Predictive model for long term mine planning using sensor based bulk ore sorting technology for a porphyry deposit

Efficient mine planning is essential for optimizing resource recovery, operational efficiency, and sustainability in modern mining. This thesis investigates the application of MineSense’s ShovelSenseTM technology, a bulk sensor-based sorting (SBS) system, in enhancing long-term mine planning for a copper porphyry deposit in Western Canada. ShovelSenseTM enables real-time material composition analysis during excavation, offering higher precision in separating ore from waste. This research addresses the challenges posed by orebody heterogeneity and variability in porphyry deposits. Geostatistical techniques, including distribution modeling, are utilized to analyze data from grade-control block models generated from blasthole assays, and ShovelSenseTM outputs. This study evaluates the integration of real-time ShovelSenseTM data into predictive algorithms, focusing on improving the accuracy of the predicted models to be used for mine planning. The analysis revealed that Shovel Sense data enhances understanding of orebody variability, supporting more informed and adaptive mine planning decisions. By enabling precise sorting, the technology indirectly reduces energy and water consumption downstream, contributing to more sustainable mining operations. The findings also highlight the potential for Shovel Sense to address data limitations in greenfield projects and improve resource utilization. This thesis demonstrates the value of combining advanced sensor technologies with geostatistical tools to tackle operational challenges in porphyry deposits. The framework presented provides the mining industry with a practical method to integrate real-time SBS technologies into mine planning, driving greater efficiency and sustainability in the mining industry.