Bibliographic record
Abstract
Digitalization of underground excavations has resulted in increasing access to large amounts of data for rock engineering professionals. Data-driven approaches, such as machine learning algorithms, present an opportunity to aid data interpretation. At Garson Mine, a 112-year-old nickel mine near Sudbury, Canada, the microseismic database is used to manually calibrate a complex mine-scale finite difference model, which is in turn used to assess seismic risk to inform mine operations and scheduling. The manual model calibration is tedious and time consuming. This research proposes a Long-Short Term Memory (LSTM) network to assist in finite difference model calibration by forecasting the stresses in the model. The LSTM is trained using the microseismic database, the geology and geomechanical parameters from the existing FLAC3D model. Two LSTM networks are developed and compared for Garson Mine: one that predicts the principal stresses and another that predicts the six-component stress tensor at each zone centroid in the FLAC3D model. Various LSTM network hyperparameters were analyzed to determine the optimal architecture for the two sets of targets, including: input encoding and pre-processing, training solver, network layer architecture, and cost function. Architectures were chosen based on three performance metrics: the corrected Akaike Information Criterion (AICc), coefficient of determination (R2), and percent capture (%C). This study found that similar LSTM network architectures are able to adequately predict both principal stresses and the complete stress tensor, however, the ensemble variance was larger when predicting the complete stress tensor. When predicting the principal stresses, AICc was -59.62, R2 was 0.996, and %C was 97%, and when predicting the six-component stress tensor AICc was -45.50, R2 was 0.997, and %C was 80%. This research represents progress towards continuous, automated calibration of complex numerical models, whereby earlier and more accurate forecasts of changes in stress conditions will allow earlier intervention and reaction to challenging stress environments, leading to increased safety of excavations and mine personnel.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
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".