Tag Archives: drill core analysis

Minalyze and Colorado School of Mines team up to tackle advanced drill core analysis

Researchers at the Colorado School of Mines are teaming up with Minalyze AB to build an advanced geosciences research laboratory for non-destructive compositional analysis of drill core, the Sweden-based company says.

“This new laboratory establishes the Colorado School of Mines as a global leader in this emerging field with important applications in the development of Earth resources such as the critical minerals needed in the manufacturing of clean energy technologies,” Thomas Monecke, Director of the Center for Advanced Subsurface Earth Resource Models (CASERM) at the Colorado School of Mines, says.

“Minalyze’s choice of CASERM as a research partner is a testament to the calibre of our faculty and students we have, and the establishment of the new research facility will help our research team to advance solutions for the mining sector and contribute to our fundamental understanding of the geological processes resulting in the concentration of metals in the Earth’s crust.”

The new laboratory will support research conducted within CASERM, a collaborative research venture between the Colorado School of Mines and Virginia Tech supported by a consortium of mining companies and federal agencies aiming to transform the way geoscience data is used across the mining value chain.

Minalyze’s X-ray Fluorescence-backed CS scanner has been used throughout the mining sector for drill core analysis and, more recently, is being used in artificial intelligence-backed projects.

In addition to ore deposit research, the new core scanning laboratory will offer unparalleled opportunities for undergraduate and graduate student education, according to Minalyze.

Annelie Lundström, Chief Executive Officer of Minalyze AB, added: “We are excited to collaborate with the CASERM research team and look forward to helping build a strong future in Earth resource research at the Colorado School of Mines and Virginia Tech.”

Initial research using the new analytical capabilities will focus on the identification of elemental enrichment and depletion patterns around ore deposits that were caused by the interaction of ore-forming fluids with the host rocks during deposit formation, Minalyze explained. Identification of these vectors to ores requires the use of machine-learning techniques that are currently developed and tested by the CASERM research team.

In addition to data science, the research team is planning on conducting method developments involving the integration of additional sensors in the core scanner.

Seequent adds to cloud-based geoscience software base with Imago acquisition

Bentley Systems’ Seequent business unit has acquired Imago Inc, a developer of cloud-based software for the capture and management of geoscientific imagery.

The acquisition, which comes only a month after announcing the purchase of Aarhus GeoSoftware, will expand Seequent’s technology solutions portfolio while boosting cloud capabilities to help geoscientists and engineers solve earth, environment and energy challenges, it said.

Imago’s cloud-based platform enables the capture, cataloguing and review of drilling core and chip images from any source, to support every aspect of the geological process from exploration to grade control. Continued development of Imago’s machine learning will lead to a step function in the interpretation of geological data, according to Seequent.

Seequent said: “Mining companies around the world apply Imago’s solution in conjunction with geology data management and modelling tools to enable teams to make more confident, profitable decisions using instantly available, high-quality images. Seequent already integrates its Leapfrog, Oasis montaj, Target, and Minalytix MX Deposit with Imago’s solution, making it easy for geologists, engineers and other stakeholders to extract knowledge and learn from geoscientific imagery. The goal is to unlock significant potential for mining and other industries, transforming image data into meaningful insights for geological activities.”

Imago establishes a consistent process for capturing high-quality images, which integrate with existing workflows and allow the application of machine learning

Graham Grant, CEO of Seequent, said: “It’s an exciting step to welcome the Imago team on board to help advance Seequent’s progression into the cloud. We’re continually exploring ways to provide new technologies and solutions to solve workflow challenges, improve operational efficiency and deliver greater value for our users who are working to solve some of the world’s major civil, environmental, and energy challenges. This acquisition demonstrates Seequent’s continued growth and our commitment to make a positive contribution to the industries we serve globally.”

Imago’s Co-Founder, Federico Arboleda, said: “As a small team in Phoenix and Perth, we’re excited to join forces with Seequent, as this will now allow us to substantially scale Imago’s solutions in mining and other markets. We founded Imago to help mining companies manage the high volume and size of geological images and unlock the great value in this geoscience imagery. Image data is an increasingly important source of data across the geosciences – and can come from potentially any source, including core photos, hyperspectral, aerial photos, drones, and handheld devices. It will become even more important to transform image data into knowledge as automation needs increase.”

Swick Mining working on drilling and technology business demerger

Swick Mining Services says it is working towards a demerger of its drilling and mineral technology businesses following a strategic review.

The announcement came at the same time as the ASX-listed METS firm revealed Drilling Business revenue and EBITDA results of A$149.6 million ($111 million) and A$24.6 million, respectively, for its 2020 financial year. A 9% increase in underground metres drilled saw the company beat its 2019 financial revenue total of A$142.9 million, while the impacts of COVID-19 and ramp-up costs at the Pogo mine contract (Northern Star Resources) saw EBITDA drop from A$28.2 million in the previous financial year.

