From Data to Decisions: The Mining Decision Problem

Modern mining operations are increasingly characterised by their access to large volumes of data and advanced computational tools. Over the past two decades, the industry has made substantial investments in digital technologies supporting geological modelling, mine planning, equipment dispatch, and process control(Newmon et al., 2010; Paraszczak, 2019). These systems have significantly improved the ability to generate and analyse information across the mining value chain. However, despite these advances, the decisions that ultimately determine operational performance remain largely implicit and unmanaged (Kruger et al., 2023; Jia, 2022). Mining decisions rarely occur in isolation. Decisions made in geology influence resource models, which shape mine plans, production schedules, and downstream processing strategies. These, in turn, affect operational execution. As deposits become deeper, ore grades decline, and operational constraints increase, these interdependencies create increasingly complex decision environments (Newman et al, 2010; Topal, 2008; Darling, 2011; Dimitrakopoulos, 2004). In practice, coordination across these domains often relies on informal communication, iterative meetings, and manual interpretation of analytical outputs. Explicit decision support systems provide a mechanism to capture these dependencies, maintain consistent decision context, and coordinate decision-making across geological, planning, and operational domains (Power, 2002; Shim et al., 2002). This paper argues that a fundamental gap remains in current digital mining systems: while data and analytics are well supported, decision-making itself is not. Addressing this gap requires treating decisions as explicit, structured elements within the operational system. By integrating data, computational analysis, and decision processes, explicit decision support systems offer a way to better coordinate complex, interdependent decisions across mining operations.