A large-scale open-source 3D seismic dataset with labeled paleochannels for advancing deep learning in seismic interpretation. Interesting paper from Wang et al (2025).Abstract“Identifying paleochannels in 3D seismic volumes (seismic paleochannel interpretation) is essential for georesource development and offering insights into paleoclimate conditions. However, it remains a labor- intensive and time-consuming task. Deep learning has shown... Continue Reading →

Enjoyed presenting the keynote at INGV 'AI Day' today. How we ethically design, educate, promote and use Language Models within the geosciences is likely to be of increasing importance.

“Landslides, triggered by natural events like heavy rainfall and earthquakes, pose significant risks to lives, infrastructure, and the environment. Effective monitoring and mapping of landslides are crucial for mitigating these risks, guiding emergency responses, and supporting resilient infrastructure planningUsing multi-source satellite data, you will work to create an accurate landslide detection model. This model should... Continue Reading →

Delighted to be invited to give the keynote at INGV day on July 9th. “The future of AI in the Earth Sciences”.“Participants at AI@INGV Day will first and foremost find a concrete opportunity to connect with colleagues and groups already working on Artificial Intelligence within the Institute.This will be a valuable moment to meet, share... Continue Reading →

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 →

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.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.“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 →