Boosting Reservoir Prediction Accuracy: A Hybrid Methodology Combining Traditional Reservoir Simulation and Modern Machine Learning Approaches
Bibliographic record
Abstract
This study presents a comprehensive investigation into the application of reservoir simulation and machine learning techniques to improve the understanding and prediction of reservoir behavior, focusing on the Sarir C-Main field. The research uses various data sources to develop robust reservoir static and dynamic models, including seismic cubes, well logs, base maps, check shot data, and production history. The methodology involves data quality control, log interpretation, seismic interpretation, horizon and surface interpretation, fault interpretation, gridding, domain conversion, property and petrophysical modeling, well completion, fluid model definition, and rock physics functions. History matching and prediction are performed using simulation cases, and machine learning techniques such as data gathering, cleaning, dynamic time warping (DTW), long short-term memory (LSTM), and transfer learning are applied. The results obtained through the Petrel simulation demonstrate the effectiveness of depletion strategy, history matching, and completion in capturing reservoir behavior. Furthermore, the machine learning techniques, specifically DTW and LSTM, exhibit promising results in predicting oil production. The study concludes that machine learning approaches, such as the LSTM model, offer distinct advantages. They require significantly less time and can yield reliable predictions. By leveraging the power of transfer learning, accurate predictions can be achieved efficiently when limited data are available, offering a more streamlined and practical alternative to traditional reservoir simulation methods.
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 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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".