Machine Learning
RSC’s machine learning (ML) solutions can help resolve trends or patterns in datasets that have too many dimensions or are too complex for the human brain to process or identify. They can help to resolve complex problems; from regional greenfields exploration through to resource and reserve estimation, and into active mining.
Machine learning solutions revolutionise the way exploration companies conduct their field programs, taking out the guesswork and minimising the risk inherent in the search for new deposits. These advancements in data analytics have the potential to rapidly identify new deposits, saving time and money.
RSC’s world-class approach to data collection, data quality and domaining, in combination with our partner, GoldSpot Discoveries Corp’s, ML technology, leverages disruptive technologies to better comprehend resource or exploration potential.
Summary of prospectivity mapping workflow integrating geology, geophysics, geochemistry, structure and mineralisation.
What is Machine Learning?
Machine learning is a subfield of artificial intelligence. It harnesses algorithms to identify patterns in data efficiently, objectively, and repeatably. It searches through data to look for patterns and teaches computers without being explicitly programmed.
Machine learning is not just a matter of “statistics”. Some statistical methods are used, but instead, the process can find relationships and links that are not obvious. It allows data processing and information tracking that otherwise would not be achieved by normal statistical processing.
It is not there to replace geologists! If the machine learning analysis shows unexpected results from the data, our specialist geologists still need to interpret it.
Does it Work?
El Penon mine, Chile
Our partners, Goldspot, worked with Yamana Gold in 2018 at its El Penon mine in Chile to find more new mineralisation to extend the life of the mine. Using historical mine data such as drill data, geophysical data, geological and geochemistry data, a predictive lithological map was created of the property that helped speed up target definition. This led to multiple successes, finding new zones and targets that are currently being explored. Yamana has credited GoldSpot’s technology with improving exploration targeting at El Penon, where it has recently added reserves and resources.
Queensway, Newfoundland
In early 2020, New Found Gold reported its maiden drill hole at its Queensway project in Newfoundland cut 19 metres of 92.86 g/t gold. The 10-hole drill programme tested several targets generated from geochemical, geophysical and structural analysis, combined with machine learning. Starting with an outdated geological map, GoldSpot used additional magnetic and electromagnetic survey data, in combination with field validation, its team of experts, and machine learning to produce a deep learning bedrock map with geophysical targets.
More success stories
The following articles show some recent news articles with several stories on the success of machine learning.
GoldSpot AI technology helps boosts exploration targeting at El Penon gold mine
How Artificial Intelligence and Machine Learning are Revolutionizing Mineral Exploration
Our toolbox
Our ML tools are varied and can be applied to a variety of two-dimensional (2D) and three-dimensional (3D) datasets across the exploration-mining value chain. Check out our tools below.
Machine-assisted geology maps
Outcrop Finder
