Beware the undulation : failure mode prediction and rock mass classification in rock mechanics using deep neural networks and synthetic rock mass models
Bibliographic record
Abstract
Rock mass classification systems (RMCS) remain prominent within the rock engineering field. Although many of these systems have become ubiquitous, they are predicated upon a series of empirical case studies tailored to particular geographic locations and stress regimes. While each classification system may be valid for the project type and location for which it was created, modern applications extend the use of these systems beyond their initial raison d’être. Furthermore, the case studies which form the basis of these classification systems are scarcely representative of the conditions to which these systems are applied which poses a risk to safety, design stability, and reliability. Rock mass characterisation deals with assigning values to individual components that dictate rock mass behaviour. Rock mass classification attempts to characterise rock mass behaviour or strength based on observed characteristics. This research focuses on the effects of rock mass classification systems. Machine learning models may be trained on images from various locations, thus eliminating a key limitation of current classification systems: location relevance. This thesis examines the application of computer vision (artificial intelligence) techniques for joint mapping and investigates the impact of joint geometry on rock mass strength in synthetic rock mass (SRM) models. Current SRM models depict joint fractures as planar surfaces which risks oversimplifying the interactions observed in geometrically complex, undulated rock masses. Experiments conducted and explored as part of this thesis investigate the effects of large-scale undulation versus conventional flat joint representations on simulated rock mass strength. Multiple discrete fracture networks (DFNs) with flat, geometrically simplified, planar fractures were contrasted against geometrically complex surfaces. Results from this experiment reveal inconsistent patterns between explicit undulated surfaces and rock mass strength across various DFN realisations. These results challenge the prevalent assumption that the ramifications of geometric simplification may be mitigated by parametric adjustments. In fact, it re-enforces the notion that network topology and general fracture connectivity govern rock mass behaviour and strength.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".