During this period, the company’s deep exploration division launched new DeepEX rigs, which Swick says are the world’s most powerful underground mobile rigs with capacities to drill exploration holes up to 3,000 m of NQ2 core. Two DeepEX hybrid rigs are currently deployed at client sites, it said.

And the company successfully completed on-site trials of its Orexplore technology, the major technology underpinning its mineral technology business.

These site-based trials were undertaken at Sandfire Resources’ DeGrussa copper-gold mine, in Australia, for a three-month pilot project and at Sweden-based mining and smelting company Boliden for a five-month paid pilot project.

“The first trial at the DeGrussa mine resulted in approximately 9,000 m of core scanned in total, generating 20 TB of 3D data – the largest and most continuous dataset of its kind in the world for a single mine site,” Swick said. “With the trial complete, Orexplore has engaged two world-class subject matter experts to assist Sandfire and other potential clients understand the benefits of a comprehensive Orexplore data set.”

Earlier this month, Swick said Orexplore had been awarded its first in-field commercial agreement with St Barbara Ltd at the Gwalia mine in Leonora, Western Australia.

Despite these wins over the last year-and-a-bit, the company said a strategic review had recommended the company carried out a demerger of the Drilling Business and the Mineral Technology Business.

This could be tied to the fact that, at a group level, Swick reported a net loss after tax of A$6 million in the 2020 financial year, which, it said, reflected the lower Drilling Business earnings and ongoing investment in the company’s Mineral Technology Business, Orexplore.

Swick Managing Director, Kent Swick, said: “Financial year 2020 has presented a unique and challenging set of circumstances with the onset of the COVID-19 pandemic. The business has quickly adapted during this difficult period, ensuring we maintained continuity of operations and protected our people on site both internationally and locally.

“I am pleased with the ability of our Drilling Business to deliver robust earnings in this environment and secure new work with existing clients, including our two largest contracts for Northern Star and BHP, which provide a strong platform for the business as we enter the 2021 financial year.

“Meanwhile, our efforts in the Mineral Technology Business are starting to show value, with successful site-based, paid trials in the year for our Orexplore technology and the award of our first ever in-field commercial agreement earlier this month.

“We have a clear strategy for these two businesses and are now progressing with the outcome of our strategic review to demerge the Drilling Business and the Mineral Technology Business to allow them to pursue their respective strategies and ultimately deliver the greatest value to Swick shareholders.

“Meanwhile, Swick is in a strong financial position, with gearing excluding AASB16 lease liabilities reduced to A10.6 per cent in the year. Swick has A$12.7 million cash and A$18.5 million in undrawn facilities, providing the liquidity that has enabled us to win and deliver on new work, invest in new technologies including DeepEX and Orexplore, and continue providing value for shareholders in these uncertain times through dividends and share buybacks.”

Swick signs BHP, MATSA drilling contracts and inks first Orexplore commercial pact

Swick Mining Services Limited has secured new drilling contracts with BHP’s Olympic Dam mine and MATSA’s copper operation in Spain at the same time as confirming the first commercial agreement for its Mineral Technology Business.

In what will be Swick’s second largest project, the company has been awarded a five-year contract to provide underground drilling services at Olympic Dam mine in South Australia.

Swick has been working with up to five rigs at Olympic Dam since 2017 when an initial trial of its underground mobile diamond drills commenced.

The new contract will see Swick increase its rig volume at site, with the first year’s scope requiring an initial eight rigs, with five to be added to the three currently operating at site. Of the five additional rigs, three are at site already and the remainder will be mobilised from Swick’s existing fleet, according to Swick.

Swick has also been awarded a five-year contract from Minas de Aguas Teñidas SAU (MATSA) at its copper operations in Spain, where two rigs are currently deployed.

These projects, combined with Swick’s existing work in hand, has expanded Swick’s order book to A$363 million ($260 million), it said.

Swick’s Mineral Technology Business, Orexplore, has also been awarded its first infield commercial agreement, the company said.

Under the agreement with St Barbara Ltd, some 1,500 m of core will be scanned per month over a six-month period at the Gwalia mine in Leonora, Western Australia.

Swick will conduct technical assessment over a number of potential benefits of the detailed core analysis and high volume of quality data generated by the GeoCore X10 instrument, it said. The agreement has a value of around A$700,000 over the six-month period.

“Orexplore will be working with world-class subject matter experts to ensure maximum value for the client is derived from the data obtained to develop a compelling justification for ongoing services beyond the initial six-month period,” it said.

Swick expects a formal contract to be signed in the coming weeks and mobilisation of GeoCore X10 instruments housed in a custom-built mobile laboratory to site in September 2020.

