•    Understanding how it supports production 
•    Looking at ways to keep its people and communities safe
•    Monitoring ESG impacts
 

•    Discussion challenges of deploying the technology.
•    Looking at safety, data sharing, and ethical concerns regarding AI and data.
•    Debating where AI works and where it doesn’t.
•    Exploring alternative solutions such as machine learning, optimisation, and simulation.
•    Unravelling the best way to use data and how it can add value.
•    Data interoperability: Production data vs Data points generated by OEMs – Best practices and how to move forward.

•    Understanding how Monte Carlo simulations and Large Language Models can be employed to assess AI vendor capabilities, focusing on aligning with Roy Hill's strategic goals.
•    Exploring the comprehensive vendor evaluation framework is developed, combining survey results with independent LLM assessments for multi-dimensional analysis.
•    Looking at the Multi-Persona LLM framework is tested for problem-solving capabilities, showing improvement with prompt engineering and curated personas.
•    Vendor feedback and enhanced evaluation metrics are incorporated to mitigate information asymmetry and confirmation bias.
•    Debating how future research will refine methodologies, explore knowledge graphs, and develop a diverse library of personas to enhance AI capability assessments.
 

•    Understanding how it can be used in mining.
•    Looking at what processes can be automated.
•    Looking at real-life case studies. 

•    Tailored ML Solutions in Mining and Exploration: In the mining and exploration sectors, custom machine learning solutions are often necessary to extract meaningful value from geoscience data.
•    Challenges and Solutions: Developing effective, bespoke machine learning models to solve critical business problems in geoscience requires deep domain expertise. However, expertise alone is insufficient. Without a clear path to production, these models remain mere experiments rather than functional solutions.
•    From Proof of Concept to Operational Solutions: Showcasing recent examples of transforming proof-of-concept projects into fully operational solutions by leveraging composable cloud computing architectures.

•    Exploring the power of traditional BI tools to uncover performance insights  
•    Uncover actionable insights with AI-powered visuals  
•    Unleashing the future of data analysis with GenAI 

•    Data Infrastructure: Companies have invested in data systems (sensors, control systems) but struggle to convert data into real value.
•    Current State: Most rely on dashboards for visualization, not for improving performance.
•    AI for Optimisation: Use cases show AI can improve operations, optimize yields, grades, energy, and productivity.
•    Environmental Benefits: AI-driven optimization often leads to reduced environmental impacts.
•    Trust is Crucial: Success depends on operators trusting AI tools for effective process control.
•    Future of Mining: Industry at a pivotal point; AI solutions can prescribe actions, deliver results, and build trust with the workforce.
•    Call to Action: Now is the time to invest in AI that goes beyond data display to actionable insights and real-world results.
 

•    Understand how digitization disrupts and shapes the future of the mining sector, as well as explore the possibilities of emerging IoT technologies.  Learn about the possibilities of IoT technologies and their implications. 
•    Explore how digitization can be achieved on complex mining and industrial sites through the use of basic prerequisite – lights.
•    Examine a series of case studies, explore the collected data and analyze its effects on the operation of the sites. 
 

Each round table is given a different topic, and attendees select the round table they want to participate in. Round table leaders spend the first 15 minutes meeting the delegates and providing a case study/lessons learned log/industry update. This is followed by a 30-minute discussion moderated by the roundtable leader with the group, during which they can give feedback and ask questions. The final 10 –15 minutes are dedicated to agreeing on 3 -5 industry recommendations. These recommendations will be made available to attendees in the post-event report. 

1. Data, Data, Data: Developing data analytics capabilities to boost mining productivity. 
   Ed Lewis, Unearthed
2. Deploying digital technologies in greenfield projects. Discussing challenges and opportunities.
   Previn Pillay, Pyromin Consulting 
3. Dynamic simulation models of the mining supply chain 
   Jacob Morhall, Theia Simulation
4. Digital Twins: Integrating and managing large-scale data from various sources.
   Kevin Kidd, WGA

•    Fast tracking mining approvals
•    WA: Leaders in automation

•    Improving interoperability between assets and increasing technology integration.  
•    Harnessing the power of mine site operational data to improve mining operations.
•    Discussing the fully automated mine – Where are we, and looking at the future.
•    Collision avoidance systems: Implementation challenges and discussing next steps.

•    Exploring future innovation and research in mining robotics.
•    Highlighting workforce efficiency and sustainability.
•    Debating how robotics can be used in remote operations and monitoring.
•    Looking at how robotics can optimise energy consumption and reduce the carbon footprint of mining operations. 

This session highlights technology innovators and their current projects.   

1. Using Digital Innovation to Improve the Quality and Efficiency of Engineering Solutions.
   Jess Page, Wallbridge Gilbert Aztec

Technology and operational efficiency could reduce emissions by 20-30%.
•    Discussing the journey to the energy transition in mining.
•    Exploring the tech perspective and its role in the energy transition. 
•    Debating how we can reduce emissions while keeping up productivity. 
•    Where to invest in R&D to reduce emissions.
•    Discovering what technologies are available and which ones work.
•    Looking at best practices and lessons learned.
•    Evaluating the importance of strategic partnerships in the energy transition.
•    Data and emissions reporting and tracking.

•    With the rise of AI, especially Generative AI, many organsations are exploring ways to better leverage their data to improve operations and foster innovation. 
•    This session will share insights gained from collaborating with local resources companies and discuss how connected and contextualised data can support these efforts. 
•    Showcasing practical examples of technology application.

Each round table is given a different topic, and attendees select the round table they want to participate in. Round table leaders spend the first 15 minutes meeting the delegates and providing a case study/lessons learned log/industry update. This is followed by a 30-minute discussion moderated by the roundtable leader with the group, during which they can give feedback and ask questions. The final 10 –15 minutes are dedicated to agreeing on 3 -5 industry recommendations. These recommendations will be made available to attendees in the post-event report. 

1. Ways to encourage and foster innovation in artificial intelligence. 
   Tim Sondalini, WA Data Science Innovation Hub
2. AI that delivers: Swapping notes on AI successful implementation and scale up  . 
   Katya Vladislavleva, Director at Partners in Performance