Tag Archives: resource modelling

Maptek machine learning trial points to future of mineral deposit modelling

Base metals, Energy minerals, Mineral exploration, Mining services, Mining software, , , , , , , ,

A trial of Maptek DomainMCF at an underground metals mine has concluded that machine learning will most likely become the preferred modelling method for mineral deposits, according to the software company.

DomainMCF is a platform that Maptek says will ‘put the geology back into geologists’, applying deep learning and big data computing methods to generate domain boundaries directly from drill hole sample data. Such rapid generation of resource models is a game changer for operations, according to Maptek.

In the trial of DomainMCF, geologists at the IGO Limited Nova-Bollinger underground mine in Western Australia trialled the solution’s machine-learning tools for modelling its resource.

Nova-Bollinger is 700 km due east of Perth, with the operation mining and processing nickel-copper-cobalt sulphide ores.

Traditional resource modelling is based on a drill hole database containing 99 lithological and 11 sulphide mineralisation logging codes. From this database the mine geologists use implicit modelling to interpret 22 different domains – 21 sulphide domains and one all-encompassing waste halo domain.

The block modelling process is undertaken annually by a team of geologists on site and in the Perth corporate office, taking several months to complete. The team trialled DomainMCF in parallel to the standard workflow as part of the 2020 resource update.

The required inputs for DomainMCF are a csv file comprising drill hole database or composite data, and an optional upper and lower surface to define the spatial extents of the region to be modelled. A block model parameter file details the origin of the block model, the 3D spatial extents and the block/sub-block dimensions.

Grade estimates are done on a 6 m x 6 m x 2 m block size and sub-blocks are permitted down to a quarter of the parent block size, according to Maptek.

During the trial, three primary tests were run using different versions of the drill hole file to explore the capabilities of the application and see how they compared to the existing workflow.

Test 1 provided DomainMCF with the drill hole composite file for the 22 different domains. Six chemical elements (Ni, Cu, Co, Fe, Mg and S) were provided to assist with the training phase of the machine-learning algorithm.

For Test 2, the data used in the first test was augmented with lithology coded data from the drill hole information outside the estimation boundary limits. The chemical variables were again used to help train the algorithm.

The purpose of this test was to determine if a combined sulphide and lithological model could be produced, and to see if giving DomainMCF additional information would impact the prediction of sulphide domains.

A hands-off approach was used in Test 3 to see how DomainMCF modelled a file containing only mineralisation codes and the grouped lithology used for Test 2. None of the domain codes from Test 1 were used.

Test 3 examined if the DomainMCF model was comparable with a manually-coded domain model and whether it was useful in the mineral resource estimate process.

IGO Senior Mine Geologist, Fletcher Pym, presented the trial results in a paper to the AusIMM International Mining Geology Conference 2022 in March.

“We were able to run Test 3, which was a relatively complicated model, in 45 minutes,” Pym said.

For Pym, Test 3 also showed that machine learning can produce very comprehensive models without the strong influence of a geologist.

Because machine learning made resource modelling much faster, senior staff had more time to focus on training less experienced core loggers. Improving the processes resulted in better quality drill hole logging, according to Maptek.

Pym added: “Machine learning will become particularly attractive if the process can not only model geological domains, but also return reliable grade estimates for mine planning across the full range of mineralisation styles.

DomainMCF model section

“Providing a well-understood confidence measure can assist in risk quantification of both geology and grade.”

The study, Maptek says, highlighted several advantages of machine learning:

  • The inputs required for machine-learning processing can be readily prepared in most resource modelling software;
    Machine learning modelling times are relatively short;
  • The pay-by-use business model is more cost-effective than maintaining implicit modelling software systems;
  • The machine learning model returns an objective measure of uncertainty in the geological model, which is likely to be useful in mineral resource classification and mining reconciliation work; and
  • Multiple different geological models can be prepared in parallel, meeting the JORC requirement to investigate ‘the effect, if any, of alternative interpretations on mineral resource estimation’.

Maptek Technical Lead for DomainMCF, Steve Sullivan, says he is excited at the potential of machine learning for revolutionising resource modelling.

“I’m amazed at the response – we are already seeing companies subscribe to DomainMCF for use in domain modelling for their 2022 resource reports,” he said.

