geometallurgical validation to strengthen the connection between visual domains and processing behaviour. 7. CONCLUSIONS GeoLithAI is presented as an anonymized AI-assisted workflow for lithological recognition and grade-control support in an underground Peruvian mine. The proposed method combines CNN-based semantic segmentation, YOLO-type object detection, uncertainty flagging and geologist review to generate traceable lithological-domain information from underground face images. The most defensible contribution is not the replacement of geologists, but the acceleration and standardization of short-cycle geological mapping. By separating lithological domains from non-geological occlusions and by returning ambiguous predictions to expert review, the workflow can improve repeatability while maintaining geological accountability. The pilot framework defines five initial domain classes, a 500-image first training cycle, and measurable indicators such as IoU, Dice coefficient, mAP@0.5, review acceptance and mapping-cycle time. The approach is scalable to additional sensors and mining contexts, but its current strength is a confidentially safe, technically grounded framework for underground lithological-domain recognition. ACKNOWLEDGEMENTS The author acknowledges academic mentors and mining professionals whose technical discussions on operational geology, image-based interpretation and responsible digital transformation contributed to the conceptual development of this anonymized workflow. REFERENCES Bellian, J. A., Kerans, C. and Jennette, D. C. (2005). Digital outcrop models: Applications of terrestrial scanning lidar technology in stratigraphic modeling. Journal of Sedimentary Research. 75(2), 166-176. Bissig, T., Ullrich, T. D., Tosdal, R. M., Friedman, R. and Ebert, S. (2008). The time-space distribution of Eocene to Miocene magmatism in the central Peruvian polymetallic province and its metallogenetic implications. Journal of South American Earth Sciences. 26(1), 16-35. Bochkovskiy, A., Wang, C.-Y. and Liao, H.-Y. M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv preprint arXiv:2004.10934. Goodfellow, I., Bengio, Y. and Courville, A. (2016). Deep Learning. MIT Press, Cambridge, MA. He, K., Gkioxari, G., Dollar, P. and Girshick, R. (2017). Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision, 2961-2969. Krizhevsky, A., Sutskever, I. and Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems. 25, 10971105. Noble, D. C. and McKee, E. H. (1999). The Miocene metallogenic belt of central and northern Peru. In: Skinner, B. J. (ed.), Geology and Ore Deposits of the Central Andes. Society of Economic Geologists Special Publication 7, 155-193. Riquelme, A., Tomas, R., Cano, M., Pastor, J. L. and Abellan, A. (2018). Automatic Mapping of Discontinuity Persistence on Rock Masses Using 3D Point Clouds. Rock Mechanics and Rock Engineering. 51, 3005-3028.
RkJQdWJsaXNoZXIy MTM0Mzk2