Mining / Copper
BHP: Analyzing ore characteristics and supporting blasting and blending decisions at the Escondida mine
- Company
- BHP
- Country
- Australia
- Adoption stage
- In operation
- Source published
- Date basis
- The date the source was published. It can differ from the date adoption started.
- How the source was checked
- Read the full source text
The work problem
In an article BHP published on its official website on March 25, 2026, Digital Officer Mikko Tepponen wrote that BHP always seeks to maximise what it can produce from its mines, and that because exploration, development, processing and maintenance are interconnected, constraints in processing can affect mine performance. At Escondida, variability in ore characteristics led to production losses at the semi-autogenous grinding (SAG) mill.
Technology and data
Teams at Escondida use digital twins and AI models to understand how ore characteristics influence processing performance. This analysis supports more informed blasting and blending decisions before material reaches the plant. BHP said these technologies do not replace the expertise of its people but help them apply their judgement and experience more effectively.
Results
According to the article, this approach has reduced losses associated with ore variability at the SAG mill, and in targeted applications some production losses linked to granulometry were reduced by around 70%. BHP said its digital and analytics initiatives delivered more than US$2 billion in value over the past four financial years across the value chain, from exploration to operations to logistics.
Limits and open questions
The article does not disclose when the application started, the AI models used, the period and scope over which the roughly 70% was measured, or the effect converted into production volume or cost. The US$2 billion is the value for BHP’s digital and analytics initiatives as a whole.
Sources
- From discovery to decisions: data, AI and the future of miningbhp.com, Accessed
Compiled from public sources. These are not results from ATF Works customers.