I provided input to this interesting article written by Clarissa Wright in the Energy Voice E-FWD recently. The more subsurface and geoscience data we can use in the pre-permit and planning phase of Carbon Capture and Storage (CCS) projects, the more likely we are to reduce uncertainties to support policy and investment decision making. Where... Continue Reading →
Geoscience Machine Learning and Semantics with guest Paul Cleverley: PODCAST
Honoured to be a guest on a podcast with Ashleigh Faith recently. Ashleigh has been an inspiring communicator on information semantics for many years. https://www.youtube.com/watch?v=S3TNmYj4y-I
Ethics in Geoscience Artificial Intelligence
Back in June 2024 I authored an online article on serious concerns for potential state censorship, copyright infringement and lack of transparency in the Deep-time Digital Earth (DDE) Project's AI Chatbot GeoGPT. This has now been published in the autumn edition of the Geoscientist magazine from the Geological Society of London. A reply from the... Continue Reading →
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... Continue Reading →
Essential questions in earth and geosciences according to large language models
Interesting paper from Hatvani et al (2024) on the Top 100 important questions for geoscience and earth science using Large Language Models (LLM), published in 'Open Geosciences' this week. The authors cover the differences between using 'geoscience' and 'earth science', mapping to the UN Sustainable Development Goals, and issues and benefits of using such approaches.AbstractCan... Continue Reading →
Geoscience Big Data Workshop
A new workshop held at USC’s Information Sciences Institute hopes to have a ripple effect throughout the geoscience Big Data community. The FROGS (Facilitating Reproducible Open GeoScience) workshop held last month drew participants from various fields within geosciences.Examples given included, "Dannielle Fougere a paleoseismologist, is focused on understanding the behavior of the Garlock Fault in the... Continue Reading →
Generative AI in subsurface science and policy
Innovative use of generative AI to support policy making through design and people focused approaches."Policy Lab partnered with the UK Government Office for Science (GO-Science) to reimagine the future of the subsurface and consider the policy implications with policy professionals and stakeholders in a highly interactive workshop. Here the ‘subsurface’ refers to everything below the land or... Continue Reading →
Creating 3D Mesh Photogrammetric Models of Fossils
I've been experimenting creating 3D models of the fossils in my collection. This is the rostrum (jaw) from an Ichthyosaur (Jurassic; Charmouth, UK) an early attempt using the camera on my smartphone and a window sill in the house with a white blind behind it - very quick and easy to create.I probably need to... Continue Reading →
International Union of Geological Sciences (IUGS) Sponsored Meeting on Large Language Models in the Geological Sciences
AI in Geoscience: An International Union of Geological Sciences (IUGS) sponsored meeting on Geoscience Large Language Models (LLM) took place at the Geological Society of London on July 16th attended by 59 stakeholders world-wide.I was asked to attend representing the IUGS Geoethics Commission. Of particular focus was the IUGS endorsed, Deep-time Digital Earth (DDE) LLM... Continue Reading →
Novel counterfactuals and LLM’s in Geoscience?
Reasoning skills of large language models are often overestimated: Interesting MIT study showing how LLM's often do well in familiar scenarios but not in novel ones, illustrating the challenges of moving from memorization to reasoning. Testing on GPT-4, GPT3.5, Claude and PaLM-2 they conclude:"...it would also be interesting future work to see if more grounded... Continue Reading →