“Machine learning works best when all the available data is presented, as shown in Test 3. The more data the better.

“The industry is struggling to find experienced personnel during the current mining boom, so embedding years of experience into smart systems helps get the job done on time and under budget.”

Maptek continues to work on proposed enhancements following feedback from industry trials of DomainMCF, with grade trend prediction added in the March 2022 release.

This is an edited version of an article that appeared in Maptek’s Forge newsletter.

Geovariances leverages Isatis.neo batch capacity, Python scripting for ‘infinite capabilities’

Mineral exploration, Mining services, Mining software, , , , , , , , ,

Sometimes, turnkey software solutions only partially fulfill a company’s needs and do not always meet its requirements; the company may want to go beyond standard jobs by customising specific processing route. This could see a company engage software developers to come up with in-house solutions that answer their needs – something that is challenging to maintain over the years.

To help clients get over this issue, Geovariances, the global provider of geostatistics-based software solutions, puts a significant part of its development efforts into the customisation capabilities of its flagship software product Isatis.neo.

Isatis.neo implements two powerful functionalities in that respect: recording a series of tasks and their parameters – the so-called batch capacity – and Python scripting for completing the data processing and interpretation workflow.

The combination of batch capacity and Python scripting gives the software almost infinite capabilities, according to the company, permitting the user to go beyond the geostatistical calculations: preparing company resource estimate/categorisation workflows, developing optimisation-based solutions, and more advanced algorithmic approaches for a more powerful use of the software.

Using Isatis.neo batch features, users select tasks, parametrise them, insert loops and conditional statements to set up workflows and tune them to the orebody specificities. Instructions are recorded into batch files that can be launched later on, either interactively from Isatis.neo or as a background process from a command-line interface or a third-party software solution using Python, to automatically rerun the whole task sequence with new data.

Isatis.neo’s Python functionalities allow further process customization, with users able to generate a wide range of variables or execute operations by calling on a wide choice of external Python libraries and functions.

During its last user meetings, held in January, Geovariances presented two of its achievements related to these capabilities.

The first case study was about the work completed for a multinational mining and metallurgy company.

This company called on Geovariances’ expertise to establish a global processing workflow to update the resources of one of its projects: several deposits with similar geometrical, geological and spatial characteristics. A few month’s work was required to define, test and validate the routine on one deposit. Another week was enough to run the routine on the other deposits and get the expected resource estimates. In addition to the considerable time the company’s resource team saved, they also gained insight from the batch file processes that mirrored the expertise of Geovariances’ consultants. The quick model update in the subsequent phases of exploration, or even excavation, is another advantage of this batch system.

The second case study was about the work Geovariances completed for Alcoa S.A. The aim was to rebuild the resource estimation workflows the company set up with the precursor of Isatis.neo, Isatis, into Isatis.neo and make the update routines even easier for the user. The complex original workflow, developed by Alcoa’s resource team, involved ordinary and indicator kriging and geostatistical simulation and resource classification. The batch files were prepared, incorporating Python coding for specific operations not yet available in the software and importing search and variogram parameters from csv files using the Pandas library. In the end, Alcoa had a set of standard batch files that could be used for any deposit, but, at the same time, customised according to its needs.

Datamine adds mining consultancy expertise to portfolio with Snowden buy

IoT, Mining mergers and acquisitions, Mining services, Mining software, , , , , , , , ,

Datamine, a wholly owned subsidiary of Vela Software, has acquired mining consultancy and software business Snowden.

As part of the transaction with Datamine, the Snowden brand will be retained, it said, with the company explaining: “We are dedicated to maintaining consistent high levels of expertise and support that you have come to expect from Snowden.”

Being part of the Datamine group will provide long-term benefits for Snowden, its staff and customers, according to the company. “We will have the opportunity to strengthen and grow our business by leveraging resources including an office network across 20 countries, and deep software expertise.”

Tarrant Elkington, Global Manager, Snowden, said: “Snowden has a proud 33-year history, evolving from a geological consulting company to a diversified advisory consulting, software and training business. This acquisition marks the next step on our growth journey.

“The software expertise and global footprint of Datamine offers tremendous opportunities for the growth of our business and to improve the experience of our clients. For example, we will now be able to offer in-country support to our supervisor clients in South America. And we can easily and cost-effectively expand our consulting business to other countries.

