Geological AI: New open-source tool for scanning grains of sand. A convolutional neural network (CNN) was trained by researchers at Stanford on hundreds of electron microscope images of sand grains to determine the depositional environment. This represented material from different geological ages and locations, terrestrial environments fluvial (rivers and streams), eolian (windblown sediments, such as sand dunes), glacial, and beach. This can be used for geology, geoarchaeology, forensics etc.
“Instead of a human going through and deciding what one texture is versus another for sand grains, we are using machine learning to make microtextural analysis more objective and rigorous,” said Lapôtre, who is senior author of the paper. “Our tool is opening doors for microtextural analysis applications that were not available before.”
“Worldwide, sand is the most used resource, after water, and is critical in the construction industry. Materials such as concrete, mortar, and some plasters require angular sand for proper adhesion and stability. Gauging the origins of sand, however, to ensure ethical and legal sourcing is challenging, so the researchers hope SandAI can bolster traceability. For example, SandAI could help forensics investigators crack down on illegal sand mining and dredging.”
SandAI has also been tested on deposits dating back to the Cryogenian “Snowball Earth’ time, to perform new science.
SandAI is freely available, link to the paper from Hasson et al (2024).
A Geodyssey - Geoscience Text Analytics and Enterprise Search Research 
Leave a comment