Aws I. Abueid

Background: The mining sector’s digital transformation increasingly relies on AI-driven digital twins (AI-DTs) that integrate real-time data with intelligent analytics. A recent systematic literature review (SLR) of 68 studies identified a critical gap: which technical choices guarantee industrial success? Objective: This study extends that SLR by validating a Deployment Readiness Score (DRS) to identify which combinations of technical and methodological choices are associated with high readiness AI-DT studies in the literature. Methods: Each study was coded across eight dimensions and assigned to a DRS based on data source, validation method, and operational metric reporting. A random forest classifier was used as a consistency check for the DRS framework. Results: The model achieved 100% test accuracy as an internal consistency check within the coded dataset, confirming that the DRS scoring rules produce a coherent classification across the reviewed studies. The data source was the strongest association (41.2%), followed by publication year (25.6%) and validation method (22.7%). AI technique showed minimal association (0.9%). Studies using sensory data achieved 100% high readiness within the DRS framework; mixed data achieved 95.2%; and experimental validation achieved 95.7%. The proportion of high-readiness studies increased from 35.7% in 2024 to 93.5% in 2025. Conclusions: Within the reviewed literature, high-fidelity data and rigorous validation show stronger associations with high readiness than algorithmic complexity. We provide a Deployment Readiness Scorecard and propose minimal reporting standards, shifting focus from theoretical algorithms to practical data acquisition and validation.

The mining industry is going through a big digital change because of the use of new technologies that are meant to make work safer, more productive, and more environmentally friendly. AI-driven digital twins (AI-DTs) are one of these new ideas. They combine real-time data collection with smart analytics to make it possible for decisions to be made in a predictive, adaptive, and autonomous way. This paper provides a thorough systematic literature review (SLR) of AI-DT applications in mining operations, encompassing studies published from 2015 to 2025. According to the PRISMA method, 68 primary studies were chosen and looked at from many angles, such as publication trends, demographic analysis, research methods, data sources, mining domains, and the AI techniques that were used. The findings reveal an increasing scholarly interest in AI-DTs, characterized by a significant prevalence of machine learning and deep learning methodologies, alongside a preference for real-world sensory data to augment model accuracy. Most applications deal with physical assets, processing plants, and operational systems. Subsurface environments, on the other hand, are still not well understood. The review also points out some major problems with data integration, scalability, interoperability, and the fact that there has not been much large-scale industrial validation. Based on these findings, the paper points out important areas of research that need more work and suggests ways to move forward with the development and use of AI-DTs in mining. In conclusion, this study gives researchers and practitioners a clear plan for how to use AI-DTs to make mining operations more efficient, resilient, and long-lasting.