural cropland and 2) other types of land cover. Overall mapping accuracies attained are 90 % and 96 % for the two study areas respectively. This mapping method increases the timeline at which historical cropland expansion can be mapped purely from brightness information in B&W photography up to the 1930s. ",

author = "M.F.A. Vogels and {de Jong}, S.M. and G. Sterk and E.A. Addink",

year = "2016",

doi = "10.3990/2.462",

language = "English",

isbn = "978-90-365-4201-2",

editor = "N. Kerle and M. Gerke and S. Lefevre",

booktitle = "Proceedings of GEOBIA 2016 : Solutions and synergies, 14-16 September 2016, Enschede, Netherlands",

publisher = "University of Twente, Faculty of Geo-Information Science and Earth Observation (ITC)",

note = "6th International Conference on Geographic Object-Based Image Analysis, GEOBIA 2016 : Solutions & Synergies, GEOBIA ; Conference date: 14-09-2016 Through 16-09-2016",

url = "https://www.geobia2016.com/",

}

Vogels, MFA, de Jong, SM, Sterk, G & Addink, EA 2016, A semi-automatic cropland mapping approach using GEOBIA and random forests on black-and-white aerial photography. in N Kerle, M Gerke & S Lefevre (eds), Proceedings of GEOBIA 2016 : Solutions and synergies, 14-16 September 2016, Enschede, Netherlands. University of Twente, Faculty of Geo-Information Science and Earth Observation (ITC), Enschede, 6th International Conference on Geographic Object-Based Image Analysis, GEOBIA 2016, Enschede, Netherlands, 14/09/16. https://doi.org/10.3990/2.462

A semi-automatic cropland mapping approach using GEOBIA and random forests on black-and-white aerial photography. / Vogels, M.F.A.; de Jong, S.M.; Sterk, G. et al.
Proceedings of GEOBIA 2016 : Solutions and synergies, 14-16 September 2016, Enschede, Netherlands. ed. / N. Kerle; M. Gerke; S. Lefevre. Enschede: University of Twente, Faculty of Geo-Information Science and Earth Observation (ITC), 2016.

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

TY - GEN

T1 - A semi-automatic cropland mapping approach using GEOBIA and random forests on black-and-white aerial photography

AU - Vogels, M.F.A.

AU - de Jong, S.M.

AU - Sterk, G.

AU - Addink, E.A.

N1 - Conference code: 6

PY - 2016

Y1 - 2016

N2 - For decades land-use and land-cover (LULC) conversions have had an important impact on land- and ecosystem degradation, accordingly (historical) LULC information is important for the assessment of such impacts. This information can be derived from black-and-white (B&W) aerial photography. Such photography is often visually interpreted, which is a very time-consuming approach. This study shows that machine learning can be applied on only brightness to derive LULC information. Cropland acreage is semi-automatically mapped by means of Geographic Object-Based Image Analysis (GEOBIA) and Random Forest classification in two study sites in Ethiopia and in The Netherlands. The result is a thematic map with two classes: 1) agricultural cropland and 2) other types of land cover. Overall mapping accuracies attained are 90 % and 96 % for the two study areas respectively. This mapping method increases the timeline at which historical cropland expansion can be mapped purely from brightness information in B&W photography up to the 1930s.

AB - For decades land-use and land-cover (LULC) conversions have had an important impact on land- and ecosystem degradation, accordingly (historical) LULC information is important for the assessment of such impacts. This information can be derived from black-and-white (B&W) aerial photography. Such photography is often visually interpreted, which is a very time-consuming approach. This study shows that machine learning can be applied on only brightness to derive LULC information. Cropland acreage is semi-automatically mapped by means of Geographic Object-Based Image Analysis (GEOBIA) and Random Forest classification in two study sites in Ethiopia and in The Netherlands. The result is a thematic map with two classes: 1) agricultural cropland and 2) other types of land cover. Overall mapping accuracies attained are 90 % and 96 % for the two study areas respectively. This mapping method increases the timeline at which historical cropland expansion can be mapped purely from brightness information in B&W photography up to the 1930s.

U2 - 10.3990/2.462

DO - 10.3990/2.462

M3 - Conference contribution

SN - 978-90-365-4201-2

BT - Proceedings of GEOBIA 2016 : Solutions and synergies, 14-16 September 2016, Enschede, Netherlands

A2 - Kerle, N.

A2 - Gerke, M.

A2 - Lefevre, S.

PB - University of Twente, Faculty of Geo-Information Science and Earth Observation (ITC)

CY - Enschede

T2 - 6th International Conference on Geographic Object-Based Image Analysis, GEOBIA 2016

Y2 - 14 September 2016 through 16 September 2016

ER -

Vogels MFA, de Jong SM, Sterk G, Addink EA. A semi-automatic cropland mapping approach using GEOBIA and random forests on black-and-white aerial photography. In Kerle N, Gerke M, Lefevre S, editors, Proceedings of GEOBIA 2016 : Solutions and synergies, 14-16 September 2016, Enschede, Netherlands. Enschede: University of Twente, Faculty of Geo-Information Science and Earth Observation (ITC). 2016 doi: 10.3990/2.462

A semi-automatic cropland mapping approach using GEOBIA and random forests on black-and-white aerial photography

Abstract

Conference

UN SDGs

Access to Document

Research output

GEOBIA 2016 : Solutions and Synergies., 14-16 September 2016, University of Twente Faculty of Geo-Information and Earth Observation (ITC): open access e-book

Cite this