Home > News > Maple Gold using machine...

Maple Gold using machine learning for gold targeting at Douay

Jul 7, 2020


Maple Gold Mines Ltd. has engaged Computational Geosciences Inc. ("CGI") to complete a new and expanded Artificial Intelligence ("AI") study for targeting high-grade gold at Douay. This study will use all available digital datasets within a 128km² area centered on the resource area (Fig. 1) in order to generate gold prospectivity maps and provide additional target areas to validate and rank in advance of the Company's next phase of drilling later this year. 

AI studies, as applied to Mineral Exploration, involve the application of automated mathematical models (intelligent algorithms) to data-rich environments in order to allow recognition of subtle features or patterns in the data that are not always evident to the human eye. CGI will be employing their proprietary VNet segmentation deep learning algorithm to help the Company's targeting efforts.

The Company believes that the quality of its databases, together with CGI's rigorous methodology and built-in interaction with the Company's geologists at all stages of the process, will result in a high quality product that will allow for the definition of additional new drill targets. 

Maple Gold's President and CEO, Matthew Hornor, commented: "Our team is excited to collaborate with CGI, a group we are very familiar with given their strategic partnerships with the Ivanhoe group of companies. The last time any machine learning was applied at Douay was limited and more than a decade ago. There is significantly more project data now, with more sophisticated algorithms and increased computing power on the processing side. We are excited to complete this exercise in parallel with our IP program as we refine and detail top priority discovery targets in advance of our planned drilling in late Q3 or early Q4." 

About VNet: 

VNet is a customized convolutional neural network (CNN) that can handle an arbitrary number of geoscience data inputs in either 2D or 3D. This customized CNN is sensitive to sparse or dense data areas, can detect multiple feature resolutions (i.e. regional trends vs. 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. 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.

Image removed.

Fig. 1: Area of AI survey, including data-rich resource area and its extensions.

To view an enhanced version of Figure 1, please visit:
https://orders.newsfilecorp.com/files/3077/59246_c18e083584573b6c_001full.jpg

CGI's methodology includes a multi-step process that will involve close interaction between CGI and Maple Gold geologists. The database review and validation step has largely been completed, with the next step being the generation of preliminary prospectivity maps. Final results, prospectivity maps and a corresponding report are expected in Q3. 

About Maple Gold 

Maple Gold is an advanced gold exploration and development company focused on defining a district-scale gold project in one of the world's premier mining jurisdictions. The Company's ~355 km² Douay Gold Project is located along the Casa Berardi Deformation Zone (55 km of strike) within the prolific Abitibi Greenstone Belt in northern Quebec, Canada. The Project benefits from excellent infrastructure and has an established gold resource that remains open in multiple directions. For more information please visit www.maplegoldmines.com

About CGI

Computational Geosciences Inc. is a world leading consulting company in artificial intelligence and geophysical 3D inversion modelling. Our strength is the combination of geoscience data expertise within the natural resource sector, coupled with innovative inversion and machine learning capabilities. By leveraging these knowledge bases within our customized convolutional neural network architecture (VNET), CGI applies a novel approach to prospectivity mapping in order to find the discoveries of tomorrow.



Tags: Quebec / Exploration / Gold / All Articles