“This is a great day for our business, and our people, and we look forward to exploring the synergies that Datamine offer.”

John Bailey, Executive General Manager at Datamine, said: “We are excited to acquire the Snowden business which aligns closely with our existing offering to the mining industry. Snowden has a strong, expert brand with a wealth of experience and has developed industry-leading products that complement Datamine’s software portfolio.”

Snowden refers to Datamine as the world’s leading provider of technology to seamlessly plan and manage mining operations.

“With operations in 20 countries, Datamine provides solutions spanning exploration, resource modelling, mine planning, operations, logistics and marketing to over 6,000 companies worldwide,” Snowden said.

Supervisor is a complementary solution to Datamine’s existing resource estimation suite, offering a simple intuitive interface and workflow, advanced local and global estimation optimisation functionality and compatibility with all major mine planning software packages.

Reconcilor provides a robust system to identify differences between grade and tonnage estimates, plans and actual mine production. The Reconcilor solution is highly complementary to Datamine’s inventory tracking and metal balancing solutions, with several customers already using the combined systems.

Seequent adds geotechnical analysis software to growing portfolio

IoT, Mine surveying, Mineral exploration, Mining mergers and acquisitions, Mining services, Mining software, , , , , , ,

Seequent has announced the acquisition of GEOSLOPE, a Canada-based company famed for its integrated, geotechnical analysis software.

The New Zealand-headquartered leader in the development of geoscience analysis, modelling, and collaborative technologies says the addition of GEOSLOPE will offer additional innovative geoscience technology solutions to its customers.

Seequent has been busy on the business development front in the past year, announcing, in November, that it was to merge with Geosoft and, in July, saying it was starting a partnership with Minalytix.

GEOSLOPE is known by geotechnical engineers who use the GeoStudio suite for design, analysis, and decision making. This suite includes products for modelling slope stability, deformation, heat transfer and groundwater flow in soil and rock. The products are used in over 100 countries for analysing infrastructure projects including dams and levees, reinforced walls and slopes, open-pit mines, and transportation, according to Seequent.

Shaun Maloney, Chief Executive of Seequent, says: “We welcome the GEOSLOPE team to the Seequent family. Together, we are better equipped to deliver on our commitment to help mitigate and solve some of the world’s major civil, environmental and energy challenges.”

GEOSLOPE’S President, Paul Grunau, said the company had, over the years, invested in the long-term growth of the company to develop a set of “world-class solutions” for geotechnical engineers.

He added: “Joining Seequent presents the opportunity for greater integration of geotechnical analysis into the overall engineering and design workflow, thereby enabling our customers to more effectively analyse their problems and deliver better outcomes.”

The GEOSLOPE team will continue to be led by Paul Grunau and will maintain its presence in Calgary, Canada, Seequent said.

Seequent says its software is used on large-scale projects globally, including road and rail tunnel construction, groundwater detection and management, geothermal exploration, subsea infrastructure mapping, resource evaluation and subterranean storage of spent nuclear fuel.

Micromine modelling boosts Piedmont lithium project resource base

Energy minerals, Mineral exploration, Mineral project development, Mining services, , , , , ,

Piedmont Lithium has become the latest US-focused exploration company to use Micromine modelling to refine its mineral resource estimate – reporting a 47% increase in the process.

The company is on track to own the US’ largest spodumene orebody, located in the Carolina Tin-Spodumene Belt, in North Carolina, after increasing the mineral resource estimate to 27.9 Mt grading 1.11% Li2O, with further drilling to come, MICROMINE said.

The Piedmont lithium project is located along trend to the Hallman Beam and Kings Mountain mines, historically providing most of the western world’s lithium from the 1950s through the 1980s.

A scoping study on the project envisaged production of 22,700 t/y of lithium hydroxide over an initial 13-year mine life. This would involve a staged development to minimise up-front capital requirements and equity dilution, with stage 1 coming in at $109 million for the mine/concentrator and by-product circuits. Stage 2, for the chemical plant, would be funded largely by internal cash flow, the company said.

