Goldcorp, IBM develop 'first-of-a-kind' AI exploration tech

Goldcorp and IBM Canada have co-created a new technology product: IBM Exploration with Watson, which aims to improve predictability for gold mineralisation
Goldcorp, IBM develop 'first-of-a-kind' AI exploration tech Goldcorp, IBM develop 'first-of-a-kind' AI exploration tech Goldcorp, IBM develop 'first-of-a-kind' AI exploration tech Goldcorp, IBM develop 'first-of-a-kind' AI exploration tech Goldcorp, IBM develop 'first-of-a-kind' AI exploration tech

IBM Exploration with Watson was developed using data from Goldcorp's Red Lake Gold Mines. © Goldcorp

Staff reporer

PRESS RELEASE: The solution applies artificial intelligence to predict the potential for gold mineralisation and uses powerful search and query capabilities across a range of exploration datasets.

Todd White, executive vice president and chief operating officer at Goldcorp, said: "The potential to radically accelerate exploration target identification combined with significantly improved hit rates on economic mineralisation has the potential to drive a step-change in the pace of value growth in the industry."

Developed using data from Goldcorp's Red Lake Gold Mines in northern Ontario, Canada, IBM Exploration with Watson leverages spatial analytics, machine learning and predictive models, helping explorers locate key information and develop geological extrapolations in a fraction of the time and cost of traditional methods.

"Applying the power of IBM Watson to these unique challenges differentiates us in the natural resources industry," said Mark Fawcett, partner with IBM Canada. "We are using accelerated computing power for complex geospatial queries that can harmonise geological data from an entire site on a single platform. This is the first time this solution has been ever used, which makes this project all the more significant."

At Red Lake, IBM Exploration with Watson provided independent support to drill targets planned by geologists via traditional methods and proposed new targets which were subsequently verified. Drilling of some of these new targets is ongoing, with the first target yielding the predicted mineralization at the expected depth.

"Timelines are short in mining and exploration. I am excited to see the improvements we can make with the data platform and gold mineralisation predictions," said Maura Kolb,

Goldcorp's exploration manager at Red Lake Gold Mines. "These tools can help us view data in totally new ways. We have already begun to test the Watson targets from the predictive model through drilling, and results have been impressive so far."

Goldcorp will put the new technology to work on additional targets in 2019.