This study explores the integration of data fusion using machine learning methods for ore tracking frommine to mill, with the goal of developing predictive geometallurgical models. Conducted at BolidenMineral AB's Garpenberg Zn-Pb-Ag-(Cu-Au) mine in Sweden, the research utilizes extensive geological,operational, and legacy data to create a foundation for a digital twin geometallurgical model for theprocessing plant. By combining 3D geological data with mining and plant operational data, the projectaims to enhance the understanding of ore variability and its impact on processing performance. Thisapproach not only seeks to improve efficiency and reduce variability in production but also providesvaluable insights for more accurate prediction and simulation models in geometallurgy. The outcomesof this research could contribute significantly to the future of data-driven mine planning for optimizedperformance.