The researchers tested their model in October 2020 by requesting locations for rutherfordine, andersonite, schröckingerite, bayleyite, and zippeite. For efficiency, they set parameters in which only predictions with a 70% or higher “confidence” level would be shown. The model returned four predicted localities for rutherfordine, one of which has since been confirmed in Italy; one for andersonite, which has yet to be confirmed; one for schröckingerite, which was confirmed in Colorado; two for bayleyite, both Utah locations of which have been suspected before; and seven for zippeite, one of which has been confirmed in the Czech Republic. (As with bayleyite, four of the predicted zippeite localities had already been suspected.)

Another test run focusing exclusively on raw earth elements (REE) predicted localities for monazite, allanite, and spodumene, which are used for construction, radiation research, and batteries. Out of 15 predictions, 12 monazite localities have been confirmed; 13 out of 19 allanite localities have been confirmed; and one out of 12 spodumene localities have been confirmed.

Eoin Treacy's view

Innovation in prospecting has been a major driver of resource discoveries over the last couple of decades. Applying deep learning models to abundant data is the most productive use of AI because the data is not in question. Together with better geophysical models there is clear potential for impressive resource discoveries to be made. That’s essential if the ambitions of climate activists are to be attained.
At the Future Minerals Forum two years ago Robert Friedland gave a characteristically bullish presentation on the outlook for copper demand and the key role his companies can play in fulfilling it. Despite questionable demand growth projections from China, Ivanhoe Mines hit a new closing high today.
Friedland’s prospecting technology company Ivanhoe Electric listed on the stock market in 2022 and is testing its March peak.