Search
Close this search box.

Customer Success Story: Sibanye-Stillwater & Isatis.neo

Company

Sibanye-Stillwater

Region

USA

Geology

ISATIS.NEO

Ready to elevate your mining operations?
Let's talk

When the Unit Manager Group Resource Estimation & Reporting at Sibanye-Stillwater wants to identify better two intricate geological domains in a complex Platinum Group Metals deposit in their mine in Montana, USA, he uses the Isatis.neo advanced sample clustering tool.

 

CLIENT STORY

Geological domaining is a crucial step in the resource modelling process. However, domains can be challenging to identify when grade populations are overly intricate.

Sibanye-Stillwater faced one such challenge for a PGM (platinum group metals) deposit with complex low-grade and very high-grade zones and several faults. They generated two domains that successfully separated the two grade populations and improved the block model’s quality.

They opted for the sample clustering tool to overcome it, combining:
Grades
The orebody thickness

Sibanye-Stillwater is a global mining and metals processing group with a diverse portfolio of projects and investments spanning multiple countries.

Established in 2013, they currently operate in Argentina, Australia, Finland, France, India, South Africa, the USA, and Zimbabwe. Specialising in a variety of commodities, Sibanye-Stillwater’s portfolio includes gold, platinum, copper, zinc, lead, and lithium.

 

They deal in various commodities such as:

The company was founded in 2013 and is present in:

HOW TO TAKE MASSIVE GRADE SPOTS INTO ACCOUNT IN PLANNING?

Sibanye-Stillwater is working on a PGM orebody extension project close to its Stillwater and East Boulder mines in Montana.

The project presents extremely high-grades that are distributed sporadically throughout the deposit interspersed with lower-grade material and intersected by fault lines. These factors contribute to the complexity of establishing distinct domains.

THE ISATIS.NEO CLUSTERING TOOL IS THE SOLUTION

Isatis.neo offers a powerful sample clustering tool based on geostatistical hierarchical clustering.

It automatically groups borehole samples into homogeneous classes based on several continuous and categorical variables. Users can select the number of classes they want data to be grouped into, the variables used for the classification, and the weights to assign them.

Users can select:
The number of classes they want data to be grouped into
The variables used for the classification
The weights to assign them
“Several faults cut the orebody, but we were unsure which to use to generate the domaining. We were seeking a solution that would allow us to identify geological domains undoubtedly and objectively.”
Antonio Umpire – Unit Manager Group Resource Estimation & Reporting

A PROCESS IN SEVERAL STEPS

Antonio Umpire, who is familiar with Isatis.neo and its predecessor, Isatis, utilised the sample clustering tool to categorise samples into a specific number of domains.

  • Initially, he attempted to create three domains based on platinum- palladium grade values, which identified one area with low grades.
  • He then tried four domains, which provided a clearer classification.
  • Finally, Antonio introduced the undiluted horizontal width into the computations and created five domains to validate his assumptions.

 

This approach enabled him to quickly and accurately pinpoint two distinct groups of samples: with low values and with extremely high values.

The Isatis.neo clustering tool automatically groups samples according to their similarity in different variables. In this case, four classes were used for the clustering analysis. Clusters are displayed as a dendrogram.

Automated sample clustering:

2D cross-section showing the domaining in four classes, defined by Isatis.neo’s automated sample clustering. The west part clearly identifies the lower grades.

Undiluted horizontal width:

Domaining using the “undiluted horizontal width” variable validates domaining computed only with PTPD data.

OPTIMIZED CAPPING

Antonio applied a similar principle in another mine block to determine optimised capping values for two grade populations, which also had a complex distribution This technique enabled him to efficiently and objectively separate samples with normal grades from those with extremely high grades and define a suitable capping value for each population.

The results
Better resources
Improved planning

“Without this detailed domaining,the little spots of extreme gradeswould not have been consideredin the estimation, and the planningwould not have met the targets.Using this split, planning will bedone accordingly.”

Antonio Umpire – Unit Manager Group Resource Estimation & Reporting

Ready to elevate your mining operations?
Let's talk

See RELATED cases

GET in touch