Self-supervised representation learning for geographical data - a systematic literature review

Corcoran, Padraig ORCID: https://orcid.org/0000-0001-9731-3385 and Spasic, Irena ORCID: https://orcid.org/0000-0002-8132-3885 2023. Self-supervised representation learning for geographical data - a systematic literature review. ISPRS International Journal of Geo-Information 12 (2) , 64. 10.3390/ijgi12020064

PDF - Published Version Available under License Creative Commons Attribution. Download (351kB)

Abstract

Self-supervised representation learning (SSRL) concerns the problem of learning a useful data representation without the requirement for labelled or annotated data. This representation can, in turn, be used to support solutions to downstream machine learning problems. SSRL has been demonstrated to be a useful tool in the field of geographical information science (GIS). In this article, we systematically review the existing research literature in this space to answer the following five research questions. What types of representations were learnt? What SSRL models were used? What downstream problems were the representations used to solve? What machine learning models were used to solve these problems? Finally, does using a learnt representation improve the overall performance?

Item Type:	Article
Date Type:	Published Online
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	MDPI
ISSN:	2220-9964
Date of First Compliant Deposit:	22 February 2023
Date of Acceptance:	10 February 2023
Last Modified:	03 May 2023 08:11
URI:	https://orca.cardiff.ac.uk/id/eprint/156611

Actions (repository staff only)

Edit Item