Practical Application of Pareto-Based Multi-Objective Optimization and Proxy Modeling for Steam Alternating Solvent Process Design
Bibliographic record
Abstract
Abstract Steam alternating solvent (SAS) process is a thermal heavy oil recovery technique, where steam and solvent (e.g., propane) are injected alternatively through the same well configuration as in the steam-assisted gravity drainage (SAGD) process. The SAS process is deemed to be more energy-efficient and environment-friendly with less greenhouse gas emission and water usage. However, proper design of the SAS process is challenging as multiple conflicting objectives need to be optimized simultaneously. Conventional optimization methods that aggregate multiples objectives into a single weighted objective are not appropriate. In this work, a novel workflow is developed to identify a set of Pareto-optimal operational parameters for the SAS process. First, a synthetic base model is constructed based on data gathered from the cold lake reservoir. Sensitivity analysis is carried out to determine the main decision variables [e.g. solvent (propane) concentration and duration of solvent injection in each cycle] and to formulate the objective function (e.g., recovery factor and cumulative propane injection). Next, a set of initial SAS models encompassing a wide range of decision variables are generated and subjected to flow simulation, and the corresponding objective functions are computed. Third, a response surface (proxy) model is calibrated to approximate the non-linear relationship between the multiple objective functions and the decision variables. Finally, a non-dominated sorting genetic algorithm II (NSGA-II) is applied as a multi-objective optimizer to obtain a set of optimal decision parameters. The predictions from the base model are corroborated by several previous SAS simulation studies in the literature, where comparable production trends and patterns are observed. It is observed that both the solvent compositions and duration of solvent injection in each cycle would have significant impacts on the objective functions. The proposed hybrid optimization workflow can facilitate the identification of a set of Pareto-optimum solutions with considerable savings in computational costs.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".