https://youtu.be/81mLYoZKOk8

This research article explores the use of Random Forests (RF), a machine learning algorithm, for creating Mineral Prospectivity Maps (MPMs) to identify areas with high potential for orogenic gold deposits in the Geraldton area of Ontario, Canada. The authors address challenges in MPM modeling, including a novel application of natural language processing (NLP) to analyze geological map data and pinpoint potential gold sources and traps. They also investigate various methods for defining non-deposit training data and demonstrate the effectiveness of combining multiple MPMs in an ensemble approach. The study focuses on the Beardmore-Geraldton greenstone belt, known for its gold deposits, and uses a variety of geological, geophysical, and geochemical data. The authors utilize 3D density, susceptibility, and resistivity models derived from geophysical data to define lithology at different depths. They also employ NLP to extract text-based information from geological maps, converting it into numerical data for RF modeling. Results highlight the importance of weighting gold mines based on production and demonstrate that the MPMs generated using RF are effective in predicting known gold occurrences. The research identifies several promising areas for gold exploration, primarily located within the Beardmore-Geraldton greenstone belt. P. Geo. Ricardo A Valls, M. Sc. and Geo Gadfly Valls Geoconsultant ORCID ID- https://orcid.org/0000-0002-5421-0914 Scopus Author ID: 7003369619/35335510700 ResearcherID: S-6604-2018 If you like this content, please "buy me a coffee" https://www.buymeacoffee.com/goldendroplets