A Novel Particle-Tracking Based Proxy for Capturing SAGD Production Features under Reservoir Heterogeneity
Bibliographic record
Abstract
Abstract Steam-assisted gravity drainage (SAGD) process is strongly impacted by the distributions of shale heterogeneities, which tend to impede the development of a steam chamber and potentially reduce oil production. Detailed compositional flow simulators are often employed to assess the impacts of reservoir heterogeneities on the steam chamber growth and to forecast production. To reduce the computational costs, machine learning techniques have been widely proposed in recent studies to develop various data-driven models. In all cases, a training data set consisting of many (>1000) synthetic simulation cases are required to achieve reasonable accuracy, especially in the case of 3D models. A suitable training data set should be large enough to sufficiently span the parameter space without exhaustively sampling cases with similar production characteristics. A novel physics-based proxy is proposed to approximate key SAGD production features in heterogeneous reservoirs. A simplified flow model based on particle-tracking principles is developed to approximate how steam would travel in a three-dimensional heterogeneous reservoir. First, a large number of steam particles are launched, and the particles’ transition probabilities to nearby cells are calculated based on Darcy's law and energy balance: the directions of particles’ movement are governed by the intrinsic permeability, while the energy released by the steam particles upon condensing is used for heating the bitumen. Next, it is assumed that the steam particles would become immobile (instead of draining down) upon condensing. The temperature of nearby cells is updated after each time step. The process is repeated, and new steam particles are launched to represent a continuous injection. The locations traveled by the steam particles are tracked to quantify the chamber development as a function of time. A set of 3D synthetic models using representative petrophysical properties and operating constraints extracted from Suncor's Firebag project is tested. The predicted steam chamber profiles match reasonably well to those obtained from detailed compositional simulations. As expected, shale barriers that are located in the near well region would have a more pronounced impact. Increasing the number and/or size of the shale barriers may delay the steam chamber development. However, the run time for this simplified model is much less than the conventional simulations. This work provides a novel and fast particle-tracking based method to approximate the effects of complex shale heterogeneities on SAGD production and chamber development. It can be used to effectively screen a large number of shale heterogeneity realizations and to categorize them into different groups in accordance to their steam chamber development characteristics. It presents a significant potential to be integrated with many other data-driven approaches, such as cluster analysis, to visualize the (dis)similarity among a set of shale barrier configurations.
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".