The mining newspaper for Alaska and Canada's North

AI to assist Auryn in search for gold

North of 60 Mining News – February 2, 2019

Auryn Resources Inc. Jan. 30 announced that it is employing an artificial intelligence program to assist in the targeting of high-grade gold mineralization at its 390,000-hectare (964,000 acres) Committee Bay gold project in Nunavut.

To accomplish this cutting-edge step in geology and geoscience, Auryn has teamed up with Computational Geosciences Inc., a company that utilizes advanced software tools for data processing, inversion, interpretation, and targeting.

These tools include the VNet segmentation deep learning algorithm being employed at Committee Bay.

VNet is a type of convolutional neural network, a class of deep neural networks, that can handle an arbitrary number of 2D or 3D geoscience data inputs. It is also sensitive to sparse or dense data areas, can detect multiple feature resolutions – such as regional trends versus local anomalies – and is scalable across large areas.

This style of deep learning for mineral exploration is an emerging technology that requires expertise in geoscience data processing, data interpretation, and artificial intelligence.

Auryn said the biggest advantage of a data-driven solution is to extract subtle correlations across multiple datasets over a large spatial area, all while reducing human bias. By generating targets with deep learning, and vetting them with an experienced geoscience team, the expertise of the human is still utilized but complemented by the power of the machine.

"The CGI machine learning platform will leverage our highly-disciplined and thorough approach to data collection with the deep knowledge of Auryn's technical team to produce the highest probability targets," said Auryn Resources COO and Chief Geologist Michael Henrichsen.

Auryn will initially use the Computational Geosciences machine learning platform to generate additional targets across the "Three Bluffs playing field" – a 1,600-square-kilometer- (620 square miles) area which includes the Three Bluffs deposit and a 20-kilometrer- (12.5 miles) long shear zone hosting the Aiviq and Kallulik targets where significant gold mineralization has been encountered.

Three Bluffs, the most advanced deposit on the Committee Bay property, hosts 2.1 million metric tons of indicated resource averaging 7.85 grams per metric ton (524,000 ounces) gold; and 2.9 million metric tons of inferred resource averaging 7.64 g/t (720,000 oz) gold.

Aiviq, a new gold target, is located about 12 kilometers (7.5 miles) north of Three Bluffs.

Auryn discovered Aiviq with rotary air blast drilling in 2017, including one hole that cut 12.2 meters of 4.7 g/t gold, including 3.05 meters of 18.09 g/t gold.

The company reported that all 16 holes drilled at Aiviq during 2018 encountered the targeted structure, with the best intercept being 13.5 meters of 1.54 g/t gold, including six meters of 3.3 g/t gold.

"The Committee Bay belt represents a global opportunity for substantial gold deposits. As a technical team, we remain committed to discovering large-scale gold deposits and we will continue to use innovative techniques, such as machine learning, to improve our probability of success when working on a widely till-covered belt," said Henrichsen.

The gold identified at Aiviq is situated in a 7,000-meter-long gold-in-till anomaly that runs along the shear zone being targeted with Computational Geosciences AI platform.

This platform will process the vast amount of data collected through extensive surface geochemical sampling, geological mapping, geophysical surveys, and drilling completed by Auryn and prior explorers.

Auryn said extensive experience in the fields of geoscience data processing, data interpretation, and artificial intelligence are needed to realize optimum results, expertise Auryn and Computational Geosciences bring to the table.

The company is currently in the process of generating the AI-assisted targets and plans to reveal the results later this month.

–SHANE LASLEY

 

Reader Comments(0)

 
 
Rendered 12/20/2024 08:50