361 Figure 4. Examples of outcomes in terms of Displacement Rates by Geological Units using AI-tools (Calderon, Barnes, 2025) Taken together, the technical results of this work make clear that early-stage slope deformation is both detectable and interpretable when advanced analytics and geotechnical expertise are brought together in a structured way. The ability of SMA and AI driven pattern grouping to reveal subtle, long horizon movement trends—well before they manifest in real-time alarms—demonstrates a step change in how uncertainty in ground conditions can be monitored and managed. These insights move geotechnical monitoring from a reactive, mitigation focused control toward a genuinely preventive one, giving operations materially greater Leadtime to plan, intervene, and protect people and production. This reinforces the central message of the paper: the real value is unlocked not only by the analytics themselves, but by embedding them within a transdisciplinary operating model that ensures they translate into confident, earlier, and more effective decision making.-stage slope deformation is both detectable and interpretable when advanced analytics and geotechnical expertise are brought together in a structured way. The ability of SMA and AI-driven pattern grouping to reveal subtle, long-horizon movement trends—well before they manifest in real-time alarms—demonstrates a step-change in how uncertainty in ground conditions can be monitored and managed. These insights move geotechnical monitoring from a reactive, mitigation-focused control toward a genuinely preventive one, giving operations materially greater lead-time to plan, intervene, and protect people and production. This reinforces the central message of the paper: the real value is unlocked not only by the analytics themselves, but by embedding them within a transdisciplinary operating model that ensures they translate into confident, earlier, and more effective decision-making. 6. CONCLUSIONS AND IMPLICATIONS FOR INDUSTRY This work demonstrates that combining AI-enabled analytics with geotechnical subject-matter expertise materially improves the industry’s ability to detect, interpret, and act on early indicators of slope deformation. Slow Movement Analysis (SMA) enhances monitoring granularity and uncovers long-horizon deformation trends that traditional real-time systems often cannot detect, providing earlier and more reliable insight into emerging ground behaviour. Together, SMA and data-driven movement-pattern grouping allow Material No Failure Post Failure Pre + During Failure Pre Failure Post Failure Failure No Failure Velocity Distributions
RkJQdWJsaXNoZXIy MTM0Mzk2