It seems like every week, we hear about a new data breach during which some company has been hacked and their data stolen. Breaches like this result in severe costs to both reputation and the bottom line.  It seems clear that companies should do everything in their power to prevent their data from falling into the wrong hands.

And yet, companies should be sharing their data more, not less. Justin will discuss the surprising reasons why.

The incredible benefits of Machine Learning and modern MLOps across a plethora of non-mining industries are already evident. However, astute mining industry leaders and investors want an accelerated pathway to tangibly harness these benefits to best utilise their data, in turn achieving optimal performance at their mining operations.

With new unprecedented precision in measurement and large-scale data collection possible today, Mining Leaders want to move beyond stale PoCs to data impact at scale.

In this energetic presentation, Coert will cover;

• The state of ML across the mining value chain, focusing on critical areas to outline how miners can uncover the gold hidden in the mountain of data.

How to navigate the operational uncertainty that starts in-ground and permeates the mining value chain to the customer, which requires a vastly different approach to ML than most other industries where their inputs are stable and known.

In early 2019, Roy Hill started using machine learning to forecast our process plant yield / recovery. This solution started off as a simple MVP (minimum viable product) and has grown into a MLOps implementation - This session is about sharing this journey and the learnings from this journey.

• Introducing to BHP’s current way of working
• Exploring a deep dive into an application of reinforcement learning in the scheduling of vessels
• Looking at further examples of machine learning within BHP

• Organisational dynamics of large data projects
• Human factors and the bridge between data science and business
• Data integration at scale: technical and project experiences

• Value of Information – Value of having the right information at the right time
• Orebody Knowledge (OBK) and the role of geoscientific data across the mining lifecycle
• Unique requirements and challenges for successful application of ML to OBK
• OBK in Action – Using high-density spatial data with ML to increase efficiencies in mining operations

• Machine Learning models outperforming rules-based analysis to predict sample outcomes
• Analysing the change management and operational involvement required for successful implementation

Exponential growth in big data and recent breakthroughs in deep learning continue to drive the widespread adoption of machine learning in industry. In this presentation, the impact of deep learning in the process industries will be reviewed, focusing on sensor data analytics and process monitoring.

This will include examples of the monitoring of bulk particulates on conveyor belts, the underflow of hydrocyclones, froth image analysis and signal processing in general, and a brief look at the emerging application in modelling and control.

-               Data-driven decisions in geoscience may be achieved through a machine augmented and human-driven approach

-               Machine learning can be used to produce efficient, consistent and repeatable outcomes, but its deployment in industry practice is challenging

-               Deployable machine learning (or data science in general) needs to address transparency, their seamless integration into human interpretation workflow, and generating solutions that are acceptable by domain experts

-               Machine learning is used not only used for structured data but also unstructured data towards building AI for geological knowledge discovery

Whether it’s automated haulage, decarbonisation, robotics, remote work or machine learning, we want to connect the best and most creative minds to the opportunities and challenges we face as an industry, and change the very nature of the way we work.

We believe that the ingenuity and energy that exists in the METS sector unlocks potential for companies like us, our peers and partners, and ultimately the nation. As an industry, we must continue to work on the new ideas and solutions to make what we do better every day.

Over the past two years, we've been working together with the METS sector and with the women and men on the front line of our operations to improve safety outcomes across our mobile maintenance teams - developing Dash Tools (dash.bhp.com).

In this session, we'll share our journey and lessons learnt from our work on elimination of live work with Dash Tools - putting sensors in harm's way, not people - and how they can be applied to Machine Learning challenges.

• Exploring a Data Value Framework that shows how to design data investments focused on value
• How a critical learning approach is not going to achieve the breakthrough results
• Ensuring you do not neglect complex data investments to the detriment of your investments and value
• Managing your data investment portfolio and understanding the entire data solution lifecycle

As technology advances, data can provide opportunities to solve problems in various areas, including accelerated research, increased transparency, and the identification of novel solutions to problems. Unfortunately, the appropriate data are not always readily available. The Global Mining Guidelines Group (GMG) has produced a Guideline for Sharing Open Data Sets in Mining to assist in this area. The purpose of this guideline is to provide best practices for data sharing for those within the mining industry based on existing initiatives so they can benefit from open data.

Realising value through data is hard and outcomes can be inconsistent. The technology is getting better but process and capability are still developing. A successful data workflow, one that is embedded in the business, invokes all roles to consistently realise value. It follows then, that all roles need to be data capable and demonstrate an understanding of the data workflow. Having an industry framework or shared way to build data capability in support of all roles across an organisation is therefore critical.

Machine learning and cloud computing hold the immense promise of adding value to mining operations. A new domain modelling solution delivers significant improvements in processing speed, ease of setup and use, alongside the ability to use all your data and in a secure manner. This paper will outline how access to cutting-edge machine learning has never been easier and how it delivers confidence in domaining and modelling decisions.

