EP 162 | AI in Mining: Tool or Threat to Geologists?

Was the sample representative? Every geological model, resource estimate, grade control decision and reconciliation result ultimately depends on the quality of the samples behind it. In this episode of Fresh Thinking by Snowden Optiro, Melanie Bulley is joined by Senzeni Mandava Matondi to explore the Theory of Sampling and why representative sampling is fundamental to reliable decision-making throughout the mining value chain. They discuss why natural heterogeneity makes sampling challenging, the difference between correct and incorrect sampling errors, why precision should not be confused with representativity, and why even highly precise laboratory analysis cannot correct a sample that was unrepresentative from the beginning. The episode also explores the practical consequences of poor sampling, including ore loss, dilution, poor reconciliation and unreliable resource estimates. In this episode: Why sampling is the foundation of mining data Understanding representativity and natural heterogeneity Correct vs. incorrect sampling errors Precision vs. representativity Why laboratories cannot fix poor sampling The impact of sampling on grade control and reconciliation Principles of good sampling practice

Tailings Mineral Resource Estimates can appear straightforward. The material has already been mined, crushed, processed and deposited in one location — but tailings facilities present their own unique set of technical challenges. In this episode of Fresh Thinking by @SnowdenOptiro  , Senzeni Mandava and Melanie Bulley explore the nuances of estimating Mineral Resources within tailings facilities. They discuss how tailings differ from conventional in situ deposits and why depositional engineering, rather than natural geological controls, can become fundamental to understanding continuity. opics covered include: Density and moisture uncertainty Sampling unconsolidated and saturated material Variography and spatial continuity in tailings • Depositional history and hydraulic segregation The importance of the phreatic surface and hydrogeology Metallurgical recoverability and project economics Mineral Resource classification Tailings reprocessing, critical minerals and ESG considerations As Senzeni and Melanie discuss, a tailings facility is not simply a relocated orebody. It is an engineered, evolving sedimentary system with its own geotechnical, hydrogeological, metallurgical and operational complexities.

In Part 2 of our Fresh Thinking by @SnowdenOptiro  two-part series, host Melanie Bully is joined by Senzeni Matondi to continue the discussion on why the most expensive mistake in grade control isn't necessarily mining low-grade material — it's making the wrong decision about whether material is ore or waste. Following on from Part 1, this episode explores how mining operations can make better grade control decisions by understanding and managing uncertainty. Melanie and Senzeni discuss why average grade alone doesn't tell the full story, how conditional bias and grade smoothing can affect ore and waste classification, and why local accuracy around the cut-off grade is so important. They also explore grade control as a complete value chain — from sampling, QA/QC and geological logging through to estimation, dig planning, mining execution, stockpile management and mine-to-mill reconciliation. The conversation then turns to modern approaches to uncertainty and risk, including conditional simulation, probability-based ore classification and risk-based digline optimisation. In this episode Melanie and Senzeni discuss: Why two models with similar average grades can deliver very different operational outcomes Conditional bias and the impact of grade smoothing The importance of local accuracy around the cut-off grade How ore loss and dilution result from misclassification • Why reconciliation reflects the performance of the entire grade control system Moving from deterministic estimates to risk-informed decision-making What best-practice grade control looks like at high-performing operations The key message from this two-part series is simple: grade control isn't about producing the perfect block model — it's about consistently making better mining decisions.

What if the most expensive mistake in grade control isn't mining low-grade material — but making the wrong decision about what is ore and what is waste? In this two-part episode of Fresh Thinking by Snowden Optiro, Senzeni Matondi, Principal Consultant, joins Melanie Bully, Senior Consultant, to explore why grade control is fundamentally a decision-making discipline, not simply a grade estimation exercise.  In Part 1, Senzeni and Melanie unpack the operational and financial consequences of misclassification, including: Ore loss — when valuable material is classified as waste and potentially lost forever Dilution — when waste enters the ore stream, reducing head grade and consuming valuable processing capacity Misclassification — and why it can result from accumulated uncertainty across sampling, geological interpretation, estimation, blast movement, survey accuracy and mining execution Reconciliation — and why poor reconciliation can reflect issues across the entire mining value chain, rather than the resource model alone The key takeaway? A technically sound grade estimate is only useful if it supports the right operational decisions.

