RNN-based CO2 minimum miscibility pressure (MMP) estimation for EOR and CCUS applications
Bibliographic record
Abstract
Accurate estimation of minimum miscibility pressure (MMP) is crucial for assessing the efficiency of most miscible and immiscible processes, specifically CO 2 -based enhanced oil recovery (EOR) methods and Carbon capture utilization and sequestration (CCUS). The experimental procedure for MMP prediction is often time-consuming and costly. On the other hand, the empirical models that have been historically used could work based on limited input parameters, ignore the importance of others and are not necessarily accurate. The novelty of the current study is using an explainable deep-learning approach, Recurrent neural network (RNN), to train a model using a multi-dimensional (22 features) dataset with 544 rows of data. The Dataset comprises mole fractions of injected gas (pure and impure CO 2 ). Out of those features, eight subsets of parameters (labelled X_1 to X_8) were used to develop models. The multi-dimensionality of the dataset makes it suitable to study the effects of various parameters on MMP, specifically in conditions of interest to CCUS-EOR applications. Among the multiple inputs tested, the model trained with X_1 and X_8 input parameters (including mole fraction of different hydrocarbon and nonhydrocarbon components and reservoir temperature) resulted in the most accurate estimations of MMP (R 2 = 0.99). To further enhance the explainability of the model, feature importance and shapely values analysis were conducted on the developed models, and the impact of each input feature on MMP was elaborated. Temperature, volatile/intermediate, and nonhydrocarbon components are the most influential parameters depending on the subset of parameters chosen. Moreover, the developed model using X_8 inputs performed significantly better (37 % more accurately) than three well-known empirical models from the literature.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 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 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".