BY IAN JONES, 
COMMIT WORKS HEAD OF PRODUCT

As formal mining education pathways shrink, the industry risks losing the expertise that gives operational data meaning. Capturing and transferring practitioner knowledge is now essential to unlocking real value from AI. 

Keeping the theme from part one, have a look at these images. They are both from museums associated to the Nobel Prize. Many of us instinctively correlate the Nobel Prize with peace, but the truth is prizes are awarded across diverse areas of life and study including science, engineering, economics, literature and medicine.  

I believe the images, as I have shown them, represent a summary of the achievements of each recipient. To a casual observer they may not fully portray the impact of the works of these leaders in their fields. The first shows the Stockholm Museum. Cards hanging from the ceiling depict Nobel Prize recipients, recording individual achievements with some context. The second is of the Oslo Museum. An interactive, digital display allows patrons to engage with similar data about recipients. When you first enter the museum, this can be overwhelming but once you start to track a particular field of endeavour, these tools provide a wonderful summary of the thinking behind each achievement. 

Expert knowledge is essential for real operational impact.

What does this have to do with AI and mining? I believe we can learn a great deal from these images. The collected data reflects the expertise each recipient bought to the world of knowledge.  

As we see Universities continue to scale back dedicated Mine Engineering programs,  the depth of academic knowledge imparted to newcomers to the industry is lessened. This places a great responsibility on those of us still in the industry to preserve, structure and transfer learnings from academia and practice.  

How do we, as experienced practitioners, ensure the next generation of mining professionals can access and build on this knowledge rather than relearn it through failure? I’ve been very fortunate in my mining career to work for, and with, some industry visionaries. Listening to how they think and observing how they work has built my knowledge of many facets of the mining industry.  

Learning from experience.

I was first introduced to mining through data collection and reporting whilst working for an early business intelligence startup called CorVu. We worked with MIM (now Glencore), Pulse Mining and others to build reports on mine and equipment performance. When I started, I wouldn’t have known the difference between a dozer and a digger! But I was keen to listen, and I learned a great deal.  

A determining career change was being to join Thiess’ Resource Development Group. There are few opportunities to join an internal think tank combining years of knowledge from across an industry. Nick Jukes had taken his vision and assembled a fascinating team of experts. My contribution was a small but pivotal system that still operates, in a revised form, on Thiess Mines 20 years later. Along the way I learned Pit to Port on an Indonesian Mine, Drill and Blast on a Hunter Valley Mine, Data Warehousing across many operations, Asset Maintenance of Fixed and Mobile Plant, and Fleet Management on coal operations.  

After my time at Thiess, I could apply  the knowledge and experience gained at Deswik (underground hard rock mining), RPMGlobal (underground coal mining) and iVolve (fleet management) before joining Commit Works. The guidance of Adam White, Wayne Romer and Jay Gillon at Deswik helped me translate open pit learnings to an underground context. A practical example that experts can accelerate learning on any topic.  

As a business analyst I would never have been able to design or deliver these solutions without the contributions from experts I had access to. Once I acknowledged I didn’t know it all, I could learn a great deal. I was then able to design and deliver some great solutions to the market.  

Bridging knowlege and innovation.

Now, Commit Works gives me the opportunity to deliver a solution that marries 12 years of development with my experience. Together, we will deliver a better operational planning solution. I enjoy taking a team of very strong technicians on a journey of learning, sharing the theoretical and practical knowledge I’ve gained along the way.  

I hope others are afforded the opportunity to listen first, rather than assume they know the solution or have the answers. After all, effective business analysis requires a careful review of historical solutions, understanding the ‘as-is’ state and using this data to derive a ‘to-be’ state that meaningfully improves on the past.  

BY IAN JONES, 
COMMIT WORKS HEAD OF PRODUCT

Mine planning systems and fleet management solutions capture what happened, but rarely why it happened. Even when operational decisions are captured digitally and connected to planning and execution data, AI can only explain outcomes without understanding intent. Artificial Intelligence in this context will be limited in its ability to support better planning, performance and safety. 

As we move focus from collecting data to leveraging the information contained in the data through AI, we need to acknowledge that our datasets are incomplete. At Commit Works, we work to capture the decisions made throughout the operational planning process, often commencing at the Weekly Plan on a mine site.  

The Three Pillars of Mining Data AI Needs

We are seeing three key pillars of data that support the types of analysis our client base is increasingly seeking. The Short-Term Mine Plan (supported by a summary maintenance plan), the Operational Plan, and Data Capture Systems (e.g. Fleet Management Systems). 

