Big Data Means Big Opportunities For Mining

A modern mining operation produces vast quantities of data. The data comes from almost every facet of the operation, from traditional exploration, production, and enterprise data to so-called “big data” streamed in real time from the multitude of instruments installed in the mine, plant, and mobile equipment. While many miners are already taking advantage of the big data revolution, data analytics remains one of the biggest opportunities in the mining industry to drive better and faster decisions. 

“The industry’s greatest opportunity is how best to use big data”, contends Andrew Hall, Director and Advisory Executive Lead at AMC Consultants. “There’s a lot of it, and it’s easy to lose focus on the real value drivers.” says Hall.

In Papua New Guinea, Freeport Resources deployed Minerva Driver artificial intelligence (AI) solution at their Star Mountains project to enhance surface and subsurface exploration. The Driver AI software delivers new insights into exploration data by evaluating all elements returned by modern laboratories, not simply the elements of direct economic interest, Freeport says. The work this requires is too time-consuming and complicated to be carried out by project geologists using conventional database tools and statistical methods.

Big data mining case studies from around the world

In Mongolia, Shenbao Energy and Aerospace Heavy Industry successfully tested five 5G autonomous trucks in extremely cold conditions at their Baorixile coal mine. 

And in Russia, Alrosa installed an automated wireless monitoring system and wearable devices for employees at its Aikhal division.

Accessing big data remotely

The COVID-19 pandemic has made it difficult to visit many mine sites. But the extensive amount of data and new technologies now available have allowed AMC to complete a significant number of 10X Performance DiagnosticsTM studies remotely. Drone footage and surveys, and comprehensive production datasets have enabled detailed review and benchmarking of work quality, time-usage, activity costs and productivity to determine the mines' full potential. Undertaking site visits always provides greater insights but having access to the large amount of data we do today makes it possible to undertake meaningful analysis remotely like never before explains Hall. 

These applications are diverse, but they all have one thing in common: they rely heavily on the generation, collection, organisation, and analysis of huge quantities of data. 

What is big data analytics?

Big data analytics involves the use of advanced analytic techniques—such as artificial intelligence (AI), machine learning, predictive analytics, data mining, and statistics—on very large, diverse data sets.

What are the types of big data analytics?



In general, big data sets are of a size or type that are beyond the ability of traditional relational databases to capture, manage and process with low latency—that is, at a practical speed. The data is diverse, comprising structured, semi-structured and unstructured data, sourced from every facet of the operation. 

Data types can include geochemical, geophysical, geological, geotechnical and hydrological properties of samples; chemical and physical properties of concentrates; mine design and surveying; mobile and fixed equipment condition monitoring; GPS tracking; consumption rates of fuel, energy and additives; plant feed rates and metallurgical recoveries; personnel safety monitoring; environmental monitoring; and much more.

Because of the extreme volume or unstructured nature of the data, big data is often difficult or expensive to capture and store and, as a consequence, is often discarded or ignored. However, analysis of big data allows companies to gain new insights from previously untapped data sources, particularly when done in combination with traditional production and enterprise data. 

“It’s about understanding the reality of every layer of the business and ensuring data is shared so that there is one source of truth.” says Jayson Tolley, Advisory Lead - Strategy Optimization at AMC.

Maximising your mine’s big data

The potential cost and revenue drivers in a mining operation are as diverse as they are numerous. Energy consumption, rock hardness, ore and waste chemistry,  feed grade, reagent levels, flow rates, mineral recovery, effluents, temperature, road surface, wear rates, warehouse capacity, time usage, shift cycles, lost-time injury frequency, operator competency, and supervision levels are just a few of the multitude of factors that can flow through to the cost of production.

The better you are able to understand the relationships between these drivers, the more opportunity you have to design and operate in ways that will maximise your margins. In particular, ore bodies are intrinsically variable on every scale from kilometres at the tectonic scale right down to micrometres at the mineral grain scale. But only a tiny fraction of an orebody can be sampled before it is mined.



At the feasibility stage, data is sparse, which makes development of predictive relationships and forecasts difficult. But modern data science and machine-learning are enabling step-change improvements in predictions. The more accurately you can predict ore behaviour, the more opportunities you have to manage the natural variability of the ore—for example, by developing smarter blending and scheduling techniques.

Big data challenges

While some mining companies have embraced data, many haven’t made it past basic spreadsheets. But before you rush off and start a conversation with the IT department, you need to do a bit of planning. To be successful, you need to understand what data needs to be collected, how it’s going to be collected and stored, which tools you’ll need to analyse it, and, above all, what you can realistically expect to gain from analysing the data once you’ve captured it.

The companies that are benefiting the most from data are the ones that have implemented data collection and analytics throughout their organisation, from the drill rig to the processing plant. “Many big mining companies have invested heavily in data collection and then use specialist data science to identify the root cause of problems that are not identifiable by simply looking at spreadsheets”, says Tolley.



Good data management practices and processes are vital to realising the full potential value of the data. You also need to make sure that the data is clean and representative. If data isn’t collected, stored, and managed efficiently, or if the right tools or metrics aren’t used to analyse it, you run the risk that the project will not only fail to realise the targeted improvements, but may instead make things worse, exposing the operation to greater risk. Damian Peachey, AdvisoryRegional Lead and Principal Engineer at AMC, agrees. “Some try collect so much raw data they risk ending up down a rabbit hole”, says Peachey.

Big data and the need for expert analysts

It takes more than just the data. Due to the vast size of the data, conventional methods of data analysis are impractical. To encompass the entire volume of data flowing from the operation, specialist data science is needed. And it takes specialist knowledge to know where to look and what the most appropriate tools are.

Put simply, data is meaningless without expert analysis. Strong collaboration is required between every discipline to provide a holistic view of the operation. Without experience and deep-domain understanding, the data itself won’t help.

Effective data analysis needs to be timely and requires an experienced analyst. “A proper understanding of context is crucial to correctly identify the root causes of a problem. Then, armed with that knowledge, you can make informed, practical decisions that provide sustainable outcomes”, Peachey agrees.

“Increasingly, the thread that runs through every aspect of a mining operation is data”, says AMC’s Andrew Hall. “If you understand the data and choose the right methods to extract information and insights, then information from each part of the mining process can be used to inform and improve the performance of the whole. That’s how smart data adds value to a mine.”

Talk with the experts

Companies around the world are tapping into AMC’s deep-domain expertise to unlock the value hidden in their data. Using a range of unique proven tools and processes, underpinned by SmartData™, the world’s most extensive, site-sourced, independently validated mining database, AMC Advisory helps mining executives make data-backed strategic and operational decisions.

To learn more about how to extract the maximum value from your operation’s data, fill in the contact form below and a representative from AMC Advisory from your local AMC office will be happy to set up a meeting.