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 …

4.1. What types of representations were learnt? 13 In this section, for each individual data
type, we state the number of articles that 14 considered the problem of learning
representations of that type. For each type, we also list 15 the corresponding articles and
describe the specific data they used. 16