Earthgenome's Earthindex looks an interesting way for earth observation as a no-code solution for detecting activities using satellite imagery. Such as illegal mining in the Amazon and Africa, undocumented waste sites in Indonesia, Dams along the river Tigris and Eurphrates, wheat fields in Ukraine, Solar Energy construction in the Mekong Basin etc. Supporting indigeneous communities... Continue Reading →

Global search trends of disaster topics ‘Flooding’ (blue) and ‘Hurricanes’ (red) over the past 5 years. These data are from Google search trends.Relative popularity of natural disaster search queries appears to be increasing globally.Examining search data and trends may reveal some interesting phenomena. It reflects what is popular / of interest in parts of society... Continue Reading →

It can be relatively easy to create Large Language Model driven apps that exploit your own structured and unstructured data to produce rich results. This example is showing information on quarries in a certain area, combining data, text and geospatial information.One difference in this approach between using Google search and ChatGPT type approaches, is that... Continue Reading →

Spent a day talking artificial intelligence with the British Geological Survey in Nottingham this week. Fascinating to hear the projects already being undertaken and opportunities to apply new techniques.They hold over 15,000 cores from onshore boreholes, as well as core from just about every oil & gas well ever drilled offshore in the UK. An... Continue Reading →

Interesting article on AI ethics. Is it ethical for AI to be hosted to the international scientific community from a legal jurisdiction that will not allow questions or outputs that tarnish the image of that particular government or its policies? With the blessing and legitimacy of a prestigious international scientific body?Local laws must be respected.... Continue Reading →

Gave a talk today on Artificial Intelligence to the UK Government Department for Environment, Food and Rural Affairs (DEFRA). A focus on Natural Language Processing, Large Language Models and Machine Vision in the Geological Sciences.Areas I covered for these techniques included: geology, palaeontology, outreach and education, geotourism, hydrogeology, hydrology, environmental contamination and pollution, geohazards -... Continue Reading →

Delighted to be appointed Chair of the Artificial Intelligence Ethics Task Group of the International Union of Geological Sciences (IUGS) Commission on Geoethics. We will be working towards a white paper as a guiding document for the Union.

Using AI to describe fossils. I've been experimenting with GPT-4o to see how well it can describe fossils from smartphone photographs. At a high level it seems to perform reasonably well given most fossils found are not complete specimens.In my unscientific experiment using 10 commonly found fossils from the Jurassic Coast in England, it was... Continue Reading →

Free open-source tools: Automated petrographic image analysis by supervised and unsupervised machine learning methods. Interesting paper from Azzam, Blaise and Brigaud (2024).“We present two novel software tools: GrainSight, which utilizes a supervised deep learning model (FastSAM) for automated grain detection and morphological characterization; and PetroSeg, which employs an unsupervised segmentation approach to explore rock properties... Continue Reading →