The Short Term Mine Plan is a key plan developed by planning engineers. This plan sets a guide for all decisions made during the week and influences outcomes in the weeks that follow. It directs mining activities and is often centered on locations and major equipment. It forms the basis for Conformance to Plan reporting, foundational to meaningful future analysis.  

The second is where we at Commit Works operate. We help mines create and manage an Operational Plan. This plan may start in a digital tool like PowerPoint, Microsoft Project or Excel, but key decisions are often made external to a digital platform. They are captured on paper, written on whiteboards, or penciled onto maps. In every case, these decisions impact the shift execution yet are rarely available for post-shift analysis.  

Data collection solutions like Fleet Management Systems are highly integrated and collect vast amounts of data from sensors mounted throughout modern mining equipment. This data is often further categorised by input through operator inputs, GPS or radar systems. This result is rich, accurate data supporting Time Usage Models, Equipment Movements and utilisation analytics.  

Implementing a solution that captures this rich data is essential. Once captured, it should be transferred to a structured data lakehouse. This will allow companies to answer questions that are currently only considered against statistical analysis of post shift results.  

AI Can See Outcomes But Can’t Explain Them 

Imagine a senior site manager asking an AI agent like ChatGPT, “How did we perform against target this week?”. Now imagine receiving a response that performance was 82% of target. The natural follow-up is, “Why did we miss target?”. This second question is where most operations are challenged. The reason isn’t immediately obvious, but it is simple. The data that explains operational decisions is not consistently captured digitally. Therefore, it does not exist in the data lakehouse. The AI agent can see outcomes, but it cannot see intent. 

When a supervisor draws a border on a map to indicate a no-go area, this can dramatically change onsite equipment movement, task execution sequencing and generate additional tasks. A fleet-focused solution would conclude an underutilised fleet. However, reality may be that unplanned work delayed access to and work at the planned location. Without digitally capturing that decision-making process, reasons and context, an AI agent cannot explain the outcome. 

Open Data Models and Industry Collaboration

There is a practical solution. Implement solutions that capture operational decision-making digitally through desktop solutions in the Control Room or mobile solutions used by Supervisors in-field. Once all tasks, actions and decision are captured, data can be moved to the data lakehouse and integrated with Mine Planning data and FMS outputs. 

It is important to remember: 

• A mine plan is an optimistic representation of intended work.
• A fleet system captures equipment behaviour, not operational intent. 
• Many critical activities do not require equipment and therefore never appear in FMS data. 

The image that leads this article shows a robot interacting with the usual players in a daily planning meeting. While this is currently a far-fetched (ai-generated) concept, imagine that robot as your AI agent. It can read and has access to historical data, decisions, outcomes and constraints. This means it can support supervisors and planners with informed recommendations in real time. Organisations with strong data foundations, visibility of decision-making, and integrated tooling across planning, execution and data capture can accomplish this. 

Can this be achieved today? Possibly. The likelihood improves significantly with common data models and open data sharing between systems. The time is right for industry bodies and vendors to work together to prepare for this future. 

BY IAN JONES, 
COMMIT WORKS HEAD OF PRODUCT

Artificial intelligence promises transformational outcomes for mining, but without curated, connected, and contextualised data, its impact will remain theoretical rather than operational. 

This image was taken in the Long Room at Trinity College, Dublin. It reminded me of the current state of Artificial Intelligence in the mining industry. AI is a technology with the potential to change the world. It is also one struggling to source the correct data to deliver its undoubted value.  

For context, the Long Room is normally home to some of the most valuable works of literature, science and engineering ever written. When this photograph was taken in 2024, those works had been temporarily removed for cleaning and restoration. The statues lining the room are busts of the most famous alumni of the college. Each is accompanied by notes describing their significant contribution to their respective fields.  

Data foundations matter.

So why does this scene so poignantly reflect the current state of AI in the mining industry, to me? 

First, the globe positioned centrally is a reminder that, if AI is delivered correctly, the whole world will benefit. Realising this requires a common data solution that can be accessed globally, bringing together data from many systems. Much has been written about data lakes and data warehouses, but the key, for mining, is capturing broad and representative data from across operational, planning, maintenance and execution systems. 

Second, while our shelves are not empty, there is a significant gap. Much of our data requires digitisation, curation, repair and contextualisation to make it fit for computer analysis. This is the domain of data architects and data scientists. In a traditional library, like the Long Room, an indexing system allows readers to locate and interpret data that points to the literature or answers they seek. Mining, by contrast, still lacks coherent data messaging solutions and, in many cases, the willingness to share data across systems or vendors. The excellent work of the Global Mining Guidelines Group (GMG) and ISA-95 working groups is starting to address this gap, but there is considerable progress to be made.  

