A Geodyssey – Geoscience Text Analytics and Enterprise Search Research
A voluntary non-commercial research blog since 2015
So many applications of machine vision YOLO (You Only Look Once) models in the earth sciences. I came across a few environmental examples where YOLO models were used on unmanned boats and drones to detect rubbish (garbage). This might help clean up our rivers to some extent. There are other examples where even recyclables can... Continue Reading →
Using Large Language Models to estimate the intensity of earthquake shaking from multimodal social media posts.Interesting paper from Mousavi et al (2025) using Google’s Gemini 1.5 Pro LLM to estimate earthquake intensity from social media and CCTV. The authors state:“Our experiments demonstrate that Gemini can estimate ground shaking intensity based on the content of a... Continue Reading →
Open access code: Querying one of the largest mineral databases in the world using natural language for co-occurrence mineral analysis and heat map visualization for geoscience data analysis.Interesting paper from Zhang et al (2025) from the University of Idaho connecting Open AI's GPT-4o Large Language Model (LLM) through prompt engineering to the mineral database Mindat... Continue Reading →
Interesting use of GenAI methods to create photorealistic satellite imagery analogues from seismic attribute maps as a visual aid for depositional environment models in seismic interpretation.Ramdani et al (2024) conclude, “Conditional Generative Adversarial Network utilized as a method to convert seismic attribute maps into photorealistic virtual satellite image renditions of the modern analog. This virtual... Continue Reading →
I came across an old photo I took 35 years ago of the fossil Trilobite ‘Paradoxides’ in Wales, UK. As a national fossil for Wales, this might be a candidate. Some of the largest Trilobites ever found came from the dark mudstone deposits from an ancient sea in Wales, of Middle Cambrian age approx 500... Continue Reading →
The Bubble Effect: Focusing only on your geoscience disciplinary session at a conference may miss 44% of the 10 most relevant contributions. This may therefore pose a risk of missing geoscience contributions addressing similar problems from a different perspective presented outside their own sessions.Interesting paper from Sodoge et al (2024) using Natural Language Processing (NLP)... Continue Reading →
Delighted my paper on AI Ethics in the Geological Sciences has been published today in the peer reviewed open access Journal of Geoethics and Social Geosciences!AbstractArtificial Intelligence (AI) offers many opportunities for the geosciences to improve productivity, reduce uncertainty in models and stimulate discovery of new knowledge. There are also risks to geoscience, from the... Continue Reading →
Expanded AI Model with Global Data Enhances Earth Science Applications: NASA have released V2 of the open-source Prithvi Geospatial Artificial Intelligence foundation model with global data to support a broader range of geographical applications. These include tracking changes in land use, monitoring disasters, and predicting crop yields worldwide. Previous use cases of V1 included post-disaster flood... Continue Reading →
A Geodyssey - Geoscience Text Analytics and Enterprise Search Research 