The GeoCore X10 analyses the element concentrations and minerals contained in a drill core, as well as providing a visualisation of the rock’s internal structure in 3D. This speeds up the chemical laboratory analysis process, enabling miners to accelerate their own decision making.

Swick Managing Director, Kent Swick, said the company was delighted to be awarded a long-term contract with BHP at Olympic Dam.

“Credit goes to our operational team who have delivered outstanding safety performance, and high quality and productive drilling that enabled Swick to secure this long term, high volume work,” he said.

“In addition, securing a five-year agreement with a large copper miner MATSA, in Spain, adds to our ongoing work with Somincor in Portugal along the historic Iberian Pyrite Belt. Our local workforce in that region is highly skilled and they are to be commended for converting a trial into a long-term contract in Spain.”

He concluded: “In the Mineral Technology Business, it is very exciting that we have taken a significant step forward with the award of Orexplore’s first infield commercial agreement. We look forward to ensuring the value is extracted from this rich 3D data set and I am confident we can add significant long-term value to the Gwalia mine and the wider brownfield market.”

Datarock machine learning drill core analysis tool hits major milestone

DiUS and Solve Geosolutions have leveraged PyTorch-based image analysis techniques to help automate the analysis of drill core imagery and provide greater insight that can be used to influence decision making on mine sites.

Mine sites often produce between 100 and 1,000 m of drill core per day, generating hundreds of images a week at a single drill site, according to PyTorch, an open source machine learning platform.

Historically, these images have been kept as a record of the job and a resource for geologists to refer to, rather than being used as a quantitative dataset that adds value to a mining operation.

Tapping into this rarely used data source of drill core imagery, DiUS – an Australia-based technology services organisation with a strong focus on machine learning and deep learning image segmentation analysis – joined forces with Solve Geosolutions – a mining-focused data science and machine learning consultancy – to build a machine learning-powered, cloud-based platform to automate the analysis of this drill core imagery using image segmentation technology.

Together, DiUS and Solve Geosolutions worked on applying a range of PyTorch-based image analysis techniques, including image classification, object detection and both semantic and instance segmentation, to a range of geological problems.

In particular, the team wanted to understand how different models performed in terms of training and inference speed, training requirements and overall accuracy of prediction to inform how they could be deployed in a production environment.

One model they used extensively is Mask R-CNN.

“This model can be applied to a range of segmentation tasks, however it can also demand large training datasets that are sometimes not available,” PyTorch said. “To support this, the team developed novel ways to increase the initial, often sparse training dataset through data augmentation techniques such as rotation, flipping, contrast, saturation, lighting and cropping.”

Following the initial discovery period, the team set about combining techniques to create an image processing workflow for drill core imagery. This involved developing a series of deep learning models that could process raw images into a structured format and segment the important geological information, according to PyTorch.

Their first productionised process was a metric referred to as RQD, otherwise known as rock quality designation. “RQD is a difficult and monotonous dataset to collect manually,” PyTorch said. “It’s also well suited to automation, and of high value to a mining operation. RQD is used by engineers to understand the strength of a rock and is used in the design and engineering of a mine.”

With the release of Detectron2 – a PyTorch-based computer vision library released by Facebook in October 2019 – the team made the decision to switch from the previous model implementation on TensorFlow to the next-generation platform to help improve instance segmentation tasks, PyTorch said.

The team found Detectron2 to be four times faster in training the models (using GPUs) and three times faster in inference (using CPUs) than the previous model implementation, PyTorch said.

Building the models on PyTorch-based frameworks meant the team was able to reduce valuable training time across the board. This increased the number of experiments and, as a consequence, improved model accuracy on an identical dataset. The PyTorch Dynamic Graph also made it much easier for the team to debug and investigate any issues that arose, PyTorch said.

The resultant Datarock platform is a software as a service offering that applies machine learning – image segmentation technologies – to drill core imagery and delivers information about a mineral deposit’s geology at scale, and at a resolution that’s not been previously economically viable, PyTorch says.

Since launching Datarock in 2019, the team has extended the platform to turn drill core imagery into high-quality datasets to support decision making throughout the entire mining cycle.

“The models perform optical character recognition, instance and semantic segmentation, as well as geological statistical analysis on a dataset,” PyTorch said. “This allows a geologist to inspect the model prediction and check for quantity and quality in unmatched datasets.”

Mining and exploration companies can now get consistent geological information from their rock core imagery in a matter of minutes, according to PyTorch.

“This near real-time power is enabling more intelligent decisions to be made further down the mining chain – saving time and money that can be put towards other business-critical projects – and freeing up geologists to do higher value tasks,” PyTorch said.

To date, the Datarock platform has processed more than 1 million metres of drill core images – that’s enough core to cover the distance between Sydney and Melbourne – over 800 km.