Constructing Reservoir Flow Simulator Proxies Using Genetic Programming for History Matching and Production Forecast Uncertainty Analysis
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
Reservoir modeling is a critical step in the planning and development of oil fields. Before a reservoir model can be accepted for forecasting future production, the model has to be updated with historical production data. This process is called history matching. History matching requires computer flow simulation, which is very time‐consuming. As a result, only a small number of simulation runs are conducted and the history‐matching results are normally unsatisfactory. This is particularly evident when the reservoir has a long production history and the quality of production data is poor. The inadequacy of the history‐matching results frequently leads to high uncertainty of production forecasting. To enhance the quality of the history‐matching results and improve the confidence of production forecasts, we introduce a methodology using genetic programming (GP) to construct proxies for reservoir simulators. Acting as surrogates for the computer simulators, the “cheap” GP proxies can evaluate a large number (millions) of reservoir models within a very short time frame. With such a large sampling size, the reservoir history‐matching results are more informative and the production forecasts are more reliable than those based on a small number of simulation models. We have developed a workflow which incorporates the two GP proxies into the history matching and production forecast process. Additionally, we conducted a case study to demonstrate the effectiveness of this approach. The study has revealed useful reservoir information and delivered more reliable production forecasts. All of these were accomplished without introducing new computer simulation runs.
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 | 0.001 | 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