by Mayra Flores
Artificial intelligence applied to mineral exploration could reduce drilling by up to five times, generating substantial savings in time and capital, and allowing for more informed decisions to continue or discard projects.
This was the central message of Jef Caers, professor of Earth and Planetary Sciences at Stanford University and one of the world’s leading experts in applied geosciences and decision-making under uncertainty, during a webinar held as part of the World Mining Congress 2026 series.
According to Caers, this AI-based approach can significantly decrease drilling requirements by changing the traditional logic of exploration. Instead of drilling according to a fixed grid to estimate grades, the system plans drilling campaigns aimed at refuting human-generated geological hypotheses and strategically reducing uncertainty until the company can make an informed decision to “continue or abandon.”
From autonomous vehicles to the smart prospector To explain the concept, Caers referred to the autonomous vehicles currently operating in San Francisco: “These systems work extremely well. They are very sophisticated. We call this type of AI an intelligent agent.”
This “intelligent agent” is not simply a predictive tool.
“An intelligent agent is an AI for sequential planning under uncertainty. It is not just a tool; it is an AI that makes decisions while acquiring data,” explained Caers.
Exploration: drilling to refute hypotheses
Caers applied this framework directly to mineral exploration, noting that “all critical challenges in the mineral supply chain can be understood as sequential planning problems under uncertainty, starting with exploration.”
In conventional practice, companies typically build a single deterministic model of the subsurface and drill systematically. “An intelligent agent will plan the drilling to refute human-generated hypotheses and then drill only to define ore grades and tonnages,” he warned.
“If your hypothesis about the subsurface is completely incorrect, the drilling will be extremely inefficient,” Caers explained.
Instead of completing a grid independently of emerging information, the system dynamically adjusts drilling locations to reduce geological uncertainty as efficiently as possible.
Technological transformation in decision-making under uncertainty will be a central theme of the upcoming World Mining Congress 2026. Jef Caers is a member of the WMC 2026 Program Committee. The event will take place from June 24-26 at the Lima Convention Center in Peru. It will bring together global leaders from mining, technology, and academia to discuss the future of critical minerals and innovation in the sector. Early bird registration fees are available until March 31 on the official website: https://wmc2026.org.
Information provided by Mineria-Pan Americana