Massive High-Fidelity Focal Mechanisms Reveal Detailed Structure of Re-Activated Faults During Hydraulic Fracturing in Western Canada
Bibliographic record
Abstract
Microseismic focal mechanism solutions (FMSs) are essential for understanding reservoir stress changes and rock fracturing during hydraulic fracturing. While machine learning has shown strong performance in seismic data processing tasks, including phase picking and magnitude estimation, as well as identifying P-wave first-motion polarity for moderate to large earthquakes to invert FMSs, its application to microseismic events remains limited. This limitation arises from the distinct characteristics of microseismicity, such as lower signal-to-noise ratios (SNR) and different rupture mechanisms, which challenge the effectiveness of existing polarity pickers. At the same time, the increasing deployment of dense seismic arrays has generated vast amounts of data, creating both the need and opportunity to develop AI models specifically tailored to microseismic events. In response to the challenges of determining the P-wave first-motion polarity for microseismic events, we propose Micro-EQpolarity, a fine-tuned model based on the EQpolarity framework. The model combines convolutional blocks for feature extraction, transformer blocks for feature enhancement, and an MLP network for classification. Utilizing transfer learning, the model is pre-trained on the Southern California Seismic Network (SCSN) dataset and fine-tuned with 19,724 manually selected waveforms from the Tony Creek Dual Microseismic Experiment (ToC2ME) dataset, achieving an accuracy of 99.20%. Applied to seismic data from Western Canada, Micro-EQpolarity successfully inverted 2,519 high-quality focal mechanism solutions, creating a comprehensive catalog that extends analysis to events with magnitudes as low as -1.4. The model identified four distinct FMS types, revealing fine-scale fault structures and detailed patterns of fault reactivation. These findings provide new insights into fault reactivation mechanisms in the NS-Fault cluster and fluid diffusion processes in the NE-Fault cluster. In the NS-Fault cluster, our analysis reveals two possible reactivation mechanisms: higher friction coefficients and enhanced cohesion, with fault reactivation driven by the combined effects of Coulomb static stress and pore-fluid pressure. In the NE-Fault cluster, two-stage hydraulic fracturing facilitated fluid propagation, initially reaching the southwestern part of Fault 1 before spreading to Faults 2-6, with Fault 3 acting as a "transfer station" directing fluid diffusion both eastward and westward through low-dip fault conduits.
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 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".