MaxMine has announced the successful implementation of a production-grade machine learning (ML) system for load and dump classification across its Australian mining customers, including Glencore, NRW Holdings and Macmahon.
The system, which has now been fully operational for six months, has delivered significant operational improvements, including:
- Reduce the workload of your site team by minimizing missed and erroneous loads.
- More accurate production tracking, especially in complex and edge-case scenarios.
- High internal development efficiencies with structured data and modern ML pipelines enable systems to address diverse edge cases without the need for bespoke development.
“The successful implementation of this new machine learning system confirms what we have been observing across industries: the organizations that are successful with AI are those with the highest quality datasets,” said Sean Mitchell, CEO of MaxMine. As adoption accelerates, it has become essential to have high-fidelity ground truth data to provide accurate results, improve operational visibility, and enable faster, more informed decision-making.
This milestone comes as MaxMine Executive Chairman Tom Cawley has been appointed Head of Mining for the newly formed AI Accelerator Cooperative Research Center (AI CRC). The AI CRC aims to build Australia’s sovereign AI creation capacity and enable sectors such as mining to develop their own AI tools rather than relying on offshore capabilities.
“Despite increasing investment in AI, industries such as mining still struggle to move beyond pilot efforts and achieve operational results at scale. Gartner estimates that 60% of AI projects fail due to a lack of AI-enabled data and 42% of organizations abandon AI efforts before reaching production. At MaxMine, we have demonstrated Australia’s ability to develop advanced AI tools that work effectively at scale in the mining industry. I look forward to my role at Accelerator CRC.” Drive further innovation across the sector and help strengthen Australia’s competitiveness in key minerals markets. ”
The new ML system is deployed within a private, secure environment and leverages over 14 million hours of high-quality, labeled operational data and high-resolution datasets across the entire material handling and transportation operations.
This foundation allows MaxMine’s latest ML models to deliver stable, reliable results with industry-leading accuracy in real-world production environments.
Professor Anton van den Hengel, principal investigator at the Australian Machine Learning Institute and interim CEO of the AI Accelerator CRC, added: “The ability to deploy models with such accuracy across such a wide range of assets and site types is rare. MaxMine’s ability to do this demonstrates a uniquely rich, accurate and human error-free data set, combined with a long-term, multi-site, multi-machine training data set.”
