SPECIALIST EQUIPMENT TECHNOLOGY TRAILS
Business exploration company Earth AI is shaking up the mining industry. Saskia Henn gets the low down on the company’s business model and outlook
R
ecent exponential advancements in artifi cial intelligence mean that the technology is leading most
industries by the nose – and mining is no exception. Australia-based EarthAI, an AI-driven mineral exploration company, is arguably one of the best know AI companies in mining. It uses a precise metal detection technology, fundamental geology and responsible drilling to fi nd and deliver diff icult to excavate resources. International Mining Engineer’s Saskia
Henn caught up with EarthAI’s CFO Monte Hackett to fi nd out more about the company’s practices and operations.
HOW DO YOU USE AI TO IDENTIFY MINERAL DEPOSITS AND THEN DECIDE ON A DRILL SITE? The model learns from 400 million training cases around the Australian continent. In each case, it passes raw data through the neural net and characterises the geological environment for each site. The neural net changes and evolves as it learns from the data. Once trained, the AI can scan any area on Earth and identify fertile geological environments yet to be discovered.
WHAT KIND OF DATA DOES THE PREDICTIVE TECHNOLOGY TAKE INTO ACCOUNT TO LOCATE UNTOUCHED RESERVES? In Australia all exploration work since the 1970s has been entered into a central archive. This includes, with coordinates, drill results, geochem,
geophysics and soil samples. Our algorithm organises this large 50-year data set into predicting new prospective greenfi eld sites. We leverage these data points along with remote sensing and geophysical imaging to pick up subtle anomalies that are unable to be detected by the human eye. We run this analysis across the continent which then creates targets, typically 2km2 sites that we thereafter evaluate and drill using more traditional exploration methods.
IN WHAT WAYS DOES EARTH AI’S TECHNOLOGY IMPACT THE DISCOVERY PROCESS OF NEW MINERAL DEPOSITS? Earth AI’s technology drastically improves the discovery process because our algorithm does the heavy lifting for site selection. When we get to the site, we are looking at a 2km2 area, this is signifi cantly smaller than your typical tenement (which might be greater than 50x that size). This allows our team to be much more eff icient in fi nding the concentrated deposit.
HOW DOES EARTH AI’S ROLE IN LOCATING UNTAPPED AREAS IMPACT MINING COMPANIES AND IN WHAT WAYS ARE THEY AFFECTED? Our company vision is ultimately to partner with miners. We recognise the value in extraction, fi nancing, construction and selling, we also view this as a completely diff erent skill set from our core competency. Our goal
is to be the organic growth engine to the mining industry, leveraging technology to fi nd exciting new projects that we then sell to mining partners who can more eff iciently tackle the subsequent steps once feasability tests have been done.
TELL ME ABOUT SOME NOTABLE EARTH AI DISCOVERIES AND PROJECTS SO FAR THIS YEAR We have made several exciting discoveries. Perhaps one of the more interesting was at Fontenoy on the east coast of Australia. This is a partnership with publicly traded company Legacy Minerals. Fontenoy has been interesting because there was geological consensus that the east coast was not a good site for magmatic nickel deposits. Our AI predicted the opposite and shortly thereafter we indeed found magmatic nickel and platinum group elements. An exciting case showing that technology can disprove convention.
WHAT PLANS DOES EARTH AI HAVE FOR 2025 AND BEYOND? We have recently purchased two additional rigs, bringing our current fl eet to three. Our near-term focus remains in Australia and will be balanced between adding new sites to our portfolio with continuing to drill and develop the sites for which we have already have success.
For more information visit:
www.earth-ai.com
www.engineerlive.com 21
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44