Assessment of CO2 storage potential in reservoirs with residual gas using deep learning
Bibliographic record
Abstract
Abstract CO 2 injection into the underlying water leg of depleted hydrocarbon reservoirs is a desirable option for carbon storage as demonstrated by existing industrial-scale storage projects in these geologic environments. This study sheds light on the effect of residual methane on the CO2 storage efficiency as a screening criterion for selecting a water-bearing zone of a depleted gas reservoir to store CO2. Using compositional reservoir simulations, we have evaluated the impact of residual methane on the injectivity, operational pressure, and long-term CO2 trapping efficiency during injection and postinjection stage in a reservoir model representative of the so-called “HC sand” gas reservoir in the High Island 24L field located in the offshore Texas State Waters. Results suggest that the presence of residual hydrocarbon gas negatively affects CO2 residual and dissolution trapping because it enhances the injectivity and pressure management arising from the increased mobility of CO2 plume in the vicinity of the injection zone due to its mixing with the resident residual hydrocarbon gas. We further investigate the application of artificial neural network (ANN)-based proxy models for fast-track modeling of CO2 storage in geologic structures associated with depleted gas reservoirs, aiming at the prediction of CO2 trapping efficiency. We then use the developed ANN model to perform Monte Carlo simulations for quantifying the uncertainty of geologic and reservoir parameters on CO2 trapping efficiency in these formations. It becomes evident that the residual hydrocarbon saturation is a key screening criterion for the storage site selection. The developed data-driven model can offer a robust and fast tool for screening the water-bearing zone of the depleted gas reservoirs by evaluating the efficiency of CO2 storage.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| 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".