Automated Surveillance of Subsurface Wellbore Integrity in a Heavy Oil Field using Passive Seismic Systems
Bibliographic record
Abstract
Abstract Continuous subsurface surveillance is important for heavy oil in-situ recovery processes where induced stresses in the overburden can compromise the integrity of the wellbores. Wellbore failure may lead to the undesirable loss of fluids into the overburden. In recent years, there has been a rapid growth in the use of Passive Seismic monitoring systems to aid in subsurface surveillance activities, with the ultimate goal of detecting potential integrity issues as early as possible. However, the massive volume of data recorded by these instruments is time-consuming and error-prone to process manually. This paper introduces EMMAA (ExxonMobil Microseismic Automated Analyzer), an automated workflow to reliably process continuous microseismic data, detect subsurface integrity issues, and ultimately reduce the latency in responding to wellbore integrity issues. A novel cloud-based technology for managing microseismic data is briefly described. The seismic waveforms, recorded by a distributed array of geophone receivers, are automatically analyzed to determine the type and source of subsurface disturbances (‘events’). First, novel frequency-domain and deep learning analyses are used to distinguish noisy signals from the seismic waveforms such as compressional and shear waves produced by the events. Next, the location of the event is calculated and its seismic attributes are computed. Finally, the type and severity of the seismic event are determined by an event classifier. The performance of the automated workflow is examined in the context of accurate detection of casing failures in a heavy oil Cyclic Steam Stimulation (CSS) application. The event features that distinguish casing breaks from other seismic events are described. It is shown that the methodology is able to achieve a high detection rate when back-tested against a historical data-set of known casing failures. False positives are adequately contained by preventing waveforms of electrical or mechanical noise from being processed. In a production environment, the event processing workflow is run on distributed servers and analyzes triggered seismic data in real-time. Depending on the severity of the microseismic events detected, operators are immediately alerted via email and text messages, so that remedial actions may be swiftly initiated. The utility of this integrated system is further exemplified by the massive reduction in the time taken to detect casing breaks—from up to 36 hours historically, down to less than one hour in most instances. Extensions of EMMAA that enable the detection of a wide variety of microseismic events are also discussed. These events include surface casing slips that occur at the casing shoe, cement de-bonding events near the wellbores, and events indicative of potential fluid migration in the overburden.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 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".