Underground
7 papers4 directions
Underground is a research venue active between 2002 and 2025 that focuses on the application of machine learning and computational modeling to geological and civil engineering. The venue is characterized by its emphasis on underground construction, tunnel engineering, and the management of geological uncertainties. Research published here often explores the intersection of structural analysis and data-driven methodologies, such as using Bayesian networks for failure probability estimation in excavations and ensemble models for regional 3D geological modeling along metro lines.
The venue's contributions include work on modeling non-orthogonal architectural layouts and the neural reconstruction of sparse spatio-temporal fields. Specific research directions involve the classification of rock quality grades using multifractal-based models and the evaluation of visual comfort in underground spaces through intelligent sorting algorithms. Prolific contributors to the venue include authors such as Baiyi Li, Chong Yu, Jiajun Wu, and Jian Chen. By integrating probabilistic seismic response analysis and copula-based coupled Markov chains, the venue serves as a specialized platform for addressing technical complexities in underground environments, braced excavations, and reservoir areas.
Papers by Year
| 2025 | 1 |
| 2024 | 2 |
| 2023 | 1 |
| 2021 | 1 |
| 2019 | 1 |
| 2002 | 1 |
Top Research Directions
Research directions most represented by papers from this venue.
| Modeling Anisotropic Spatial Dependencies | 1 |
| Spatial Uncertainty Quantification and Confidence Mapping | 1 |
| Modeling Spatial Non-Stationarity in Geographic Data | 1 |
| Relaxing the Manhattan World Assumption | 1 |