Third, data alone rarely delivers high-quality results without expert guidance and guidelines. Domain knowledge must inform how data is structured, interpreted and applied as it begins to fill the shelves. This is where the academics and experienced industry experts add significant value. Data science may be about data, but applying insights effectively is about mining, operational, and maintenance expertise. Many data projects are run by IT and Data teams. While they deliver technical solutions, they often lack operational knowledge required to curate data effectively or embed the rules, constraints and learnings that allow AI solutions to deliver meaningful outputs. 

Practical steps to strengthen data foundations.

I have worked with data for many years, predating my involvement in mining by more than 10 years. My recent completion of a Graduate Certificate in Data Science did not reassure me that we are adequately preparing students for the challenges they are likely to face. In the mining industry, data complexity, context and consequence matter materially.  

Based on my experience, I offer the following recommendations: 

• Encourage genuine data collaboration between vendors. The richness of available data is limited only our ability to effectively integrate it across systems. 
• Recognise and retain expert, industry knowledge of the experts. Too much knowledge is lost by moving engineers off projects that could unlock meaningful data insights. These experts should be engaged to develop the rules engines used to categorise and interpret data.  
• As with Time Usage Models, develop standardised data categorisations for aligned to industry. These models can deliver value across multiple projects and shouldn’t need to be recreated by every organisation.  
• Attribute data at a granular level. For example, don’t store only a location label, but ensure underlying information and attributes of the location can be captured and queried.  
• Test assumptions rigorously using training data aligned to expected outcomes. Machine Learning may uncover some hidden gems, but poorly defined models are likely to miss the very issues you are looking intending to reveal.  

It’s an exciting and generational opportunity for our industry. Let’s take time to build strong foundations, respect domain expertise, and collaborate more effectively. When we democratise the data we can make better decisions, extend machine life and, most importantly, keep our people safe.

Machine Learning in Mining Operations

The mining industry is shifting toward digitization, technology like automation or robotics, and Industry 4.0 (or 5.0 depending on what you are reading). Artificial Intelligence (AI), Machine Learning (ML) , and specialized mining software are no longer futuristic concepts. These tools are driving driving intelligent, safe, efficient, sustainable and more predictable mining operations.

AI and ML are often talked about as high-tech concepts, but in mining, their value will come from solving real operational problems. Machine Learning is a type of AI that allows machines to continually learn from data and make predictions or decisions based on various inputs. At their core, these technologies help machines mimic human decision-making, identify patterns in complex datasets, and optimize processes.

AI and ML don’t replace human judgment and data analysis, they augment it, providing insight, predictions and foresight that make planning and execution more reliable.

The Benefits: Productivity, Safety, and Cost

The first wave of AI and autonomous technology in mining came about a decade ago with autonomous trucks. Since then, the potential benefits have expanded. Applied correctly, modern mining technologies allow teams to focus on the right work at the right time while reducing operational risk.

Driving Operational Excellence

Operational excellence is the foundation of the top tier mines. It’s about doing the right work, in the right way, every time. AI and ML have the power to strengthen this foundation by enhancing the core functions that matter most:

• Performance management
• Process optimization
• Strategy and planning
• Continuous improvement

Proven measures like Compliance to Plan, frameworks like Last Planner System, and software like CiteOps turn these principles into action. They allow teams to track execution against plans, identify where work is falling behind, and take corrective action before small issues become big problems. 

Challenges for Implementing Machine Learning

Implementing AI and ML isn’t without challenges. Economic, technological, workforce, and social barriers all exist. Success requires skilled teams, robust data, and a culture willing to embrace data-driven decision-making.

As mining companies continue to adopt digital tools, AI and ML will increasingly become part of the discussions and roadmap. Real-time monitoring, predictive insights, and automated planning will enable mines to achieve higher productivity, safer operations, and more predictable outcomes.

The biggest hurdle to applying AI or ML to mining operations lies in capturing, integrating and analyzing the required and relevant data to support these pertinent technologies.

Technology Investment Making Mines Smarter

AI, machine learning, and mining software are transforming how mines plan and operate. From improving compliance to plan, optimizing equipment, and enabling operational excellence, these tools are no longer optional, they’ve become essential. Top-tier mines are investing in the adoption of smart technologies thoughtfully, and will emerge safer, smarter, and more efficient operations.

AI and Machine Learning in Mining: Why Granular Data Matters

In recent years, the application of Artificial Intelligence (AI) and Machine Learning (ML) to revolutionise the industry has been a hot topic. Many discuss the importance of data in this transition, but few recognise the required granularity to support it.

