The increasing appetite to integrate AI into the mining value chain
Besides mining and AI (Artificial Intelligence) being two distinct fields, they are now more than ever intersecting each other in mining projects around the globe. The past five years have seen a steady infusion of AI into the digital strategies of companies such as BHP, Anglo America, Rio Tinto, Vale, and the growth plans of many mining tech firms.
Companies in the mining technology sector that incorporate AI from the beginning will possess a significant competitive edge over their competitors. By following a proven playbook for achieving product-market fit and scaling, these companies can also focus on developing a robust strategy to construct and enhance a valuable dataset and AI model.
This latest article from InvestMETS brings some reflections of the main players and industry specialists on the subject, including our very own CEO Sam Bose.

Tackling Mining and Global Challenges with Scientific AI
Amidst the high demand for critical minerals, the world needs to reach net zero while facing a decrease in ore deposits. In fact, many mine sites have exhausted the high-grade ore and are now mining much lower grades), urgently increasing the need to improve the efficiency of their mining processes. Also, safety and sustainability issues in mining are pushing companies to incorporate continuous excellence across their operations.
However, the adoption and use of Artificial Intelligence in the mining industry continue to be challenging both because of the mines’ harsh environment and inherent inertia in the risk-averse approach to new technology. But for Sam Bose, for those mine sites that get it right, the returns are fast and large.
For example, AI-driven solutions can provide valuable insights into Stockpile contents and ore properties, enabling more informed blending decisions and accuracy on what is coming to the plant. While AI-led recommendations on setpoints can enhance downstream processes like Grinding, resulting in increased throughput. Moreover, AI can optimize operating parameters in the Flotation circuit, leading to incremental improvements in metal recovery. This is just a taste of what IntelliSense.io customers experience.
IntelliSense.io’s development of ‘small’ proprietary machine learning models built for specific industrial processes that can be retrained, allows users to ‘look inside and influence the model performance’ to build trust between end users and AI outputs, has been key to its success
The Old ‘Consulting-Led’ World
One of the biggest hurdles in mining is the requirement to cater for the large degree of variance in ore properties, including impurities, that go downstream through the plant. These new AI solutions need to account for this, and be explainable to build user trust.
Nevertheless, there is still market confusion being created by point, ad-hoc solutions that are being built to only work on one site. As such, it’s difficult to get scale or network effect benefits from the data to create truly robust and accurate models.
These kinds of internal initiatives often supported by generic consultancies have high failure rates. And unfortunately, this tends to feed the overall inertia preventing miners from getting huge productivity and efficiency advantages provided by these technologies, especially when they are being asked to produce more metals at the lowest environmental and cost footprint.
Wrapping Up
Overall, the integration of AI in the mining industry has the potential to improve operational efficiency, safety, sustainability, and decision-making, leading to more productive and responsible mining practices.
Stimulating digitization to improve business performance, and sustainability and reduce risk is part of IntelliSense.io’s core values. Through the use of Scientific AI* (pioneered by IntelliSense.io), we have created a fusion of first principle or phenomenological models with machine learning approaches which is a completely new way of looking at the real world. By doing so, our apps can drive process improvements, identify and remove bottlenecks, increase asset availability, reliability, and utilization for a single operating unit (like Flotation, Thickeners, Stockpiles, Grinding, Leaching, etc), or work in tandem to increase overall mine-to-market efficiency.