Passive‐seismic event‐classification techniques applied to heavy‐oil production from Cold Lake, Alberta
Bibliographic record
Abstract
The CREWES Project at the University of Calgary is conducting research with Imperial Oil Limited concerning passive seismic monitoring of heavy oil production wells at Cold Lake, Alberta, Canada. This monitoring is required to proactively detect mechanical breakdowns in producing wells that can arise from the cyclic steam stimulation enhanced recovery process used to extract the viscous bitumen. These breakdowns induce microseisms that are recorded at the surface, resulting in the creation of a microseismic event file. Noise vibrations generated by pump rods or passing vehicles also trigger the passive seismic monitoring system and are recorded. Noise events comprise approximately 99% of all microseismic event files generated, but are generally not of interest and are usually discarded. The current classification software on this monitoring system incorrectly classifies a large portion of these files, resulting in many noise events being classified as microseisms worth further investigation. The objective is to develop accurate passive seismic signal analysis and classification algorithms capable of precisely distinguishing between microseismic event files warranting further investigation, also referred to as “good” event files, from noise event files that are generally not of interest. Compared to noise events, many “good” events generally have lower frequency content, shorter P-wave event-lengths, and flatter time-domain characteristics. Based on these observations, methods involving frequency-filtering, event-length detection, and statistical analysis are developed and combined into a MATLAB graphical user interface. Testing of this application on thousands of microseismic event files yields a classification accuracy between 96% and 99%, depending on the tested dataset. We aim to implement some of the developed algorithms on Imperial's passive seismic monitoring system at Cold Lake in the future, which would likely result in significant time-savings.
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 | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 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".