Data rich but knowledge poor

2026-10-13T00:00:00.000Z

This article first appeared in CIM Magazine (Vol. 21, No. 5), co-written by Munkhtsolmon Munkhchuluun, co-founder of Ayavex Solutions, and Davide Elmo, professor of rock engineering at the Norman B. Keevil Institute of Mining Engineering, University of British Columbia.

Read the full article (PDF, 85 KB)

In short

A mine collects data from millions of metres of drill core, terabytes of surface monitoring, convergence measurements, maintenance records and inspection sheets. The risk is not running out of data. It is running out of the people who know what the data means and why it was collected. Roughly half of the industry's senior engineers are expected to retire within the next decade, and that knowledge leaves with them.

A newly hired geotechnical engineer inherits the reports, the rock mass parameters and the support design, but not the reasoning that connected the observations behind them. When engineers move on, what remains describes what was measured, not what it meant.

More computing power does not fix this on its own. A model trained on fragmented records learns from incomplete records about the mine, not from the mine, and inherits their gaps. Ground falls account for roughly 40 per cent of underground mining fatalities, yet the knowledge that might prevent them is rarely captured in a form any system can use.

The article argues for a different conception of mining knowledge: a continuous thread, maintained through the life of the mine, that ties

every observation and decision to where and when it was made (a drift, a stope, a coordinate, a stage of mine life),
to who made it and what they believed it meant at the time,
and to what it triggered: a design change, a support revision, a production hold.

Every mine is a repository not just of what was measured and how, but of why, with data and narrative dispersed along its drifts, stopes and ramps.

In the authors' words, the data exists and the sensors are in place. What is missing is the thread, and the willingness to treat it as the primary asset rather than an afterthought to the numbers.

Comments on the article can go to editor@cim.org, or to us at info@ayavex.com.

Ayavex Solutions blog

Data rich but knowledge poor

In short