Smart Learning from Past Data Yields 50% Incremental Oil Production
Bibliographic record
Abstract
Abstract This paper presents a novel methodology for re-developing mature fields and increasing their production and reserves. It has been successfully applied to Butte Voluntary Unit, Canada, where it yielded a 50% production increase. Such upside results from a rational and massive search for the best re-development plan. The method uses a reliable production forecast tool specifically developed and calibrated for the given field. This is based on a smart learning process from historical production data, constrained by reservoir and well physics. The tool is not only reliable, it is also very fast: any given production forecast can be played within seconds. A powerful search engine is used to generate, select, adjust, and compare 100,000s potential field development plans ("scenarios"). Those are ranked for best Net Present Value, within different sets of financial and technical constraints ("strategies"). The full process was successfully applied to Butte Voluntary Unit, a water flooded mature field in Western Canada. A comprehensive range of strategies was explored, enabling robust decisions with respect to future oil price assumption, and ranking investment priorities. After playing 600,000 different possible production scenarios, a financially optimized re-development plan was identified involving four conversions out of 69 candidates, and the drilling of four new infill wells out of 20 possible sweet spots, as well as an upgrade of the field injection capacity. This re-development plan was actually implemented on the field and became operational during the summer of 2011. Since then, oil production has soared as planned and incremental 5 year-reserves about 50% above the baseline are being demonstrated. This project illustrates that historical production data of mature fields have plenty to tell, and demonstrates how they can be smartly used to engineer the right re-development path and unlock considerable upside with controlled investment and low risk. Mature fields are gaining increasing importance within most oil & gas companies’ portfolios. Relying on several field proven successes, the technology presented in this paper is becoming a reference tool for re-developing mature fields.
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 | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".