Element 84 Logo
MENU

  Queryable Earth  

  Natural Language Geocoding  

Natural Language Geocoding

Natural Language Geocoding is an open source Python library and geocoding database that converts natural language descriptions of areas on Earth into precise geometry. Rather than limiting users to simple place names, it enables complex spatial descriptions by leveraging LLMs to generate graphs of spatial operations, including place lookups, boundary calculations, coastline analysis, unions, intersections, differences, buffers, and more.

This site is intended to operate in a demo capacity to demonstrate Element 84’s work on natural language geocoding and Queryable Earth.
For dedicated access, please reach out to our team on our contact us page.

Check out the blog post to learn more

Explore how natural language geocoding resolves ambiguous place descriptions into consistent coordinates, turning location phrases into reliable spatial context for features.

Partial screenshot of the world map, the Natural Language Geocoding query selected is "Show me algal blooms within 2 miles of Cape Cod" and the portion of Massachusetts is appropriately outlined in a blue line. There is an image of the algal blooms tiled next to the map.

Machine Learning

Geospatial

jason gilman

Natural Language Geocoding

Even more about our work in Geospatial AI/ML

Machine Learning

Software Engineering

Jason Gilman

Introducing Natural Language Geocoding v0.1.0: An LLM-Enabled Geocoding Database
An outline of the state of Massachusetts with several locations noted on the map depicting a single tree in an empty field.

Machine Learning

Cloud Computing

Software Engineering

Adeel Hassan

Building a queryable Earth with vision-language foundation models

Machine Learning

Software Engineering

Jason Gilman

ADEEL HASSAN

NATHAN ZIMMERMAN

Why We’re Talking About a Centralized Vector Embeddings Catalog Now

Need help bringing your project to life?

Let’s talk