Toward Foundation Models for Mobility Enriched Geospatially Embedded Objects
Maria Despoina Siampou, Shang-Ling Hsu, Shushman Choudhury, Neha Arora, Cyrus Shahabi · 2025
Read Toward Foundation Models for Mobility Enriched Geospatially Embedded Objects by Maria Despoina Siampou, Shang-Ling Hsu, Shushman Choudhury, Neha Arora, Cyrus Shahabi (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13070354.txt.
Description
Maria Despoina Siampou, Shang-Ling Hsu, Shushman Choudhury, Neha Arora, and Cyrus Shahabi argue for foundation models built for maps and movement, in a 2025 paper. Giant pre-trained models have reshaped language, image, and sound work. GeoAI, the AI of place, lacks an equivalent that handles both map objects and how people move among them.
The missing piece, they argue, is a shared code for geospatial objects: points, lines, and areas enriched with meaning and motion data. Current work treats such objects like words in a sentence, borrowing language tricks. A true foundation model for places could transfer across city planning, transport, and disaster tasks. The paper maps what such a model needs and where the gaps lie.
Catalog record
| CREATOR | Maria Despoina Siampou, Shang-Ling Hsu, Shushman Choudhury, Neha Arora, Cyrus Shahabi |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 25 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |