Stacking Learning for Smart Proxy Modeling in CO<sub>2</sub>–WAG Optimization: A Techno-Economic Approach to Sustainable Enhanced Oil Recovery
Bibliographic record
Abstract
High Resolution Image Download MS PowerPoint Slide Climate change and greenhouse gas emissions are critical global challenges, driving the need for innovative solutions to reduce carbon footprints while meeting energy demands. This study addresses these challenges by optimizing the CO 2 –WAG (water-alternating gas) injection process, a technique that enhances oil recovery while sequestering carbon dioxide in oil reservoirs. The optimization framework integrates machine learning methods with the non-dominated sorting genetic algorithm II (NSGA-II) to simultaneously maximize cumulative oil production and CO 2 sequestration, minimize water production, and ensure economic viability through the net present value (NPV) objective function. The study employs stacking learning to develop smart proxy models, which significantly reduce computational time while maintaining high accuracy in predicting objective functions. These models are trained on a comprehensive data set generated from reservoir simulations, enabling efficient optimization across diverse reservoir conditions. The NSGA-II algorithm is used to generate a three-dimensional Pareto front, representing optimal trade-offs between the conflicting objectives. To facilitate decision-making, a clustering-based approach is introduced, categorizing solutions into groups such as gold, silver, and bronze based on their performance metrics. The results demonstrate the effectiveness of the proposed framework, with the NSGA-II algorithm producing 500 optimal solutions on the Pareto front. Among these, 60 solutions are identified as gold, offering the best balance between technical and economic objectives. Compared to previous studies, the introduced framework significantly improves computational efficiency and prediction accuracy, reducing optimization time while maintaining high precision in the results. This approach not only enhances the accuracy of CO 2 –WAG optimization but also provides a scalable and adaptable framework for sustainable oil recovery and carbon management in various reservoir settings.
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 | 0.000 | 0.001 |
| 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 | 0.001 | 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".