Co-authoring paper on Big Data and AI at the International Geological Congress (IGC) in Korea

Co-authoring a paper in the Big Data and Artificial Intelligence (AI) track at the International Geological Congress (IGC) in Busan, Korea next week. T33-S4 “Data-driven or AI-driven discovery in geosciences” on a new free tool emerging for geoscientists.

Phoebe McMellon from the non-profit GeoScienceWorld will be presenting “Leveraging Machine Learning, Natural Language Processing and Knowledge Representations to Facilitate the Discovery of Insights and Analogues in Unstructured Geoscience Literature.”

Authors: McMellon, P., Reece, A., Cleverley, P.H. and Merten, S

I first applied methods using text embeddings from geoscience ‘language models’ to generate Lithostratigraphic analogues in 2015. To my knowledge, this was the first such published AI technique in the geosciences. By using complex patterns of word co-occurrence in literature, we can use AI to ‘cast a wider net’ and suggest ‘similar’ geological formations and other geological concepts to make connections and discoveries previously not known.

This 2024 paper evolves the approach further, hosting a prototype and testing it with geoscientists in different sectors. The intention is for it to be a free tool for any geoscientist to use world-wide.