Enjoyed presenting at BEOS in London today. Excellent presentations from Joseph Nicholson and Joe Court on digitalisation. Big thanks to Marcella Cilia for facilitating and everyone at BEOS for the excellent event. Busy room and really interesting questions on data and Artificial Intelligence.

More incredible open-access geological datasets. Macrostrat is the world's largest homogenised geological map database, over 2.5 Million geological polygons and over 50,000 stratigraphical names all open and accessible via an API to download. There is also a range of interactive tools, including a Digital Elevation Profile and mobile fieldbook for a smartphone.Global Big Data and... Continue Reading →

Honoured to be invited to take part in this international debate on AI at the European Geosciences Union (EGU) General Assembly in Vienna during May.Large Language Models (LLMs) and other advanced AI tools are reshaping how researchers and practitioners approach data analysis, synthesis, and communication across Geosciences. This Great Debate at the EGU General Assembly... Continue Reading →

Opensource tool released: Run a Large Language Model driven AI solution locally on your machine for insights into mineral production, reserves, trends, prices, substitutes, and recycling resources.Mohanty et al (2025) have released, Opensource, the code and data from their research in Github. Link in the comments. It is designed to run with Llama-3-8B a lightweight... Continue Reading →

In terms of outreach and education there are some great open-source visualisations, data and tools for earth sciences. Earthviewer allows people to explore Earth's history in deep time, from 4.5 billion years ago to present day. This includes the location of major cities and where they were at various points of geological time to help... Continue Reading →

There are incredible open-access datasets out there. For example the GLiM Global Lithological Map containing over 1.2 million polygons of rock types.From Hartmann and Moosdorf (2012) made interactive through a web viewer in 2017. Link in the comments.AbstractLithology describes the geochemical, mineralogical, and physical properties of rocks. It plays a key role in many processes... Continue Reading →

In areas of sparse data, patterns in text may be a helpful geoscience screening tool. One technique may be to build a text embedding model which allows you to compare the vectors of target geological concepts to location names.Disambiguation here is vitally important. The prototype example shown is for the vector of 'Monzonite' to vectors... Continue Reading →

I've combined text embeddings generated from word co-occurrences within thousands of geological reports for both lithology and minerals in a 3D t-SME plot. Following on from some recent posts I made, it may be interesting to explore similarity (cosine vector similarity) between lithologies-lithologies, minerals-minerals and lithologies-minerals.This is a technique anyone can conduct on large volumes... Continue Reading →