Geotechnical monitoring technologies in mining engineering: Trends, limitations, and future directions

Geotechnical monitoring is essential for safe, stable, and efficient mining. Recent developments in instrumentation, remote sensing, and data-driven analytics have revolutionized monitoring strategies by allowing real-time, predictive, and large-scale evaluation of slope stability, underground movements, and tailings dams. This paper is a systematic synthesis and review of literature published 2015–2025 on the use of conventional in situ instrumentation, remote sensing using satellites and unmanned aerial vehicles, wireless sensor networks, machine learning models, and integrated digital twin frameworks. The main results from 23 unique studies reveal that in situ equipment offers high-resolution local measurements, while remote sensing technologies offer wide-area coverage. Machine learning and artificial intelligence improve prediction by processing complex geotechnical data. In situ sensors, communication networks based on the Internet of Things, and real-time analytics are all integrated within installed monitoring systems to allow continuous monitoring and automatic, near-real-time decision-making in mining environments. Despite these innovations, constraints remain, such as the high cost of installation and maintenance, environmental and operational restrictions, data quality, and interoperability and standardization issues. Among the new trends identified in this review are multi-sensor data fusion, physics-informed machine learning, cloud-based analytics, and predictive digital twins, which have the potential to transform monitoring to a proactive, rather than reactive, aspect of management.