397 Aligned with the World Mining Congress 2026 theme, this study illustrates how advanced machine learning can support faster, smarter, and more responsible mineral production. By transforming large-scale geospatial datasets into actionable risk intelligence, the framework enhances decision-making efficiency, reduces subjectivity, and enables scalable deployment from national planning to mine-site operations without retraining. Through the integration of technological innovation and geotechnical risk management, this approach contributes to advancing transformation in the mining sector while strengthening societal trust through safer and more sustainable practices. ACKNOWLEDGEMENTS The authors acknowledge the institutional support of WSP Peru. Special thanks are extended to Martha Ly, ESG Mining Regional Leader and Earth & Environment Sector Leader for LAC, for her strategic leadership and sponsorship support. We also thank Dani Gutiérrez, Senior Environmental Specialist and Water Resources Leader at WSP Peru, for his early institutional backing in 2024, when AI-driven environmental platforms and automated systems were still emerging initiatives. His belief in the strategic potential of Digital Innovation and Geospatial Intelligence was instrumental in consolidating this function as a growing area with long-term organizational impact. Their commitment to advancing environmental excellence, technological transformation, and scientific innovation within the mining sector is deeply appreciated. REFERENCES Althuwaynee, O. F., Pradhan, B., & Lee, S. (2012). Application of an evidential belief function model in landslide susceptibility mapping. Computers & Geosciences, 44, 120–135. https://doi.org/10.1016/j.cageo.2012.03.003 Autoridad Nacional del Agua. (2012). Mapa de unidades hidrográficas. https://snirh.ana.gob.pe/onrh/MapaTematicoUH.aspx Beven, K. J., & Kirby, M. C. (1979). A physically based, single-source catchment model of the hydrologic response to rainfall and evapotranspiration. Hydrological Sciences Journal, 24(1), 103–110. Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural Networks, 2(5), 359–366. Instituto Geológico, Minero y Metalúrgico (2010). Mapa de susceptibilidad por movimientos en masa del Perú https://hdl.handle.net/20.500.12544/2906 Kumar, C., Walton, G., Santi, P., & Luza, C. (2023). An ensemble approach of feature selection and machine learning models for regional landslide susceptibility mapping in the arid mountainous terrain of southern Peru. Remote Sensing, 15(5), 1376. Luque Poma, G., Gomez Velásquez, H. D., Pari Pinto, W., Peña Laureano, F., & Huamán Nieto, M. (2021). Peligro geológico en la región Tacna (Boletín Serie C, No. 82). INGEMMET. Mandal, S., & Mondal, S. (2019). Statistical approaches for landslide susceptibility assessment and prediction (Vol. 27). Springer. Mandelbrot, B. B. (1983). The fractal geometry of nature. W. H. Freeman. McNab, W. H. (1993). A topographic index to quantify the effect of mesoscale landform on site productivity. Canadian Journal of Forest Research, 23(6), 1100–1107.
RkJQdWJsaXNoZXIy MTM0Mzk2