How Does the Incorporation of Engineering Knowledge Using Fuzzy Logic during History Matching Impact Reservoir Performance Prediction?
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Abstract Population-based optimization algorithms are shown to be excellent candidates for improving the speed and solution diversity of history matching and optimization workflows, based on their successful track records for solving real-world problems. The incorporation of reservoir engineering knowledge within these workflows, however, has been somewhat neglected. In particular, there is a lack of capability for guiding the optimization algorithms to specific regions of the search space. In a previous study, we introduced a framework for helping reservoir engineers incorporate their knowledge into history matching and optimization frameworks, by coupling a rule-based fuzzy system with a population-based sampling method. The question is how the use of this type of information in history matching affects the performance of the reservoir study during the prediction stage. This paper investigates the effect that the incorporation of reservoir engineering knowledge during the history matching of the Teal South model production data has on reservoir performance in the prediction stage. Two scenarios are considered. In Case I, we augment the history matching with reservoir engineering knowledge and then produce a forecast. In Case II, production data is history matched using differential evolution (DE), without fuzzy-logic-based engineering knowledge, then a forecast is produced The results show that incorporating engineering knowledge of the reservoir under study during the history matching process can significantly reduce the uncertainty in the forecast, compared with the case where unrealistic parameter value ranges are used.
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.
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 it