Zircon Knows: Smarter Ore Exploration Through Machine Learning
- Using the trace chemistry of zircon, researchers accurately predicted the source rock type—even without visible geological context.
- Random Forest models achieved over 90% accuracy in classifying both igneous rocks and ore deposits from zircon element data.
- Just eight elements in zircon—including hafnium, uranium, and yttrium—are enough to map mineral systems and guide exploration.
Wen, Z.-H., Li, L., Kirkland, C.L., Li, S.-R., Sun, X.-J., Lei, J.-L., Xu, B. & Hou, Z.-Q. (2024). A machine learning approach to discrimination of igneous rocks and ore deposits by zircon trace elements. American Mineralogist, 109(6), 1129–1142. https://doi.org/10.2138/am-2022-8899.
Listen to the Podcast
Linked Products & Services: