Deep residential representations: using unsupervised learning to unlock elevation data for geo-demographic prediction
Deep residential representations: using unsupervised learning to unlock elevation data for geo-demographic prediction
LiDAR (short for “Light Detection And Ranging” or “Laser Imaging, Detection, And Ranging”) technology can be used to provide detailed three-dimensional elevation maps of urban and rural landscapes. The geographically granular and open-source nature of this data lends itself to an array of societal, organisational and business applications where geo-demographic type data is utilised. However, the complexity involved in processing this multi-dimensional data in raw form has thus far restricted its practical adoption. This paper proposes a series of convenient task-agnostic tile elevation embeddings to address this challenge, using recent advances from unsupervised Deep Learning. We test the potential of our embeddings by predicting seven English indices of deprivation (2019) for small geographies in the Greater London area. These indices cover a range of socio-economic outcomes and serve as a proxy for a wide variety of potential downstream tasks to which the embeddings can be applied. We consider the suitability of this data not just on its own but also as an auxiliary source of data in combination with demographic features, thus providing a realistic use case for the embeddings. Having trialled various model/embedding configurations, we find that our best performing embeddings lead to Root-Mean-Squared-Error (RMSE) improvements of up to 21% over using standard demographic features alone. We also demonstrate how our embedding pipeline, using Deep Learning combined with K-means clustering, produces coherent tile segments which allow the latent embedding features to be interpreted.
Deep learning, Geo-demographics, LiDAR, Self-supervised learning
378-392
Stevenson, Matthew, Paul
c11bc02f-acf9-4e13-a703-8ed273bcd4e8
Mues, Christophe
07438e46-bad6-48ba-8f56-f945bc2ff934
Bravo, Cristián
d2e3a1d8-74fa-4300-ad91-26856eca161c
May 2022
Stevenson, Matthew, Paul
c11bc02f-acf9-4e13-a703-8ed273bcd4e8
Mues, Christophe
07438e46-bad6-48ba-8f56-f945bc2ff934
Bravo, Cristián
d2e3a1d8-74fa-4300-ad91-26856eca161c
Stevenson, Matthew, Paul, Mues, Christophe and Bravo, Cristián
(2022)
Deep residential representations: using unsupervised learning to unlock elevation data for geo-demographic prediction.
ISPRS Journal of Photogrammetry and Remote Sensing, 187, .
(doi:10.1016/j.isprsjprs.2022.03.015).
Abstract
LiDAR (short for “Light Detection And Ranging” or “Laser Imaging, Detection, And Ranging”) technology can be used to provide detailed three-dimensional elevation maps of urban and rural landscapes. The geographically granular and open-source nature of this data lends itself to an array of societal, organisational and business applications where geo-demographic type data is utilised. However, the complexity involved in processing this multi-dimensional data in raw form has thus far restricted its practical adoption. This paper proposes a series of convenient task-agnostic tile elevation embeddings to address this challenge, using recent advances from unsupervised Deep Learning. We test the potential of our embeddings by predicting seven English indices of deprivation (2019) for small geographies in the Greater London area. These indices cover a range of socio-economic outcomes and serve as a proxy for a wide variety of potential downstream tasks to which the embeddings can be applied. We consider the suitability of this data not just on its own but also as an auxiliary source of data in combination with demographic features, thus providing a realistic use case for the embeddings. Having trialled various model/embedding configurations, we find that our best performing embeddings lead to Root-Mean-Squared-Error (RMSE) improvements of up to 21% over using standard demographic features alone. We also demonstrate how our embedding pipeline, using Deep Learning combined with K-means clustering, produces coherent tile segments which allow the latent embedding features to be interpreted.
Text
1-s2.0-S0924271622000880-main
- Version of Record
More information
Accepted/In Press date: 24 March 2022
e-pub ahead of print date: 3 April 2022
Published date: May 2022
Additional Information:
Funding Information:
This work was supported by the Economic and Social Research Council [Grant No. ES/P000673/1]. The last author acknowledges the support of the Natural Sciences and Engineering Research Council of Canada (NSERC) [Discovery Grant RGPIN-2020-07114]. This research was undertaken, in part, thanks to funding from the Canada Research Chairs program. The authors acknowledge the use of the IRIDIS High Performance Computing Facility, and associated support services at the University of Southampton, in the completion of this work.
Funding Information:
This work was supported by the Economic and Social Research Council [Grant No. ES/P000673/1]. The last author acknowledges the support of the Natural Sciences and Engineering Research Council of Canada (NSERC) [Discovery Grant RGPIN-2020-07114]. This research was undertaken, in part, thanks to funding from the Canada Research Chairs program.
Publisher Copyright:
© 2022 The Authors
Keywords:
Deep learning, Geo-demographics, LiDAR, Self-supervised learning
Identifiers
Local EPrints ID: 457944
URI: http://eprints.soton.ac.uk/id/eprint/457944
ISSN: 0924-2716
PURE UUID: 7a8c14e9-310a-4a4e-b8b4-7c7382a10369
Catalogue record
Date deposited: 23 Jun 2022 16:58
Last modified: 26 Jul 2024 01:57
Export record
Altmetrics
Contributors
Author:
Matthew, Paul Stevenson
Author:
Cristián Bravo
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