Article 3: Geology Intelligence

So far in this series, I have talked about some of the general challenges the mining industry is facing today, such as dramatically increasing global demand for diminishing and often lower-grade mineral resources, as well as one of the biggest challenges of them all: grappling with the surge in big data and the need to manage it properly.

I’ve also looked at the challenges of dealing with big data during the exploration phase of a new underground or surface mine, and at block caving and its need for big data and proper big data management. Here, I discuss the challenges specifically facing geologists and geology departments.

Geology data challenges

Geology challenges are similar to those I outlined for exploration. For example, while advances in data acquisition technologies mean that new data from a variety of sources, like downhole geophysics and more routine collection of geo-metallurgical parameters, is now available to inform and enhance resource modelling and estimation, data alone cannot solve problems like

like poor communication between the geology department and interested stakeholders. Nor can it help if you are not managing your data properly.

Geology departments have, in general, been slow to adopt:

• Detailed dashboards that display in-depth analyses of necessary resource modeling parameters and data. Without detailed dashboards, geology departments cannot take advantage of data analytics and trends that can help them make the highest quality resource estimation decisions. A dataset that takes into account all available data will produce an estimation that is more statistically sound than one that uses only some data, and the decisions based on that more complete data will have a more positive impact on company value as well as production and other downstream activities.
• Centralized storage for all geoscience data and objects that can be accessed by anyone who needs to explore that data. Without a central knowledge repository, a geologist might unwittingly use old data for a resource estimation, or not be able to take advantage of all of the available data, simply because the geologist couldn’t find it or wasn’t aware it existed — and the result is a poor or unreliable estimate.
• A single platform on which to share ideas, ask questions, and get feedback on estimation results. Lack of a shared platform can lead to isolated and siloed teams, and managers who are unable to see resource estimations in visual form unless they have access to the same desktop applications the geologists have.

In addition, typically when kriging is used as the basis for resource estimation with a large search volume and number of samples, estimates are relatively smooth, with little variation over a given area or volume. Adding in big data — via techniques such as co-kriging using secondary variables — can help produce estimates that take more localised variations in the mineralisation into account, while still achieving acceptable slope of regression minimising conditional bias.

However, many geology departments do not have the tools they need right now to do in depth-analysis of kriging estimation outputs. They also lack user-defined dashboards to display and analyze estimation parameters and to compare current and previous estimations, all of which undermines confidence in the final estimation of resources.

One solution

One solution to these challenges is for mines to pursue geology intelligence — a way to use big data management and big data analysis to help eliminate resource estimation issues.

GEOVIA’s Geology Intelligence application enables mines to collect, store, and integrate all their geology data — no matter the type or source — on the 3DEXPERIENCE platform. With all geology data in one location, mines then have the ability to:

• select, adopt, and customise a variety of advanced-analytics programs, including AI and machine learning, and
• create customised dashboards specifically for visualising specific aspects of the resource estimation process.

From there, geologists can:

• use pre-created analytical tools to index, analyze, and report a variety of metrics, such as grade, volume, tonnage summary per level, and material type
• compare multiple versions of the block model and maturity state management for all files, and
• display and share specific analytics, such as an analysis of the estimated weight of ore, waste and average grade for various cut-off grades, or a comparison of the mathematical (spherical) model and variogram curve from the drill hole.

Next in this series

In the next article, we will discuss the challenges and solutions for caving data management.