Track 1: AI and Data-Driven Decision Making

control comminution efficiency and influence ore response during primary and secondary grinding stages. The analysis is conducted using data aggregated at a 15-minute granularity over the period from January 1, 2023 to August 26, 2025. 3.1.2. Residence Time Considered for Time-Series Transformation The residence time of the ore material is defined from its extraction at the mining face to its discharge at the Primary Crusher. These time intervals (start and end timestamps) are recorded through the MineStar system, which provides detailed information on shovel loading time, truck hauling time, and unloading time at the Primary Crusher. For the estimation of residence time within the processing plant, the analysis begins at the Primary Crushing stage and extends through the transport pathway from the Primary Crusher to the Stockpile, and subsequently from the Stockpile to the SAG mill. Residence time calculations were performed based on design layouts and mechanical drawings, including distance measurements and elevation profiles, to ensure accurate modeling of material transport across each stage and between unit operations. (Albarracin, 2021) This approach enables proper alignment of the material timestamp with its effective arrival at the SAG milling stage (Phase I), allowing the transformation of operational data into consistent time-series representations associated with the actual ore processed. Figure 42. Determination of Residence Times in the Phase I Concentrator Plant. (Albarracin, 2021) 3.2. Data Preprocessing Data from ODJIT were used, where alteration variables (Intrusive A, Intrusive B, Skarn Serpentine–Magnetite, Skarn Actinolite, and Hornfels) are available as time series derived from originally georeferenced information. As a quality control step, records were filtered to retain only those with alteration balances between 99% and 101%, ensuring consistency in the representation of the total material.

RkJQdWJsaXNoZXIy MTM0Mzk2