Development of Fast Predictive Models for CO2 Enhanced Oil Recovery and Storage in Mature Oil Fields
Bibliographic record
Abstract
Abstract Reservoir modelling tools have played a significant role in designing the subsurface fluid injection, such as CO2 enhanced oil recovery (EOR). However, these models are computationally expensive; they require extensive geological and engineering data that often are not available in the early phase of carbon utilization and storage projects. This work presents the development of fast predictive models and optimization methodologies to quickly evaluate the CO2 EOR and storage operations in mature oil fields. Considerable experience with CO2 EOR and storage has been gained by the petroleum industry. In particular, the Weyburn-Midale project (Canada) is a comprehensive case to show how an oil reservoir could securely store CO2. Employing the Weyburn-Midale project, we developed, trained and tested several types of proxy models in multiple scenarios to assess the performance of the miscible CO2 flood in recovering residual oil, increasing the ultimate oil recovery factor while maximizing the permanent CO2 storage. The history matching of the Weyburn-Midale CO2 EOR model involved 216 well histories (producers and injectors) from 1964 to 2006 using a compositional reservoir simulator. The predominant exploitation scheme was based on an inverted nine-spot pattern waterflooding, water alternating CO2, and consequently CO2 injection. Two simulation data sets were employed at different periods of 1956 through 2006, and 2007 through 2025. Among several proxy models, an artificial neural network (ANN) model proved to accurately estimate features of interest, namely fluid production (oil, water, gas), fluid injection (water, CO2) and the amount of CO2 stored in the reservoir. Additionally, an autoregressive exogenous input (ARX) model was implemented to predict the future outputs in response to a future input. Inspection of the relative estimation error and the model fitness score showed that the proxy model was capable of rapidly reproducing the trend in the validation set satisfactorily. Lastly, we evaluated the transfer of learning from a proxy model, trained to the Weyburn-Midale field (Canada), to assess the performance of CO2 EOR in another mature oil reservoir in Europe (Romania). The application of proxy models under geological and operation uncertainties offers huge reduction in computational time and engineering data requirements. The results from the Weyburn-Midale case study deliver critical insights into the analysis of many process factors and modeling techniques intended to assess the economic limits and long-term performance of CO2 EOR and storage in mature oil fields.
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 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| 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".