Integration of Data-Driven Models for Characterizing Shale Barrier Configuration in 3D Heterogeneous Reservoirs for SAGD Operations
Bibliographic record
Abstract
Abstract Shale barriers may act as flow barriers with adverse impacts on the steam chamber development, as observed in numerous field-scale SAGD projects. Efficient parameterization and inference of such heterogeneities in 3D models from production data remain challenging. A novel workflow for SAGD heterogeneity inference by integrating data-driven modeling and production time-series data analysis is presented. Variation of shale barriers along the directions between the cross-well pair, as well as of the horizontal wellbore, is considered. Based on a dataset gathered from the public domain, a set of reservoir and operational parameters that represent the typical Athabasca oil sands conditions are extracted to build a 3D homogeneous (base) model. The heterogeneous models are constructed by superimposing shale barriers with varying volume, geometry and locations onto the base model. Production data is recorded by subjecting the generated models to numerical simulation. Input features are extracted from the production time-series data, while output parameters are formulated based on the distribution of shale barriers in the generated models. Data-driven models, such as artificial neural network (ANN), are applied to approximate the non-linear relationships between input and output variables, facilitating the inference of shale characteristics. The final outcome is an ensemble of 3D models of heterogeneity that honor the actual SAGD production histories. A decline in oil production is observed when the steam chamber encounters a shale barrier. The proposed workflow can capture the observed production patterns effectively. The proposed methodology is demonstrated to be useful for characterizing shale heterogeneities. A testing dataset is used to assess the consistency between model predictions and the target values. In addition, the production responses corresponding to the characterized heterogeneous models are in agreement with the actual responses. Previous data-driven modeling studies involving 3D heterogeneity inference and SAGD production analysis are limited. The issue of parameterizing a large number of possible heterogeneity descriptions is still challenging. This work presents a preliminary effort to explore this issue. It offers a significant potential to extend most widely-adopted data-driven modeling approaches for practical SAGD production data analysis. The outcomes serve to support the use of data-driven models as complementary and computationally-efficient tools for inference of shale barriers.
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 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| 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) | 0.001 | 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".