Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

GeoFM : how will geo-foundation models reshape spatial data science and GeoAI?

Janowicz, Krzysztof ; Mai, Gengchen ; Huang, Weiming LU ; Zhu, Rui ; Lao, Ni and Cai, Ling (2025) In International Journal of Geographical Information Science 39(9). p.1849-1865
Abstract

The emerging field of geo-foundation models (GeoFM) has the potential to reshape GeoAI and spatial data science research, education, and practice. In this work, we motivate and define the term and put it into its historic context within GeoAI and spatial data science more broadly. Next, we review core datasets, models, and benchmarks. Based on this overview of the state-of-the-art, we introduce key research challenges for future GeoFM research, such as GeoAI scaling laws, geo-alignment of AI, truly multimodal GeoFM, and so on. Finally, we discuss potential risks of GeoFM research and outline the road ahead with a specific focus on the increasing role of international large-scale collaborations and the future of GeoAI and spatial data... (More)

The emerging field of geo-foundation models (GeoFM) has the potential to reshape GeoAI and spatial data science research, education, and practice. In this work, we motivate and define the term and put it into its historic context within GeoAI and spatial data science more broadly. Next, we review core datasets, models, and benchmarks. Based on this overview of the state-of-the-art, we introduce key research challenges for future GeoFM research, such as GeoAI scaling laws, geo-alignment of AI, truly multimodal GeoFM, and so on. Finally, we discuss potential risks of GeoFM research and outline the road ahead with a specific focus on the increasing role of international large-scale collaborations and the future of GeoAI and spatial data science education.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
AI alignment, foundation models, GeoAI, spatially explicit machine learning
in
International Journal of Geographical Information Science
volume
39
issue
9
pages
17 pages
publisher
Taylor & Francis
external identifiers
  • scopus:105012758438
ISSN
1365-8816
DOI
10.1080/13658816.2025.2543038
language
English
LU publication?
yes
id
4de62635-4524-40d5-8656-6b384e52f44b
date added to LUP
2026-01-27 10:51:59
date last changed
2026-01-27 11:32:53
@article{4de62635-4524-40d5-8656-6b384e52f44b,
  abstract     = {{<p>The emerging field of geo-foundation models (GeoFM) has the potential to reshape GeoAI and spatial data science research, education, and practice. In this work, we motivate and define the term and put it into its historic context within GeoAI and spatial data science more broadly. Next, we review core datasets, models, and benchmarks. Based on this overview of the state-of-the-art, we introduce key research challenges for future GeoFM research, such as GeoAI scaling laws, geo-alignment of AI, truly multimodal GeoFM, and so on. Finally, we discuss potential risks of GeoFM research and outline the road ahead with a specific focus on the increasing role of international large-scale collaborations and the future of GeoAI and spatial data science education.</p>}},
  author       = {{Janowicz, Krzysztof and Mai, Gengchen and Huang, Weiming and Zhu, Rui and Lao, Ni and Cai, Ling}},
  issn         = {{1365-8816}},
  keywords     = {{AI alignment; foundation models; GeoAI; spatially explicit machine learning}},
  language     = {{eng}},
  number       = {{9}},
  pages        = {{1849--1865}},
  publisher    = {{Taylor & Francis}},
  series       = {{International Journal of Geographical Information Science}},
  title        = {{GeoFM : how will geo-foundation models reshape spatial data science and GeoAI?}},
  url          = {{http://dx.doi.org/10.1080/13658816.2025.2543038}},
  doi          = {{10.1080/13658816.2025.2543038}},
  volume       = {{39}},
  year         = {{2025}},
}