<![CDATA[Mining operations are increasingly facing climate-related risks, including extreme rainfall, flooding, slope instability, and infrastructure failure. These climate change risks usually occur in open mining environments. Traditional risk management methods in mining are less reactive and less effective at managing the currently rapidly escalating climate-related risks. Artificial Intelligence (AI) offers promising capabilities for improving climate resilience and risk management through predictive, data-driven, and adaptive solutions. This review shows how recent empirical studies have explored how AI is used to promote climate resilience and risk management in the mining environment. Using the PRISMA framework, peer-reviewed studies from 2020 to 2025 were analysed to identify key application areas, popular AI techniques, analytical frameworks, and implementation challenges. The PRISMA-guided search across Scopus, Web of Science, and ScienceDirect screened 580 records and identified 16 empirical studies; however, coverage of African mines was limited, and few papers linked AI predictions to routine HSE decision workflows. Results indicate that AI is primarily applied for geotechnical risk monitoring, flood forecasting, and hazard detection via machine learning, deep learning, and remote sensing. Nonetheless, AI adoption remains fragmented, hazard-specific, and hindered by data shortages, model interpretability, and organisational barriers. This review, therefore, highlights the need for integrated, interpretable, and operationally embedded AI systems to support proactive, long-term climate resilience in mining.]]>
Copyrights © 2026
