Latest hobby project is detecting fossils (in this case ammonites) from photographs. Labelling examples in existing images, building a deep learning model and applying it to new information. Whether this actually assists me scan the shingle using my mobile phone on my next fossil collecting trip remains to be seen!
There is quite a bit in the literature already using such techniques, even down to predicting fossil species level rather than class. These types of techniques have also been applied to infrared spectroscopy to determine molecular fingerprints of billion year old fossils (Loron 2023) and used to detect lithologies and microfossils in thin sections Bouziat et al (2021).
At a broader scale, deep learning has been used on aerial photographs and satellite imagery to detect new potential sites for fossil discoveries. Training models on sites where no fossils have been found and ones where fossils have been found.
According to Berdugo (2022), “Although still in its infancy, this approach can accurately locate areas of interest and has already assisted in the discovery of four new field sites in the scientifically important location of Gorongosa National Park.”
References:
https://oxsci.org/ai-fossil-hunters/
https://www.thenakedscientists.com/articles/interviews/using-machine-learning-analyse-fossils
#machinelearning #fossils #geology #geosciences #artificialintelligence
A Geodyssey - Geoscience Text Analytics and Enterprise Search Research 
Leave a comment