Machine learning and deep learning have increasingly attracted interest over the last five years and we often see these terms applied in the context of mineral exploration, mine exploitation and geoscience studies. In addition, the term “artificial intelligence” is often used interchangeably with machine learning and deep learning. These new technologies and methods are developed by global tech companies and international research teams to solve both trivial and complex problems and often to surpass humans performance at specific tasks. In the mining industry, both recent start-up companies and well-established mining and service companies are implementing machine learning in all facets of their work. It is projected that mineral exploration will be revolutionized by new implementations of these algorithms on historical data, and that in the future mines will run automatically with self-driving trucks. These implementations promise impressive value gains but how these gains will be achieved is not clear to a general public who is unaware of the technology underlying automation. In addition, the potential for these technologies to surpass human performance in specialized tasks creates fear around job loss and restructuring, motivating some to reject them altogether.
As is often the case, however, the reality of the impact of these methods on the mining industry is more complex than is widely perceived. While machine learning, deep learning and artificial intelligence are related, they are different topics. Each have the potential to add value in the mining industry, but many challenges still need to be overcome in their implementation, and these technologies do not apply in all situations. This article tries to demystify artificial intelligence, machine learning and deep learning, and gives insight on how these technologies can be applied in the domain of geoscience in the mining industry.
