Comparisons of two global built area land cover datasets in methods to disaggregate human population in eleven countries from the global South
Comparisons of two global built area land cover datasets in methods to disaggregate human population in eleven countries from the global South
Mapping built land cover at unprecedented detail has been facilitated by increasing availability of global high-resolution imagery and image processing methods. These advances in urban feature extraction and built-area detection can refine the mapping of human population densities, especially in lower income countries where rapid urbanization and changing population is accompanied by frequently out-of-date or inaccurate census data. However, in these contexts it is unclear how best to use built-area data to disaggregate areal, count-based census data. Here we tested two methods using remotely sensed, built-area land cover data to disaggregate population data. These included simple, areal weighting and more complex statistical models with other ancillary information. Outcomes were assessed across eleven countries, representing different world regions varying in population densities, types of built infrastructure, and environmental characteristics. We found that for seven of 11 countries a Random Forest-based, machine learning approach outperforms simple, binary dasymetric disaggregation into remotely-sensed built areas. For these more complex models there was little evidence to support using any single built land cover input over the rest, and in most cases using more than one built-area data product resulted in higher predictive capacity. We discuss these results and implications for future population modeling approaches.
Land cover, built areas, population modeling, remote sensing, settlement mapping
78-100
Forrest, Stephen R.
61e0a6cc-43b1-4a67-bbb9-3af3225531d5
Gaughan, Andrea E.
395221c6-1091-4657-af7e-bd6cb93dbaf9
Nieves, Jeremiah J.
2b5f2f25-afc0-4585-8531-dc2acc4b3511
King, Adam
f8f21b15-59fc-4585-8e30-52639e82fb83
Sorichetta, Alessandro
c80d941b-a3f5-4a6d-9a19-e3eeba84443c
Linard, Catherine
231a1de7-72c2-4dc1-bc4e-ea30ed444856
Tatem, Andrew
6c6de104-a5f9-46e0-bb93-a1a7c980513e
2 January 2020
Forrest, Stephen R.
61e0a6cc-43b1-4a67-bbb9-3af3225531d5
Gaughan, Andrea E.
395221c6-1091-4657-af7e-bd6cb93dbaf9
Nieves, Jeremiah J.
2b5f2f25-afc0-4585-8531-dc2acc4b3511
King, Adam
f8f21b15-59fc-4585-8e30-52639e82fb83
Sorichetta, Alessandro
c80d941b-a3f5-4a6d-9a19-e3eeba84443c
Linard, Catherine
231a1de7-72c2-4dc1-bc4e-ea30ed444856
Tatem, Andrew
6c6de104-a5f9-46e0-bb93-a1a7c980513e
Forrest, Stephen R., Gaughan, Andrea E., Nieves, Jeremiah J., King, Adam, Sorichetta, Alessandro, Linard, Catherine and Tatem, Andrew
(2020)
Comparisons of two global built area land cover datasets in methods to disaggregate human population in eleven countries from the global South.
International Journal of Digital Earth, 13 (1), .
(doi:10.1080/17538947.2019.1633424).
Abstract
Mapping built land cover at unprecedented detail has been facilitated by increasing availability of global high-resolution imagery and image processing methods. These advances in urban feature extraction and built-area detection can refine the mapping of human population densities, especially in lower income countries where rapid urbanization and changing population is accompanied by frequently out-of-date or inaccurate census data. However, in these contexts it is unclear how best to use built-area data to disaggregate areal, count-based census data. Here we tested two methods using remotely sensed, built-area land cover data to disaggregate population data. These included simple, areal weighting and more complex statistical models with other ancillary information. Outcomes were assessed across eleven countries, representing different world regions varying in population densities, types of built infrastructure, and environmental characteristics. We found that for seven of 11 countries a Random Forest-based, machine learning approach outperforms simple, binary dasymetric disaggregation into remotely-sensed built areas. For these more complex models there was little evidence to support using any single built land cover input over the rest, and in most cases using more than one built-area data product resulted in higher predictive capacity. We discuss these results and implications for future population modeling approaches.
This record has no associated files available for download.
More information
Accepted/In Press date: 13 June 2019
e-pub ahead of print date: 23 September 2019
Published date: 2 January 2020
Additional Information:
Funding Information:
FRS, AEG, JNN, AK, and AS are funded by the Bill & Melinda Gates Foundation (OPP1134076). AJT is supported by funding from U.S. National Institutes of Health/National Institute of Allergy and Infectious Diseases (U19AI089674), the Bill & Melinda Gates Foundation (OPP1106427, OPP1032350, OPP1134076), the Clinton Health Access Initiative, National Institutes of Health, and a Wellcome Trust Sustaining Health Grant (106866/Z/15/Z). We would like to acknowledge previous reviews and editorial comments which have improved the manuscript prior to its submission to IJDE.
Publisher Copyright:
© 2019, © 2019 Informa UK Limited, trading as Taylor & Francis Group.
Keywords:
Land cover, built areas, population modeling, remote sensing, settlement mapping
Identifiers
Local EPrints ID: 436838
URI: http://eprints.soton.ac.uk/id/eprint/436838
ISSN: 1753-8947
PURE UUID: 1e3fe93c-3ec7-4a94-8dd9-9a28ff5be6dd
Catalogue record
Date deposited: 10 Jan 2020 17:34
Last modified: 06 Jun 2024 01:50
Export record
Altmetrics
Contributors
Author:
Stephen R. Forrest
Author:
Andrea E. Gaughan
Author:
Jeremiah J. Nieves
Author:
Adam King
Author:
Catherine Linard
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
