AI models dramatically cut drilling costs, ensure early availability of geology data, reduce human error, increase prediction accuracy, slash overall costs, and shrink exploration lead time by as much as 90 percent.
Mining engineers, geologists and data scientists are developing Artificial Intelligence (AI) to find, evaluate, predict, and map subsurface rocks because these technologies do in weeks what traditional methods take years to achieve.
In our new Technical Post series on AI and mining resource estimation, we examine what the technology entails, how mining companies are developing it, and what it means for the industry.
What is AI?
Artificial intelligence contains many subfields, including machine learning, neural networks, deep learning, computer vision and natural language processing. AI generally refers to the broad idea that machines can execute tasks “intelligently.”
Machine learning refers to the concept that machines can learn and adapt through experience. A neural network is a computing system modeled after the human brain. Deep learning uses huge neural networks with many layers of processing networks. Computer vision uses pattern recognition and deep learning to recognize what’s in a picture or video. Natural language processing allows computers to analyze, understand and generate human language and speech.
It’s Happening Now
In mining resource estimation, machine learning is being used to locate and estimate mineral deposits by training algorithms with large data sets to identify patterns not detectable by humans alone. For example, in 2020 a team of researchers competing with other teams involving more than 2,200 data scientists and engineers from more than 100 countries developed new interpretive maps revealing undiscovered mineral deposits deep underground in remote South Australia. Researchers combined government magnetic and gravity data with deep neural network AI analysis.
The team, known as DeepSightX and led by Professor Javen Shi, director in Advanced Reasoning and Learning at the Australian Institute for Machine Learning at the University of Adelaide, developed machine learning approaches that helped geologists visualize the features of rocks that would otherwise remain invisible.
In another recent pilot, resource geologists developed machine learning models with historical geophysical data to establish orebody properties for non-core drilling holes. The project generated results in certain cases of predictions of critical properties and lithology prediction with confidence as high as 95 percent. Mining professionals also successfully calculated sonic velocity from multiple geophysical variables and improved the performance of resource models.
That’s a huge advantage because major discoveries of near-surface mineral deposits are declining globally.AI-based technologies can lead to faster decisions with greater accuracy, improved health and safety, higher efficiency through error elimination and reduced environmental footprint.
The Greatest Challenge
The challenge for mining companies, however, is not about adopting the latest technologies. The challenge is implementation. Mining industry culture is traditionally risk-averse, which can stifle innovation. Mining professionals often simply have limited understanding of new technologies. And many companies lack the capacity to absorb fast-changing technologies typically provided by external sources.
There are many groups working to help miners take on new digital tools. But mining companies are discovering that they must retool their own organizations to use these new solutions. As a Deloitte/NORCAT study concluded:
Ultimately, success for mining companies is not about adopting the latest technologies. It’s about developing an organizational culture that leverages digital thinking into the heart of the business, such that strategies and practices work together to transform the way corporate and operational decisions are made across the enterprise.
In the next posts, @ML - WW Industry Process Expert at GEOVIA - explores why mining companies need smart machines, various approaches to using AI for resource estimation, what early results tell us, and the critical barriers to implementation. We hope you find this series helpful.
About the expert
Min Liang is a Geostatistician and a Data Scientist. She holds a PhD in Geostatistics from the École Polytechnique de Montréal and records 6 publications on geospatial modelling and simulation. Before joining Dassault Systèmes in 2019, Min worked 1 year in Data Sciences and 3 years as an Environmental Consultant.
Access all technical papers and articles:
