Predicting gas migration through existing oil and gas wells
Bibliographic record
Abstract
ABSTRACT The ability to accurately predict the probability of fluid migration from depth through existing wells based on known well properties, such as age and depth, would be enormously helpful in understanding how migration pathways develop and the identification of potential migration without extensive field tests. The presence of fluid pathways is an important environmental issue because such pathways allow gas, either naturally occurring methane or sequestered CO2, to move into the atmosphere. In this paper, we explore the ability of various predictive models to forecast gas migration at existing wells in Alberta, Canada, based upon the characteristics of existing deep wells. Alberta was selected as a case study because of the availability of data in an area that has required wells to be tested for pathway development after rig release since 1995. Wells that do not demonstrate pathway development require no further testing until the well is abandoned. We show that accurately predicting fluid migration requires detailed information on well construction, production, and fluid properties, and even then, the models considered in this study misclassify a large number of wells. This suggests other factors may contribute to pathway formation. Of the models investigated, random forests provide the best results on this data set, correctly identifying 78% of the wells used.
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 | 0.001 | 0.002 |
| 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 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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".