A Geodyssey – Geoscience Text Analytics and Enterprise Search Research
A voluntary non-commercial research blog since 2015
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 →
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 →
Interesting paper generating microscopic images of rocks using generative artificial intelligence (GenAI) published this week by Młynarczuk and Habrat (2025).“The generation of synthetic images can be an important element in supporting the augmentation and analysis of multimedia data. It has applications in many scientific fields. Also, in geological and mining sciences.This study presents generative artificial... Continue Reading →
Upgrade to open-access global geomagnetism GIS portal operated by the British Geological Survey (BGS).“The World Data Centre (WDC) for Geomagnetism, based in Edinburgh, was established in 1966 and is operated by BGS. Its mission is to collate, store and distribute data (and associated metadata) from observations of the Earth’s magnetic field.As part of this mission,... Continue Reading →
AI and Planetary Impact: The Business of Saving the Planet. Insightful event today staged by John Hopkins University. How the rapid rise of AI technologies is influencing climate action, environmental sustainability, and wildlife conservation. Session included:Kate Brandt - Chief Sustainability Officer at GoogleDiego Saez Gil - CEO of PachamaMalaika Vaz - National Geographic ExplorerJerry Burgess - Director of the... Continue Reading →
Open-source: Automatic description of rock thin sections: A web application. Delighted to share Stalyn Paucar and colleagues work from Ecuador (Universidad Central del Ecuador) published this week.AbstractThe identification and characterization of rock types is a core activity in geology and related fields, including mining, petroleum, environmental science, industry, and construction. Traditionally, this task is performed... Continue Reading →
Open-source GIS LLM Copilot: towards an autonomous GIS agent for spatial analysis. Enabling non-experts to perform geospatial analysis with minimal prior knowledge. Also offering a true open-source framework based on QGIS to potentially keep data local to you.Interesting paper from Akinboyewa et al (2025). Links to the paper and code in GitHub in the comments.This... Continue Reading →
GeoGPT Data Security Risks for Geoscientists. The Deep-time Digital Earth (DDE) online proprietary GeoGPT Application operated by Zhejiang Lab has data security risks. In the interests of safeguarding the geological community, geologists should be fully aware so they can make informed decisions.Extracts below of a letter published in the ‘Geoscientist’ today of the Geological Society... Continue Reading →
On this day exactly 10 years ago, I created a free community outreach blog for geoscience data and AI. Thank you to everyone for all the encouragement and support you have given over the years.The blog was initially focused on techniques leveraging content in documents - unstructured data, search (IR) and NLP, tying this to... Continue Reading →
Large Language Models: Due to the risks, NASA decides against fine tuning a generative earth science LLM.“Based on our initial assessment, the costs and risks associated with developing an exclusive NASA Science Mission Directorate (SMD) decoder (generative) model currently outweigh the benefits.”In a paper published yesterday in the American Geophysical Union (AGU) - Perspectives of... Continue Reading →
A Geodyssey - Geoscience Text Analytics and Enterprise Search Research 