Seminar Details:

• Date: Wednesday, August 7, 2024
• Time: 11 am – 12 pm AEDT
• Location: Geoscience Conference Room 449, online 
• Zoom Link: https://uni-sydney.zoom.us/j/85859443646?from=addon

Combined machine learning and landscape evolution models reveal hidden mineral deposits needed for the energy transition

Abstract

Porphyry deposits are critical sources of copper, with surging demand to supply the transition to net-zero emissions. Declining discoveries suggest the near depletion of surface deposits, motivating the development of exploration techniques to target buried deposits. Recent progress has focussed on implementing machine learning to predict when and where deposits formed at depth but lacks any information about their preservation. Here, we show that calibrated landscape evolution models effectively predict the near-surface preservation of deposits. Combining these predictions with the machine learning formation predictions, we can account for deposit formation and subsequent movement through the crust to refine where near-surface deposits may be situated at the present-day. We test our approach on the New Guinean mountains, where our predictive models accurately identify prospective regions in accordance with many known surface deposits and highlight new areas for exploration.