Farzi is a quantum computing hardware and machine learning engineer from the University of Waterloo. Her undergraduate work in materials sciences, nanofabrication, and quantum electrodynamics informed her direction towards quantum computing, and later, with her acquired machine learning skillset, quantum machine learning. Her career inspiration is to design elegant solutions to tough problems - this has allowed her to work in fields like tissue engineering, telecom, and photonics.
Uncover Hidden Value: $50M+ In-Situ Added Through Targeted Short-Program AI Drilling
As mining operations face increasing geological complexity and tighter capital discipline, generating meaningful resource growth from existing assets has become a critical challenge. This presentation shows how applied artificial intelligence enables targeted, short-program brownfields drilling designed to rapidly test high-confidence mineralization opportunities using limited drilling meterage and existing mine infrastructure.
Through real case studies from producing copper and gold operations in Chile and Kazakhstan, the session demonstrates how machine learning integrates geological logging, assay datasets, and spatial variables to reveal mineralization patterns often missed by conventional modelling workflows. Using compact expansion drilling programs of less than ~2,500 metres, AI-guided targeting added approximately 7.7 kt of copper (~$60M in-situ value) in one underground operation and verified 37.5 koz of gold (~$70M in-situ value) across multiple clusters in another, contributing to measurable resource growth and extension of mine life.
Emphasizing practical implementation and tangible outcomes, the talk highlights how AI augments geological expertise to accelerate resource validation cycles, optimize drilling capital allocation, and support more resilient near-term mine planning in complex brownfields environments.
