Pix2Geomodel: A Next-Generation Reservoir Geomodeling with Property-to-Property Translation. Interesting paper from Al-Fakih et al (2025).Conclusions“This study presented Pix2Geomodel, a pioneering conditional GAN framework, to enhance geological modeling of the Groningen gas field’s Rotliegend reservoir. By leveraging Pix2Pix architecture, the framework successfully predicted facies, porosity, permeability, and water saturation from masked inputs and facilitated property-to-property translation,... Continue Reading →
Is AI-research being co-opted to keep track of people? Interesting paper published in Nature and supporting podcast.
Narrative“A significant amount of research in the AI field of computer vision is being used to analyse humans in ways that support the development of surveillance technologies, according to new research. By analysing the contents of thousands of research papers, the team behind the work showed that 90% of studies, and 86% of patents resulting... Continue Reading →
Data Study Group Final Report: British Geological Survey – Detecting Shallow Gas from Marine Seismic Images.
Data Study Group Final Report: British Geological Survey - Detecting Shallow Gas from Marine Seismic Images.AbstractThis data study group challenge focused on extracting information from legacy offshore seismic data. The British Geological Survey has an archive of thousands of images of scanned paper records that contain information about the marine subsurface, but these images are... Continue Reading →
The British Geological Survey (BGS) is using Large Language Models to improve real-time monitoring of geological hazards and their impacts.
The British Geological Survey (BGS) is using Large Language Models to improve real-time monitoring of geological hazards and their impacts.“To date, the real-time impact data that is needed to effectively forecast and monitor geological hazard events has been unavailable or incomplete. The FloodTags platform aims to fill this gap by using large language models (LLMs)... Continue Reading →
Synthetic Geology – Structural Geology Meets Deep Learning.
Synthetic Geology - Structural Geology Meets Deep Learning. Intriguing paper from Ghyselincks et al (2025). Subsurface deep learning by a synthetic data-generator process that mimics geological activity such as sediment compaction, volcanic intrusion, and tectonic. The authors then built a foundation model trained on this synthetic data to generate a 3D image of the subsurface... Continue Reading →
Open-access: Global Stable Isotope Dataset for Surface Water.
Open-access: Global Stable Isotope Dataset for Surface Water. The dataset consists of three main elements: website data from IEAE (GNIR), water isotope website from University of Utah, measured data and reference data - 22,432 surface water sampling sites across seven continents. Put together by Li et al (2025). Dataset link in the comments.Abstract"Hydrogen and oxygen... Continue Reading →
Fossil Box for Schools including Special Educational Needs.
Fossil Box for Schools including Special Educational Needs. I met up with Mark Baggott yesterday from the Earth Heritage Trust. He has been doing an absolutely remarkable job sourcing British Fossils in labeled boxes free for schools. So far over 150 schools have benefitted.Reading the handwritten letters first hand, from children who have had the... Continue Reading →
Webinar: The AuScope EarthBank ProjectBuilding Nationally Collaborative Geochemical Research Infrastructure to Enable Discovery.
Webinar: The AuScope EarthBank ProjectBuilding Nationally Collaborative Geochemical Research Infrastructure to Enable Discovery.Webinar 1st July 2025. Register link in the comments.AbstractProf Brent McInnes , AuScope EarthBank Project Director, John de Laeter Centre, Curtin University, Australia.“The AuScope EarthBank project (EarthBank project) is a $21 million national initiative to modernise Australia’s geochemistry data infrastructure and to advance... Continue Reading →
Open access geoscience data: First global scale submarine landform dataset driven by terrain knowledge at 15 arc second.
Open access geoscience data: First global scale submarine landform dataset driven by terrain knowledge at 15 arc second.Paper, code and dataset published by Yu et al (2025).This dataset is reported to be “the first global scale submarine landform dataset at 15 arc second, which offers a new perspective on submarine landforms, providing key insights into... Continue Reading →
Enjoyed listening and giving a talk to the AAPG and Mining Young Professionals network yesterday in London.
Enjoyed listening and giving a talk to the AAPG and Mining Young Professionals network yesterday. Excellently organised event and thought provoking discussions.Great session from Graeme Bagley on soft skills, then an inspirational talk from Promise Ekeh .This was followed by geoscience digitalisation talks from Shashwat Verma , Peter Kiss and myself on unstructured data and... Continue Reading →