Geo-LLM: Using Llama 4 to create 3D geological models from geological reports

Geo-LLM: Using Llama 4 to create 3D geological models from geological reports. Innovative work using the Llama 4 API on geological reports, converting into domain specific language for input files to visualise in GemPy. All the code is Open-sourced in GitHub.

Congratulations to William Davis and Gain Boonvanich for winning “Best Llama API Usage” at the LlamaCon Hackathon in San Francisco.

“Geologist William Davis used Llama 4 Maverick and GemPy to generate 3D geological models for possible dig locations, terrain maps, and mineral deposits. Geo-ML works by processing 400-page geology reports, consolidating the information into a structured geology domain-specific language, and then uses it to generate 3D representations of subsurface geology.”

“It’s the first time I actually ever used an LLM API to extract the really long text and images from long geological research papers, so I used the really long context window of Llama Maverick and the text and image multimodal capabilities to extract the text and convert it to a domain-specific language, giving a condensed version of everything that is stored in the documents,” Davis said. “I spend most of my time reading through geology documents in my day-to-day work. Having an LLM that can do this work for me in the background will be really excellent.”

https://ai.meta.com/blog/llamacon-hackathon/
https://youtu.be/U1fDn1C3DJA
https://github.com/williamjsdavis/geo-lm