Risk Management and Optimization in Real-Time Noncondensable Gas Co-injection under Economic Uncertainty
Bibliographic record
Abstract
Summary When the oil price is volatile, maximizing steam allocation and noncondensable gas (NCG) is essential to ensuring a profit but reducing risk. Minimizing risk entails moving the distribution of lower tail returns closer to the expected return. Thus, there is a risk-reward tradeoff during optimization. Real-time risk-return optimization with first-principle models is computationally demanding. Sibaweihi et al. (2019) presented a real-time steam-assisted gravity drainage (SAGD) recovery optimization with varying steam availability workflow. The workflow cannot handle uncertainty, and the data-driven model may forecast out of the physical range of the model output parameters. As a result, data-driven process modeling incorporating physical or operational constraints and an optimization problem formulation that references a decision-makers' metrics to a benchmark is crucial. This study proposes data-driven input-output normalization to incorporate operating constraints based on their physical range. The workflow includes model training updating based on the concept of forgetting factor to adapt the data-driven model to the current state of the reservoir. A robust optimization (RO) problem scheme in which economic risk is mitigated by formulating the objective as a tradeoff of expected returns and risk is managed in real time. A modified Modigliani’s risk-adjusted performance has been implemented to minimize the possibility of selecting the wrong optimal risk-return tradeoff of nonsymmetric return realizations in this work. In this work, the risk is quantified through variance, minimum, semivariance (down side risk), and conditional-value-at-risk of the returns realizations because of oil price volatility. Application of the proposed workflow on a synthetic reservoir with steam NCG co-injection showed the data-driven calibrated model forecast performance shows a reasonable agreement with the synthetic reservoir throughout the optimization period. In addition, the optimization study with the proposed workflow also showed a net present value (NPV) increase of approximately 25–77% and a decrease in the cumulative steam-oil-ratio (cSOR) from 4.5 to 6.7% compared with the continuous steam injection base case. The reduction in cSOR indicates a lower steam requirement. An increase in methane sequestered demonstrates workflow ability to reduce greenhouse gas emissions while improving SAGD NCG co-injection key performance indicators.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 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".