Since 2010, miners have invested in ERP (finance and asset management), mine planning and FMS (with autonomous capabilities). With planning and real-time data capture covered, a critical gap remains in integrating operational planning and execution data.

The importance and impact of this data, still commonly managed using whiteboards, PowerPoint, Excel or paper, has become increasingly clear.

Mining Activity Conformance to Plan (CtoP) and Its Limitations

Conformance to Plan (CtoP) reporting of Mining Activities often excludes enabling or development activities essential for success. Traditional CtoP reporting highlights issues but lacks context. Operations apply insufficient rigour to managing enabling tasks as is required for effective collaborative planning. For AI/ML solutions to suggest improvements, they require deeper, more granular insight than what traditional short-term mine planning tools offer.

A mine plan optimistically lists key tasks to be completed, and once reviewed with all parties, establishes a baseline of critical path items. These items form the measurable data set for KPIs. However, KPIs and plan variances are diagnostic, not actionable. Supporting data that exposes contributing factors and enables tasks to be scheduled, assigned, executed, and evaluated is needed for action.

Expanding the Mine Plan to Capture All Mining Activities

An effective plan must include all work required to deliver critical path items. It should also recognise the impact of all processes on the schedule. Many sites do not complete this scheduling work, assuming other teams will complete tasks. Mining operations cannot understand true resourcing required without considering all tasks. Capturing this information on whiteboards, spreadsheets or paper hinders future analysis, especially by AI tools needing a data warehouse for ML analysis.

Data that represents progress to plan must be captured. In mining, many critical path items can be updated from third-party tools like FMS. Capturing enabling task progress is complex and requires an IT solution. Operations must compile these inputs from varying sources into a data lakehouse to provide a platform for rules-based and ML analysis. ML can then detect data trends useful for generative, predictive or agentic AI, and support real-time schedule optimisation.

Integrating Systems to Unlock Real-Time AI in Mining

Artificial Intelligence will continue to impact how we view plans and their execution. The key is ensuring all relevant data is captured and connected so ML can identify useful trends, highlight opportunities and reveal issues early.

To support effective reporting and analytics, teams must capture data, and establish relationships in real-time, for rapid decision making. Integrating ERP and FMS with operational execution data will provide richness to power advanced AI/ML.

Capturing Critical Execution Data with CiteOps

CiteOps is an integrated planning and execution software solution. This solution improves productivity by capturing short range plans and executional activities while fostering continuous feedback loops.

This enterprise-grade operational planning and execution platform specifically designed for mining and metals companies enables:

• Unified planning and execution
• Dynamic scheduling
• Centralised resource management
• Real-time decision making and
• Mobile execution

The Last Planner System (LPS), also called Collaborative Planning or Pull Planning is a project production workflow that delivers maximum value with minimal waste. This system empowers frontline leaders and crews to take an active role in planning and execution. Built on the principles of continuous improvement, it creates a more reliable, efficient workflow and improved outcomes. LPS aligns closely with familiar improvement principles like DMAIC (define, measure, analyse, improve, control), PDCA (plan, do, check, act) and SIC (short interval control).  

Who is a Last Planner in Mining Operations?

A Last Planner is the person closest to the work with the authority to make decisions and commitments about the schedule and tasks to be done. The system improves project flow through collaborative planning that focuses on what should be done, what can be done, what will be done, what was done and what can be learned. As the timeline approaches execution, plans should become more detailed and responsive. This ensures work is both achievable and valuable.  

In mining, the last planners would include supervisors, shift bosses, undermanagers, and crew leaders. These people are responsible for the work in greatest detail, closest to delivery with the greatest context to support decision-making. Planning should happen regularly – weekly, daily, and shiftly. It should involve short, focused discussions or meetings that build commitment to the schedule. Rather than a top-down approach, these meetings promote teamwork, accountability, ownership, and commitment to both shared and individual KPIs.  

This collaborative approach enhances efficiency by aligning teams. Tasks only begin when enabling tasks are complete and resources are ready. LPS identifies potential conflicts early by visualising and planning for environmental conditions, resources, dependencies, enablers and prerequisites.  

Although originally developed by Glen Ballard and Greg Howell for the construction industry, LPS has been successfully adapted for many fields including mining, software development, product design, education, and supply chain management.  

Last Planner System and Technology

Today, technology plays an increasingly important role in enabling its implementation and real-time coordination across complex mining operations. Commit Works has developed CiteOps to ensure that the right people do the right work at the right time. Technology can help link the action and focus of frontline teams with higher level plans. When tech tools support the successful management of people, resources, and processes, mines can drive operational excellence .  

