Geospatial Representation Learning

Geospatial Representation Learning is a machine learning paradigm that, as a subcategory of representation learning, focuses on automatically discovering task-invariant, structured embeddings of geospatial entities by leveraging their geometric, topological, and semantic properties inherent in geographic data.

126

Publications

6.3K

Citations

441

Authors

172

Institutions

Publications per year

2017–2026

104

Authors

441

  1. GM
    Gengchen Mai

    University of California, Santa Barbara, United States

    8 publications · 634 citations

    8

    h-index

  2. YH
    Yingjie Hu

    University at Buffalo, State University of New York, United States

    7 publications · 924 citations

    7

    h-index

  3. SG
    Song Gao

    University of Wisconsin–Madison, United States

    6 publications · 859 citations

    6

    h-index

  4. WH
    Weiming Huang

    Nanyang Technological University, Singapore

    5 publications · 280 citations

    5

    h-index

  5. KJ
    Krzysztof Janowicz

    University of California, Santa Barbara, United States

    5 publications · 788 citations

    5

    h-index

1–5 of 441

Venues

  1. arXiv (Cornell University)

    Repository · 11 publications · 335 citations

    11

    h-index

  2. 8

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 5 publications · 297 citations

    5

    h-index

  4. Remote Sensing

    5 publications · 147 citations

    5

    h-index

  5. Transactions in GIS

    5 publications · 145 citations

    5

    h-index

1–5