Building a brain for earth.

At Columbus, we collect the world’s data, and build a brain that comprehends it all.
We’re building frontier geospatial intelligence.

An interactive Thesis

Large Geospatial Model vs Large Language Model.

If an LLM is for the digital world, our LGM is for the physical world.
We’re personifying earth with physical AI. Instead of words, we process data about our surroundings and the anthropology in them.

A new foundational model is needed.

Read our in-depth article
Columbus Earth

An LGM vs other foundation models

LLM

Large-Language-model

VLM

Vision-Language-model

LGM

Large-Geospatial-model

Trained on

Text

e.g. “The grass is” → “green”

Text & Image

e.g. dog photo → “a border collie”

Physical reality

e.g. public data + urban imagery + GIS → crime risk map

What it
outputs

Predictive words

“What word comes next?”

Visual reasoning

“What’s in this image?”

Ground truths

“What’s in this physical space?”

Who’s
building it
ChatGPT
Claude
Grok
Perplexity
Physical Intelligence
Runway
Meta
Columbus Earth

A Large Geospatial Model is the next frontier in AI

The path forward

LLM
2022
Geo-tuned LLM
& Vision Models
2025
Generalist
LGM
UGM

Timeline of foundational AI models

  • 2022LLM (Large Language Model)
  • 2025Geo-tuned LLM & Vision Models
  • 2027Generalist LGM (Large Geospatial Model)
  • 2028UGM (Universal Geospatial Model)
  1. 2022LLM
  2. 2025Geo-tuned LLM & Vision Models
  3. Now — July 2026
  4. 2027Generalist LGMRead our Paper
  5. 2028UGMOur Game Plan
Read our article on

the drawbacks of LLMs & vision models.

How the LGM innovates.

Our Reasoning

We've come up with several innovations within data collection, fusion, and core reasoning. We combine several innovations in unique ways in our research.

We learned first-hand how LLMs are not built for geospatial needs. We set out to fix every technical issue that came with GPT architecture and it converged into a new foundational model, the LGM.

Why LLMs didn't work

Our proprietary architecture is comprised of 3 parts. Within each are several innovations built during our practical research.

Data Collection

The most extensive data collection in the industry. Versatile methods ranging from drones, car data, human data, public data and more.

Read our blog
Read our articles on

our foundational model research

Our Model: Magellan-1.0

The latest results from our development of the LGM.

Contextually enriched reasoning over the semantics of urban space

Generative Geospatial data

A generalist model, grounded on a living data catalogue

Granular reasoning at scale

Careers

If you're excited about creating paradigm shifts in physical world understanding.

Join the crew

Research freely at Columbus.

By submitting, you agree with our Terms and Privacy Policy.

We answer fast.