If your resource model is statistically robust, why doesn't it always reconcile with production? In this episode of Fresh Thinking by Snowden Optiro, Melanie Bulley and Senzeni Mandava Matondi explore why good resource estimates can still lead to disappointing reconciliation results. They discuss the impact of grade smoothing, explain the concept of conditional bias, and explore why reproducing the average grade is only part of the story. The conversation also covers practical techniques used by resource geologists to assess estimation performance and improve local predictions that support better mining decisions. Whether you're working in resource estimation, grade control or mine reconciliation, this episode offers practical insights into bridging the gap between statistical accuracy and operational performance.

How do you model mineralisation when geological boundaries aren't clearly defined? In this episode of Fresh Thinking by  @SnowdenOptiro  , Senior Consultant, Melanie Bulley is joined by Principal Consultant, Senzeni Matondi to explore how Categorical Indicator Kriging (CIK) can be used to model diffuse mineralisation more objectively and consistently. The discussion covers: Why traditional wireframing can be challenging in diffuse deposits How probability-based domaining improves consistency The role of CIK in reducing subjectivity Building more robust and defensible resource models Whether you're a resource geologist, geostatistician or mining professional, this episode provides practical insights into one of the industry's most powerful domaining techniques. Subscribe for more conversations on resource estimation, geostatistics and mining best practice from the experts at Snowden Optiro.

What do consultants see that mine sites often miss? In this episode of Fresh Thinking bySnowden Optiro, Rayleen Hargreaves is joined by Ian Glacken to discuss the most common mine-to-mill reconciliation challenges, from stockpile management and siloed teams to understanding variance and improving decision-making. Learn why reconciliation is more than a monthly report—it's a powerful tool for improving mine performance.

Which commodities matter most in the global race for critical and strategic minerals? In this episode of  @SnowdenOptiro  Fresh Thinking podcast, Senzeni Mandava Matondi is joined by Julian Aldridge and Laurie Hassall to explore the commodities that consistently appear on critical minerals lists around the world and the factors driving their importance. The discussion examines key battery minerals including lithium, cobalt, nickel, manganese and graphite, alongside rare earth elements, tungsten and aluminium. The team also explores how geopolitical considerations, supply chain security and processing capability influence whether a mineral is considered critical or strategic. Topics covered include: The common commodities found on national critical minerals lists The growing importance of rare earths and tungsten Why aluminium is increasingly viewed as both critical and strategic How Indonesia's nickel production is influencing global markets China's role in downstream processing and critical mineral supply chains The relationship between resource availability, processing capacity and strategic importance

What makes a mineral critical? What makes it strategic? And why are governments around the world racing to secure supplies of certain commodities? In this episode of Fresh Thinking by Snowden Optiro , Senzeni Mandava Matondi, Julian Aldridge, and Laurie Hassell explore the growing importance of critical and strategic minerals in today's economy. From copper, lithium and rare earth elements to gallium and germanium minerals, the discussion examines how countries define these resources and why those definitions matter. The team explores: The difference between critical and strategic minerals Why supply risk matters The role of minerals in national security and defence Food security and fertiliser-related commodities How critical mineral lists differ between countries The influence of processing capability and intellectual property The minerals driving the energy transition

Will AI replace geologists? In this episode of Fresh Thinking by  @SnowdenOptiro , we explore how artificial intelligence is being used across the mining industry, from exploration targeting and core logging to resource estimation and technical reporting. Our team discusses the opportunities AI presents, its current limitations, and why geological expertise, judgement and accountability remain critical in mining workflows.