Enabling (supporting) tasks and the Last Planner System

A core principle of the LPS is that work should only be committed when it is ready to be executed. When this happens, all prerequisites and constraints are confirmed to have been addressed. In mining operations, these prerequisites are commonly referred to as enabling tasks or activities. 

A collaborative planning system strengthens execution discipline by ensuring that work commitments are based on operational readiness rather than optimistic scheduling. Teams that surface constraints early, and assign responsibility for enabling tasks, can quickly verify that conditions are primed for production work to begin. This approach reduces reactive rescheduling, improves compliance to plan, and supports more reliable production outcomes.

Download the Commitment System Handbook for Underground Coal to learn more. 

Despite a decade of continuous improvement and technological advances, global mining operations are up to 28% less productive. If we are smarter and better equipped than ever, why is productivity decreasing?

McKinsey notes that mines employing innovative technologies to generate lasting value could see productivity skyrocket. One of the key elements of operational excellence is the integration of operating systems to support and deploy the right practices and the right behaviours. Top-tier miners are leading the way. Rio Tinto’s Safe Production System (RTSPS) and BHP’s continuous improvement-driven BOS reveal how leadership and systems thinking reshapes performance.

According to a 2023 study published in Sustainability, the most productive modern mines now include intelligent management and real-time decision-making. Scheduling management is crucial for optimising productivity. A well-implemented operating system leverages technology like CiteOps to ensure that every shift, every crew, and every leader knows the plan.

Implementing shift-level execution software is key to ensuring that clear, mine-wide targets are met. When feedback loops and data-driven decision-making are employed, potential production losses, inefficiencies and safety implications can be addressed as they arise.

The cause of management-system failures is often culture. Successful mining operations measure how business culture improvements feed excellence. Investments in software and technology can accelerate and deepen the cultural change needed to achieve operational excellence. Strong culture combined with a robust operating system delivers digital transformation at scale.

In today’s competitive mining landscape, operational efficiency is key to success. Short Interval Control (SIC) has emerged as a powerful tool for mining companies looking to optimize their operations and drive continuous improvement. Let’s explore how SIC is transforming the mining industry and why it’s becoming an essential practice for forward-thinking operations.

What is Short Interval Control?

Short Interval Control is a management system that focuses on real-time performance tracking and rapid decision-making. In mining, SIC involves breaking down shift activities into shorter time intervals, typically 2-4 hours, and continuously monitoring progress against targets. This approach allows for immediate identification of issues and swift corrective actions, leading to significant improvements in productivity and efficiency.

The Impact of SIC on Mining Operations

Implementing Short Interval Control in mining operations can lead to several key benefits:

1. Increased Productivity: By closely tracking performance and addressing bottlenecks in real-time, mines can significantly boost their output. Many operations report productivity gains of 10-20% after implementing SIC.
2. Enhanced Safety: Regular check-ins and real-time communication facilitate quicker identification and resolution of safety concerns, creating a safer work environment.
3. Improved Equipment Utilization: SIC helps identify inefficiencies in equipment use, leading to better maintenance scheduling and reduced downtime.
4. Data-Driven Decision Making: With real-time data at their fingertips, supervisors and managers can make informed decisions quickly, optimizing operations on the fly.

Implementing SIC: Best Practices

To get the most out of Short Interval Control, consider these best practices:

1. Leverage Technology: Use digital tools like CiteOps to streamline data collection, analysis, and communication. Modern SIC software can provide real-time dashboards and automated alerts, making it easier to stay on top of performance metrics.
2. Foster a Culture of Continuous Improvement: Encourage all team members to actively participate in the SIC process. Regular feedback sessions and idea-sharing can lead to valuable insights and improvements.
3. Start Small and Scale: Begin with a pilot program in one area of your operation. Once you’ve refined the process and seen results, expand SIC across your entire operation.
4. Align SIC with Overall Strategy: Ensure that your Short Interval Control metrics and targets align with your broader operational goals and KPIs.

The Future of SIC in Mining

As technology continues to advance, we’re seeing exciting developments in Short Interval Control. Integration with IoT sensors, AI-powered predictive analytics, and even augmented reality interfaces are on the horizon. These innovations promise to make SIC even more powerful and user-friendly, further driving operational excellence in the mining industry.

By embracing Short Interval Control, mining companies can stay competitive in an ever-changing market, ensuring they’re always operating at peak efficiency. Is your operation ready to take the next step towards operational excellence with SIC?