Development of Effective Carbonate Steamflood Strategy Using Full-field Simulation Models and Machine Learning Algorithms
Bibliographic record
Abstract
Summary Steamflooding is a widely used thermal method for recovering heavy oil from sandstone reservoirs. In carbonates, the implementation of steamflooding usually demonstrates higher steam-oil ratio and lower oil recovery. The key performance problem is a poor sweep efficiency of steam injection. It is fully confirmed by actual results of steamflooding in the Permian – Carboniferous carbonate reservoir of the Usinsk field located in Northwest European Russia. The reservoir has the largest heavy oil remaining reserves in carbonates of Russia and Europe. Since the viscosity of its oil is more than 700 mPa*s, in some areas of the reservoir, there is a steam injection at ~300°C and ~10 MPa, which are being used for almost 40 years mostly via vertical wells. However, the current oil recovery numbers of the areas are estimated only between 12 and 15 %. It is assumed that these oil recovery efficiencies could be improved with optimized reservoir management with advanced numerical modeling to evaluate the additional oil production and steam-oil ratio and figure out the best further steamflooding strategy. For many years, an exclusively deterministic approach was used to simulate the reservoir, which significantly limited the possibilities for modifying the steam injection process. That is why, the search for alternative approaches of reservoir modeling, which ensure prompt obtaining realistic forecasting of its development, was relevant. In this work, a novel forecasting technology termed an adaptive approach that combines the full-field geological and hydrodynamic models with the unique machine-learning algorithm based on fuzzy-logic functions was implemented. The obtained results of the adaptive approach application demonstrated the improvement in understanding of the reservoir thermal performance and in making the practical recommendations of cost saving and oil production increase.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".