An estimated 74% of the mineral resource is located within 100 m of surface, while some 97% of the resource lies within 150 m of surface, according to MICROMINE. To date, drilling on the project’s 1,004 acre (406 ha) core property consists of 326 holes totaling 51,047 m, with the mineral resource estimate using all 326 holes. In general, drill spacing has ranged between 40 – 80 m, according to Piedmont.

Wireframe models of some 95 pegmatite dykes, a diabase dyke and one fault were created in Micromine by joining polygon interpretations made on cross sections and level plans spaced at 40 m. Weathering profiles, representing the base of saprolite and overburden, were modelled based on drill hole geological logging and a topographic digital terrain model was derived from a 2003 survey, MICROMINE said.

Micromine is an exploration and mine design solution offering integrated tools for modelling, estimation, design, optimisation and scheduling. It provides users with an in-depth understanding of their projects, so prospective regions can be targeted more accurately, increasing the chance of success, MICROMINE says.

The latest version of MICROMINE’s exploration and mine design solution, Micromine 2018, comprises 10 modules. “As a scalable and flexible solution, Micromine 2018 provides you with the flexibility to choose the functionality you need when you need it. Additionally, the application’s new 64-bit support means that you can work with more data than ever before,” the company said.

Micromine’s wireframing module enables very accurate models to be created that can be further analysed and interpreted to produce a precise estimation that aligns with industry codes of practice and standards, the company said.

Piedmont Lithium expects to complete its prefeasibility level metallurgical test work program, followed by a scoping study update, this month, MICROMINE reported.

Seequent delivers major releases for mining solutions

IoT, Mineral exploration, Mining services, Mining software, , , , , , , , , , , ,

Seequent says it has launched new releases for its mining solutions Leapfrog® Geo, resource modelling solution Leapfrog® Edge, model management solution Seequent Central and View.

Seequent’s General Manager – Mining and Minerals, Nick Fogarty, said: “Projects are becoming increasingly complex, and organisations are generating a huge amount of geological data to inform important investment and environmental decisions. Seequent’s mining solutions work in harmony to enable an unprecedented level of productivity and collaboration, giving customers’ insights that improve decision making and further reduce risk.”

Seequent Central’s importance as the nexus for managing geological data, across multiple projects and locations, has been recognised with major release upgrades including the Central Data Room bringing all data into one place, the company said.

Leapfrog® Geo 4.5, meanwhile, includes performance improvements designed to smooth day-to-day workflows for users, including informed uploading, simplified editing and exporting, redesigned file structures and intuitive polar nets, Seequent said.

Leapfrog Geo Product Manager, Byron Taylor, said: “Leapfrog Geo is our flagship solution well known for its stability and usability. For this release, we’ve delivered on many minor user requests that collectively add up to major enhancements. Leapfrog Geo is now well positioned to take on board some even more ground-breaking innovations that we have planned for the future.”

A major addition to Leapfrog Edge is the provision of a new Variable Orientation tool (pictured), which locally re-orientates the search and variogram, and features visual search ellipse validation, easy setup and updates, Sequent said.

“We’ve seen rapid industry uptake of Leapfrog Edge since its launch 18 months ago. This release further enhances Edge’s capability to deliver rapid dynamic resource estimates,” Mike Stewart, Seequent’s Technical Domain Expert, said.

Major advances for Seequent Central include a new intuitive web interface and Central Data Room that brings all critical project data into one place, according to the company. This allows teams to work together from a “single source of truth”, Seequent said. The Central Data Room allows data from a variety of sources to be uploaded, downloaded and version controlled within the Central Portal.

Seequent’s Central Product Manager, Peter Joynt, said: “Seequent Central is the best way to transfer Leapfrog projects to and from remote sites – its version control for geoscience data is a game changer. Before Central, companies were faced with the basic issue of trying to locate the latest version of a model. To further streamline projects, other types of data frequently used with Central can now be built into dynamic workflows, even if the outputs were generated in packages other than Leapfrog.”

View’s latest updates give teams, stakeholders and decision-makers more time-saving ways to collaborate and interact with their data in a browser to uncover insights, according to the company. The online tool allows all data and communications to be saved to the cloud.

“Users can more easily build a story, capturing an aspect of their 3D geological model and use the embedded note function to ask questions and allow stakeholders to give feedback all in one place,” Amy Gerber, View Product Manager for Seequent, said.