Image-Based Approaches for Phase and Fracture Characterization: Micro-mechanics of Stanstead Granite
Bibliographic record
Abstract
As imaging techniques and data acquisition technologies advance, and the storage of large datasets becomes more cost-effective, the field of rock mechanics has access to unprecedented amounts of detailed experimental and image data. This thesis presents the development of an image-based machine learning model to predict strain concentration during laboratory-scale experiments. Stanstead granite, an important material for many Canadian energy applications including nuclear storage, hydraulic fracturing and geothermal energy, was used in this study to develop a proof-of-concept model. Uniaxial compression (UCS) and three-point bending tests were conducted on granite samples using a customized loading configuration equipped with both a high-speed camera system and digital image correlation (DIC) system. A chemical staining technique was applied to the granite to visually distinguish between different grains, as well as classify grain boundary types after applying image processing techniques. With the collected photographic data overlaid on loading data, machine learning models, including classical machine learning and convolutional neural networks (CNNs), were employed to uncover the regional patterns of fracture propagation across sample surfaces. Classical models, including LightGBM, achieved 82.1% overall accuracy across in a categorical strain model. Classical models outperformed deep learning approaches in this study, likely due to limited dataset size. The model demonstrated the ability to generalize to unseen geometries and aligned with observed physical phenomena. Lab studies are generally limited by sample availability and the variability in natural grain structures, but the proposed methods can help overcome this gap and provide a more consistent method for predicting fractures.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| 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".