The European Geosciences Union (EGU) has recently released guidelines for the use of AI-based tools in the publication process. This is to help ensure the ethical use of AI tools in the rapidly evolving landscape of scholarly communication. https://www.egu.eu/news/1031/statement-on-the-use-of-ai-based-tools-for-the-presentation-and-publication-of-research-results-in-earth-planetary-and-space-science/ The American Geophysical Union (AGU) published their guidelines for ethical use of AI last year: https://news.agu.org/press-release/agu-publishes-guidelines-for-the-ethical-use-of-ai-in-the-earth-and-space-sciences/ Rivas... Continue Reading →

I met the Prime Minister today at No 10. Interesting to discuss various topics with those present. I discussed the importance of geoscience, the subsurface, artificial intelligence and data management.

Digital Energy Journal have published a write up of my November 2023 talk at the Society of Professional Data Managers (SPDM).https://www.societypdm.org DEJ site here: https://www.digitalenergyjournal.com/home/ Thanks to KADME, Ikon Science, Mindat and GeoScienceWorld for permission to use material in the presentation.

Photo credit: Image by Mikhail Nilov from Pexels (Pexels licence) I came across an interesting blog from the European Geosciences Union (EGU) by Paulo Hader. Link to blog here: https://blogs.egu.eu/divisions/nh/2024/02/05/new-era-of-ai-how-can-foundation-models-help-disaster-risk-reduction/ Paulo suggests how Foundation Large Language models (LLM) can be incorporated into approaches for disaster risk reduction. "While traditional machine learning models are limited in... Continue Reading →

It's nice to step away from the computer and do some fossil preparation! I'm using compressed air which is funneled through a 'pen' removing the rock matrix to reveal the fossil. In this case an ammonite (bottom right) from the Jurassic, collected at Charmouth beach in Dorset, England.  It looks like a few pieces of... Continue Reading →

When Geoscience Meets Generative AI and Large Language Models: Foundations, Trends, and Future Challenges. I found this recent paper by Hadid et al (2024) helped spark a few ideas for me on how we may apply large Language Models (LLM) to real world problems which include geological information and related disciplines. Explainability and trustworthiness of... Continue Reading →

Many organisations are using Natural Language Processing (NLP) and Machine Vision to extract and classify images from their documents (such as PDF, PPT, Word, Literature etc.). Hoover et al (2023) published an interesting paper on how they achieved this, "Enhancing knowledge discovery from unstructured data using a deep learning approach to support subsurface modeling predictions"... Continue Reading →

GeoNLU: Natural Language Processing (NLP) and Spatial Data Infrastructure. Combining NLP, Natural Language Understanding (NLU) and Spatial data is important to many sectors. An interesting paper was published by Naveen et al (2024) recently that covers this space specifically focused on querying spatial data using natural language. The abstract states: "Integrating natural language processing (NLP) techniques with... Continue Reading →

Excellent paper recently published: Using a 3D heat map to explore the diverse correlations among elements and mineral species exploiting the open API to the superb Mindat, one of the largest mineral databases in the world. To explore new associations and knowledge hidden in the big geoscience literature data. They conclude "This study demonstrates how... Continue Reading →

A couple of weeks ago Lin et al (2023) unveiled their geoscience fine tuned Large Language Model (LLM) a 30B parameter geoscience fine tuned version of Meta AI's 'OpenSource' Galactica LLM - to create GeoGalactica. This was as part of the Deep-time Digital Earth (DDE) initiative funded by NSF China. They scraped over 6 million... Continue Reading →