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 →

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 →

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 →

Panning for fossils. Standing in a river digging the gravel with a shovel to sieve for fossils is a fun hobby. This is the latest hoard. Megalodon tooth in the center (7cm) to the left are various shark teeth (such as Lemon, Tiger, Sand Tiger), towards bottom left Stingray (and Eagle Ray) tooth plates. To... Continue Reading →

The video of my talk at the Artificial Intelligence for Geological Modelling and Mapping Conference at the University of Exeter back in May is now on YouTube. You can find it on the link below in the comments, along with the other excellent talks on this topic, in a superbly organised conference by Charlie Kirkwood... Continue Reading →

NASA and IBM Large Language Models for Earth Science (INDUS). The INDUS encoders were trained on a corpus of 60 billion tokens encompassing astrophysics, planetary science, Earth science, heliophysics, biological, and physical sciences data. According to IBM/NASA the models are freely available on Huggingface and they will be releasing benchmark datasets.Under the hood, from an Earth... Continue Reading →

I gave an overview of ethical AI for chatbots during this months SPE Data Science and Engineering Analytics Technical Section (DSEATS) Advisory Board. If you wish to find out more about DSEATS and its activities, link here: https://connect.spe.org/dsea/home

Artificial intelligence-driven assessment of salt caverns for underground hydrogen storage: Interesting paper from Derakhshani et al (2024) recently published, using various raster images and machine learning algorithms to predict what might be the most suitable areas for underground geological hydrogen storage in Poland (focusing on salt caverns).  Derakhshani R, Lankof L, GhasemiNejad A, Zaresefat M.... Continue Reading →

Interesting article in The Guardian today. They picked up the Deep-time Digital Earth (DDE) Chinese chatbot article in the "Geoscientist" from last week, and have conducted some further research with geologists. Link to the article in The Guardian here: https://www.theguardian.com/technology/article/2024/jun/24/geologists-censorship-bias-chinese-chatbot-geogpt #Geology #Geoscience #ArtificialIntelligence #AI #LLM #GeoGPT #DDE #IUGS