https://youtu.be/Mhz1jyxuNts

Many valuable ore deposits, particularly those rich in copper and gold, are associated with a specific type of intrusive rock called adakite. Geologists have long used the presence of adakites as a guide in mineral exploration, but here's a critical challenge: not all adakites are created equal! Some are linked to significant ore bodies (classified as 'fertile'), while others are completely barren. Knowing the difference is essential for efficient prospecting, but traditional methods of analyzing rock chemistry can sometimes fall short in making this distinction clearly. This means exploration efforts can be wasted on areas with the wrong kind of adakite. But what if we could use cutting-edge technology to identify the 'fertile' adakites with much higher accuracy? A recent study focusing on adakites in New Brunswick, Canada, applied machine learning to geochemical data to solve this exact problem. By training AI models on the chemical compositions of known fertile and barren adakites, they found that techniques like Support Vector Machines (SVM) can classify these rocks with impressive accuracy. The research also pinpointed specific chemical elements and ratios, such as middle rare earth elements (including Gd and Dy) and Hf, as key "fingerprints" of fertile adakites. This approach offers a powerful new tool for geologists, promising to refine mineral prospectivity mapping and significantly improve the chances of discovering new ore deposits. 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