• Energy: ethics in reducing fuel consumption.
• Operations & Maintenance: ethics in operations and predictive maintenance.
• Safety: ethics in using surveillance video (CCTV) for safety.
• Data: ethics in a mixed industrial data world.

Brice Gower  - CEO and Co-Founder, Augment Technologies:

TOPIC: Ore Movement Policy; meta-reinforcement learning, heuristics, and a physics engine.

In open-cut mining, blasting is used to move hundreds of thousands of cubic meters of rock every day, the fast pace and sheer volume of ore that needs to be moved makes it incredibly difficult to put the time and effort into accurately understanding how the forces of blasting reshape the insitu orebody; but this is extremely important as dilution and mixing can cause significant loss of the revenue-generating ore. Because of the complexity of the problem, acquiring supervised answers for how the ore moved to is not practical, and hence Augment went down the path of building a custom simulated environment to augment the data that was practical to measure and the resulting Reinforcement Learning policy is now delivering accurate models of how the chaotic blasting forces mix the different ore types together, all computed in under 5 minutes after the blast based on data that is practical to measure. 

Sanabel Abu Jwade - Graduate Software Engineer, Rio Tinto

TOPIC: Sign Recognition in Underground Mines - PoC. 

In the data-driven world that we live in today, mines strive to collect quality data to make informed optimization decisions in an increasingly competitive world. One example is the ability to optimize traffic flow in underground mines by collecting truck location data.

Typically, collecting truck locations in underground mines with the absence of GPS and Wifi is a challenge. Some mines rely on a manual process where the drivers log the location based on signs on the wall as they pass them. While manual logging provides useful data, it’s inefficient, distracting, and most of the time, not done promptly.

To automate the process of logging truck locations, we investigated the viability of the use of computer vision and machine learning to automatically locate, identify and log wall signs in underground mines. The project considered environmental challenges in underground mines and integrated noise into the test data. The test data included signs with blur, occlusion, uneven lighting, and perspective transformations.

This work was done as a group project at UWA to provide a proof of concept for a Perth-based company specialised in developing mining software. The project investigated and compared two approaches utilizing a range of computer vision and machine learning techniques. The project recommended an approach that was able to identify signs correctly 100% of the time when at least 60% of the sign is visible to the camera. Moreover, the recommended approach was demonstrated to be robust against environmental noise and occlusions present in underground mines.

Russell Menezes - CEO, RadiXplore:

TOPIC: Use Machine Learning to Find Unrecognised Mineral Deposits within Legacy Text Reports.

70% of data in mining exploration is unstructured and exists in the form of PDFs, images and text files. Currently, only 2% of companies use this data and those that do barely scrape the surface, because it is time consuming and expensive to search through. For Western Australia alone, there are over 20 million pages of text-based information within the WAMEX exploration reports. This data is extremely valuable as it contains the subject matter expertise of over ten thousand individuals who contributed to them over the last 150 years.

How can we read and understand information from these reports like a geologist would, but at the same time go through all the 20 million pages accurately and quickly?

Computers can perform tasks millions of times faster than humans but are not smart enough to understand geology on its own. Can we teach the computer enough geology so that it could help us read through unstructured data (including scanned and handwritten reports) and find unrecognised deposits within it?

Introducing Natural Language Processing (NLP) - the technology used to aid computers to understand the human language. The ultimate objective of NLP is to read, decipher, understand, and make sense of the human languages in a manner that is valuable.

In this talk we will introduce some NLP techniques and use it to derive insights from a scanned, handwritten image of a document. We will then explore some real world use cases where we apply these techniques at scale to see how explorers can use NLP to find unrecognised mineral deposits within the Western Australian WAMEX database which contains over 1 billion words.

Ankita Singh, Graduate Data Scientist, PACE Analytics | Rio Tinto

Through the lens of machine learning and texture analysis: What’s inside my Tiramisu?

We all love a delicious Tiramisu! It has those rich, creamy layers alternating with biscuits dipped in coffee. The earth’s subsurface resembles the structure of a Tiramisu from which the energy and resources sector extracts vital minerals, metals, and gas. Specifically, we drill and extract rock cores to accurately characterize, develop, and estimate reserves in the energy industry. These rocks are then imaged using X-rays with a vision to understand what lies beneath us. The x-ray images depict rock features as variations in the grey-level intensities, then transformed into segmented counterparts, i.e., labelled images. However, their characterization using labelled images remains a challenge. These challenges include (1) lack of structural information of rock geometry while creating labelled images and (2) operator-based segmentation techniques which cause rock descriptors to be biased. 
 
We address the first challenge using an unsupervised machine learning algorithm. This technique is applied to account for geometrical and structural differences in the rock features, especially pores and fractures, which are key for gas flow in the earth’s subsurface. The second challenge is addressed using a texture analysis technique. This method can be directly applied to x-ray images without the need for labelled images which are affected by user bias. 
 
While these techniques were first developed and used in the 1970s, they provide remarkable insights and approaches to alleviate long-standing challenges in the energy industry. Can we use the same techniques in the mining and metals sector to better understand our resources?