grade ores. In this system, ore is stacked in lifts over an impermeable geomembrane and irrigated with a cyanide solution, allowing dissolved gold to be recovered over time. However, gold production in heap leach operations does not depend solely on the quantity of ore stacked during a given time. Instead, production results from a delayed and cumulative response mechanism governed by: Ore stacking rates, Ore grade and cyanide solubility, Column height and hydraulic flow path, Active inventory within the heap, and the temporal evolution of leaching kinetics. Strategic mine planning requires reliable production forecasting to guide lift sequencing, irrigation allocation, discharge prioritization, and cash flow projections. However, conventional forecasting methods often assume proportionality between recent stacking and production, neglecting internal inventory and spatial variability. This study addresses this limitation by proposing a dynamic, data-driven framework grounded in geometallurgical modeling and machine learning. 2. METHODOLOGY 2.1 Geometallurgical Block Model Construction A three-dimensional representation of the heap was constructed using monthly topographic surfaces. Incremental solids were discretized into regular volumetric blocks corresponding to the minimum operational discharge unit. Each block was assigned: Gold, silver, and copper grades, cyanide solubility parameters, and source attribution variables. During heap construction modeling, each block inherited grade values according to its origin. This procedure ensures that geometallurgical variability is preserved based on material source, rather than using global averaging across the entire dataset. Derived variables included: Contained metal, Recoverable metal. 2.2 Exploratory Data Analysis 2.2.1 Temporal Dynamics The heap leach system exhibits delayed production response relative to ore placement, confirming the presence of internal inventory dynamics and time-dependent recovery behavior. To quantify this delayed response, the cross-correlation between gold production and gold placement was computed as:
RkJQdWJsaXNoZXIy MTM0Mzk2