Correlating Stochastically Distributed Reservoir Heterogeneities with Steam-Assisted Gravity Drainage Production
Bibliographic record
Abstract
Application of big data analytics in reservoir engineering has gained wide attention in recent years. However, designing practical data-driven models for correlating petrophysical measurements and Steam-Assisted Gravity Drainage (SAGD) production profiles using actual field data remains difficult. Parameterization of the complex reservoir heterogeneities in these reservoirs is not trivial. In this study, a set of attributes pertinent to characterizing stochastic distributions of shales and lean zones is formulated and used for correlating against a number of production performance measures. A comprehensive investigation of the heterogeneous distribution (continuity, size, proportions, permeability, location, orientation and saturation) of shale barriers and lean zones is presented. First, a series of two-dimensional SAGD models based on typical Athabasca oil reservoir properties and operating conditions are constructed. Geostatistical techniques are applied to stochastically model shale barriers, which are imbedded in a region of degraded rock properties referred to as Low-Quality Sand or LQS, among a background of clean sand. Parameters including correlation lengths, orientation, proportions and permeability anisotropy of the different rock facies are varied. Within each facies, spatial variations in water saturation are modeled probabilistically. In contrast to many previous simulation studies, representative multiphase flow functions and capillarity models are assigned in accordance to individual facies. A set of input attributes based on facies proportions and dimensionless correlation lengths are formulated. Next, to facilitate the assessment of different scenarios, production performance is quantified by numerous dimensionless output attributes defined from recovery factor and steam-to-oil ratio profiles. An additional dimensionless indicator is implemented to capture the production time during which the instantaneous steam-to-oil ratio has exceeded a particular economic threshold. Finally, results of the sensitivity analysis are employed as training and testing datasets in a series of neural network models to correlate the pertinent system attributes and the production performance measures. These models are also used to assess the consequences of ignoring lateral variation of heterogeneities when extracting petrophysical (log) data from vertical delineation wells alone. An important contribution of this work is that it proposes a set of input attributes for correlating reservoir heterogeneity introduced by shale barriers and lean zones to SAGD production performance. It demonstrates that these input attributes, which can be extracted from petrophysical logs, are highly correlated with the ensuing recovery response and heat loss. This work also exemplifies the feasibility and utility of data-driven models in correlating SAGD performance. Furthermore, the proposed set of system variables and modeling approach can be applied directly in field-data analysis and scale-up study of experimental models to assist field-operation design and evaluation.
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 | 0.001 | 0.003 |
| Science and technology studies | 0.001 | 0.003 |
| 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".