Wednesday, November 10, 2021
9:00 AM
9:10 AM
Justin Strharsky

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.

9:40 AM
Dr. Rachna Dhand
10:10 AM
10:40 AM
Coert du Plessis

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.

11:10 AM
Mitin Hirani

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.

11:40 AM
12:40 PM
Alex Jenkins
  • Organisational dynamics of large data projects
  • Human factors and the bridge between data science and business
  • Data integration at scale: technical and project experiences
1:10 PM
Fred Blaine
  • 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
1:40 PM
Chelsea Gray
  • Machine Learning models outperforming rules-based analysis to predict sample outcomes
  • Analysing the change management and operational involvement required for successful implementation
2:10 PM
2:40 PM
Chris Aldrich

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.

3:10 PM
Eun-Jung Holden

-               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

3:40 PM
Alex Bertram

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.

4:10 PM
Thursday, November 11, 2021
9:00 AM
9:10 AM
Kylah Morrison
9:40 AM
Edin Mustajbegovic
  • 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
10:10 AM
10:40 AM
Rob Johnston

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.

11:10 AM
Tamryn Barker

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.

11:40 AM
Steve Sullivan

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.

12:10 PM
1:00 PM
Nadia Rom
1:40 PM
Holly Bridgwater
2:20 PM
Greg Stagbouer
3:00 PM