MICROMINE applies machine learning to optimise core tray imagery

Members of MICROMINE’s office in Perth, Australia, recently participated in The Newcrest Crowd, an industry-leading, crowdsourcing and partnership platform that challenges innovators around the world to solve specific mining problems through online competitions

Staff reporter
Core tray photo from MICROMINE client with the core outlines generated by the Mask R-CNN

Core tray photo from MICROMINE client with the core outlines generated by the Mask R-CNN

The ‘Get 2 the Core' competition focused on core tray photography and how companies can derive the value in historical core tray imagery. Core tray photography is currently under-utilised due to the arduous process of capturing, processing and analysing core tray photography. With so much rich textural, mineralogical and geotechnical information contained in core tray photography, there is a lot of value in optimising current processes.

Photographs taken on Newcrest sites are mostly standardised, but they have millions of historic core images from tens of thousands of drillholes. As technology evolves, image analysis techniques are becoming more powerful and prevalent within exploration and mining industry. These large image repositories will eventually become rich sources of quantitative data.

‘Get 2 the Core' asked participants to build an algorithm that could determine and map the spatial extents of the core tray and then the individual rows contained within. The successful participant was awarded a prize of A$10,000 (US$7,300), with a separate prize to be awarded for solutions that also solve the problem but do not exactly fit the scoring requirements.

MICROMINE's Wojciech Slabik commented: "The Get 2 the Core was an exciting project to be involved in. We have been working with machine learning techniques to solve mining problems on our Pitram team and we immediately noticed that we could apply these methods also to the problem presented by Newcrest."

Provided to participants was a training dataset of images and completed masking instructions - the ground truth. The test data set consists of images only, for which the participants needed to predict the masking instructions via a CSV file. The solution needed to be able to perform on inconsistent photography where:

  • Images are highly variable in terms resolution, aspect ratio and quality; and
  • Core boxes can be made from different materials (wood, steel, cardboard, plastic);
  • The relative position of the core tray within the image can be variable.

The MICROMINE team applied machine learning skills using the relatively new Mask R-CNN technique.

Wojciech added: "We utilised a technique known as transfer learning, so our Mask R-CNN learned very quickly to deal with the core tray data. Using transfer learning meant that we didn't need thousands of labelled core trays to be able to train the machine. To generate the core bounding box, we then used more traditional edge detection techniques that used the mask from the Mask R-CNN.".

The competition aimed to achieve the result of reducing the man hours required to manually review and analyse core tray photography. Due to the manual mark up, the labels may not be perfectly consistent across the entire dataset, however these labels represent the kind of work required to produce an outcome which is time consuming and labour intensive.

MICROMINE staff have combined expertise along with methodologies, from machine learning to more traditional techniques that can really assist with refining the work that the machine learning algorithm can do. The initial results achieved after only a few hours were remarkable.

Wojciech noted: "The results we got in only few hours were much better than what we have initially expected. Future development will be focused on training the network to generate not just the bit mask outlining the drill core, but also the full bounding box."

The judges were scoring on a combination of two loss functions: an intersection over union (IoU) loss to determine the accuracy of the bounding box predictions, and a negative log likelihood for the multi-class multi-label classification task. The tasks were weighted such that 90% of the score comes from solving the bounding box prediction task.

MICROMINE would like to congratulate to the ‘Get 2 the Core' competition winner and stated that it was great to see so many participants coming up with impressive results using a variety of innovative techniques. The MICROMINE solution will be used to provide this functionality to the users of the Geobank data management solution. The speed and quality of the solution has encouraged MICROMINE to continue with further development using training data sourced from our existing Geobank clients. When integrated into Geobank, core tray images can be transferred into the database and displayed in Geobank drillhole trace along with other downhole data.

The core tray photo conversion will be completed by the machine learning algorithm with minimum effort from the user.

A growing series of reports, each focused on a key discussion point for the mining sector, brought to you by the Mining Magazine Intelligence team.

A growing series of reports, each focused on a key discussion point for the mining sector, brought to you by the Mining Magazine Intelligence team.


Mining Magazine Intelligence Exploration Report 2024 (feat. Opaxe data)

A comprehensive review of exploration trends and technologies, highlighting the best intercepts and discoveries and the latest initial resource estimates.


Mining Magazine Intelligence Future Fleets Report 2024

The report paints a picture of the equipment landscape and includes detailed profiles of mines that are employing these fleets


Mining Magazine Intelligence Digitalisation Report 2023

An in-depth review of operations that use digitalisation technology to drive improvements across all areas of mining production


Mining Magazine Intelligence Automation Report 2023

An in-depth review of operations using autonomous solutions in every region and sector, including analysis of the factors driving investment decisions