Application of Analytical Proxy Models in Reservoir Estimation for SAGD Process: UTF-Project Case Study
Bibliographic record
Abstract
Summary Steam-assisted gravity drainage (SAGD) has been used successfully for the last 25 years in Canada. SAGD is a thermal recovery process that was invented to extract highly viscous bitumen from deep Canadian oil-sands reservoirs. To date, the original idea of SAGD has not changed greatly since the first pilot test in 1987. However, field operation and reservoir management have been influenced by recent developments in technology. Advanced drilling techniques, automated production control, and real-time data monitoring are gradually transforming the SAGD process into smart fields. As such, improving current history-matching techniques would support fast decision-making requirements significantly in closed-loop reservoir management. This paper recommends analytical solutions for simulations with medium-to-high levels of uncertainty. This shows how an analytical simulator can be improved effectively to mimic the essential features of a SAGD field for fast history matching. Combined with the analytical model recently proposed by the authors, this paper investigates the methodology to apply uncomplicated analytical/mathematical solutions to practical cases. The two underground test-facility (UTF) pilot-test case studies covered in this paper provide a better understanding of the proposed methodology. History matching results show that the current analytical models are suitable to act as proxy models for optimization purposes.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| 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".