Retrospective Validation of the Robustness of Reservoir Simulation Predictions
Bibliographic record
Abstract
Abstract Reservoir simulation projects are ubiquitous across the oil and gas industry. A less common practice is retrospective validation of the accuracy and robustness of the original model's predictions. This paper highlights the importance of validating previous simulation work with field data in order to test predictability and acquire more confidence in future simulation work. A fully implicit coupled wellbore-reservoir simulator was used to history match the performance of four steam-assisted gravity drainage (SAGD) well pairs after one year of operation. The purpose of this effort was to build a representative model that mimicked the observed field behavior and captured the key performance drivers such as reservoir quality, completion type, and operating strategy. A representative history matched model was achieved with an overall accuracy within 9.5% of actuals after one year of operation. This model was used to forecast well pair performance after three years. After three years of field operation, the predicted simulation forecast was compared against the actual field data. The accuracy and robustness of model's predictions remained valid and improved to within 7.5% of actuals after three years of operation. For two out of the four well pairs, the observed trends between the actuals and the simulation appeared to deviate due to completion type and operating strategy changes that occurred after the original history match was completed. Once these changes were reflected in the simulation model, predictability was restored and improved reaching an accuracy within 4.7%. This paper aims to deliver two key learnings and best practices. First, a coupled wellbore-reservoir simulation approach was successfully applied to build a representative model that captures the key performance drivers and observed field behavior. Second, a retrospective validation of the model's predictions was completed and resulted in more accurate, robust, and confident performance predictions. These robust models can be used to better understand, forecast and optimize the productive potential of oil and gas operations over their life cycle.
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 | 0.005 | 0.017 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| 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".