Real-Time Steam Allocation Workflow Using Machine Learning for Digital Heavy Oil Reservoirs
Bibliographic record
Abstract
Abstract Thermal oil recovery processes are widely used to extract bitumen and heavy oil. Traditionally, a predetermined amount of steam is allocated to various injector wells using reservoir model based open-loop optimization. This practice can face a number of constraints including interruptions in well operations and/or surface facilities. Given that steam supply costs are a significant contributor to the overall production cost of heavy oil, dynamic and intelligent allocation of steam to various wells in the oilfield deserves further attention. In this study, we propose a proactive steam allocation workflow that can learn the effect of steam injection pattern on heavy oil recovery by using machine learning. We employ data analytic predictive models for the short-term forecast of the key performance indicators (KPIs). Model parameters are updated continuously by using a moving horizon approach that considers selected prior data including real-time measurements. An objective function containing predicted KPIs is maximized by manipulating the amount of steam allocated to various injectors in the oilfield. The workflow is repeated on a daily basis for continuous optimum steam allocation. A case study is performed by using a 3D reservoir model that represents a segment of the steam-assisted gravity drainage (SAGD) operation. For each well, the polynomial model is identified in the time-domain to forecast KPIs. The effectiveness of the proposed method is evident from the results as NPV is increased by almost 25% – 50% compared to the base case with a constant steam injection pattern in all cases studied. Due to the efficient use of available steam, the steam-to-oil ratio is reduced significantly. An adaptive and flexible steam supply is also honored by the proposed workflow, ensuring maximum efficiency of the oil recovery process. Practical implications of the proposed intelligent steam allocation workflow will be consequential in improving the operational efficiency of the digital heavy oil assets, thereby increasing profits and reducing the carbon footprint.
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 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| 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".