Machine learning (ML) is advancing the fields of geotechnics and geosciences by enabling data-driven subsurface characterization, predictive modeling, and real-time decision support.
This session invites contributions on ML applications in geotechnical and geoenvironmental engineering. Topics may include slope stability, tunneling, foundation design, subsurface flow and transport, seismicity, and coupled hydro-mechanical processes. Studies leveraging supervised, unsupervised, and deep learning methods; physics-informed neural networks; and hybrid ML–finite element method frameworks are encouraged.
We also welcome work that integrates ML with monitoring data (e.g., Internet of Things (IoT) sensors, remote sensing), inverse analysis, and the development of digital twins for predictive maintenance, structural health monitoring, and hazard mitigation.
Submissions that demonstrate model interpretability, uncertainty quantification, benchmark comparisons, or hybrid data–model approaches are especially encouraged.