We are creating some awesome events for you. Kindly bear with us.

Utilising artificial intelligence to predict mineral deposits

A team from the University of Adelaide’s Australian Institute of Machine Learning (AIML) has won second place in a global challenge that tested the limits of data science and geology and developed new ideas about mineral exploration.

According to a recent press release, the team exploited multi-disciplinary skills at the intersection of artificial intelligence (AI) and geoscience in order to analyse public data sets from the Mount Woods project area, near Prominent Hill, to predict where new deposits of elements and minerals could lie.

Winning second place in the challenge has awarded the team with AU$ 200,000.

Background of the project

The researchers from AIML and the Institute of Minerals and Energy Resources (IMER), which are both hosted by the University, collaborated with industry experts in minerals exploration and geoscientific modelling for this endeavour.

The team developed a drilling exploration plan that took advantage of the overwhelming data available, while being justifiable from a geoscientific perspective.

The team was able to achieve this by integrating the latest concepts from mineral systems modelling, with recent breakthroughs in deep learning and computer vision.

The breakthroughs in deep learning included artificial neural networks and algorithms, which was inspired by the human brain that learns from large amounts of data.

The project began with the team deep diving into the available data.

Additionally, the engineers developed a variety of interactive visualisation tools, which facilitated the domain experts’ ability to explore the data.

Done in parallel, the geoscientific modelling experts have produced state-of-the-art models of TMI, Gravity, and Magneto Telluric (MT) data for the Mount Woods region.

It took the team three months to develop a world-class predictive modelling capability, which illustrates the disruptive potential of machine learning when paired with expert domain knowledge.

The model developed by the team will be tested in real life, with the top targets scheduled to be drilled by the end of 2019. Hopefully, the testing will unearth the next big Australian mineral deposit.

Participants from all over the world

One thousand global participants from sixty-two countries had joined the data-driven Explorer Challenge.

All of them dug through more than six terabytes of public and private exploration data from modern mining company’s Mount Woods tenement in northern South Australia.

The prize recognises the team, called DeepSightX, as a new and competitive minerals exploration AI team that applies a multi-disciplinary approach with the requisite domain expertise to tailor target modelling to each new geological and commodity setting as these arise.

The team from the University was comprised of 11 members plus 1 who provided valuable advice to the group.

Furthermore, it also demonstrates that South Australia has exceptional local talent.

Send this to a friend