Results indicate that recovery is not spatially uniform, revealing localized areas of enhanced metallurgical performance. This spatial heterogeneity reflects internal heap dynamics and time-dependent recovery behavior. 4. CONCLUSION This study presents, planning-level predictive framework for heap leach production forecasting. By integrating: Geometallurgical block modeling, Dynamic state reconstruction, Feature-engineered temporal indicators, and Machine learning. The regularized linear baseline model achieved stable and consistent performance across temporal splits. By identifying zones of relatively higher recovery performance, the methodology provides actionable insight for future stacking strategies and operational mine planning. The spatially resolved framework supports improved decision-making in lift sequencing, ore placement, and pad expansion design. Consequently, spatial performance mapping constitutes a valuable tool for forward-looking heap leach planning and optimization. ACKNOWLEDGEMENTS The author would like to express his sincere gratitude to his family for their continuous support and encouragement throughout this research. The author would like to express sincere gratitude to the academic supervisors and technical mentors who provided guidance and constructive feedback throughout the development of this research. The author also acknowledges the support of the affiliated academic institution for providing the necessary research framework and resources to conduct this study. Special appreciation is extended to the operational and technical personnel of the case study mining operation for their support in data collection, clarification of operational procedures, and valuable discussions regarding heap leach dynamics and discharge planning.
RkJQdWJsaXNoZXIy MTM0Mzk2