Multivariate Analysis Using Advanced Probabilistic Techniques for Completion Design Optimization
Bibliographic record
Abstract
Abstract Efforts to identify optimal completion technology and design parameters are complicated by the compounding impacts of broad statistical variability in operations, reservoir/fluid and completion/wellbore design. There are several analysis approaches available to identify and optimize key completion design parameters. Each approach offers limited insight on its own, but combining a set of approaches into a disciplined methodology can collectively present a unique understanding of optimal completion technology and design. Traditional parallel coordinates visualizations offer strong visual cues of correlations, but in datasets with broad statistical variability they often convey a lack of correlation and fail to distinguish statistical trends. Statistical methods are unique in their ability to provide insights into non-continuous correlations where upper and lower thresholds exist; however, they are not effective at providing a deterministic measure of an individual input's effect on an outcome. Modelling and regression analysis can provide a means to measure the effect of several input variables on an outcome, but lack transparency and are often perceived as a "black box" solution with outcomes that have limited supporting evidence, or supporting evidence that is difficult to understand. We demonstrate a robust multivariate analysis methodology using a hybrid approach involving the principles of parallel coordinates, dimensional normalization and advanced probabilistic techniques. One of the benefits of this approach is that it can yield statistically significant insights on sample sets as small as 80 wells. The methodology involves six steps that offer transparency to the analysis and facilitate a narrative of understanding: Selection of a performance measure setAnalogue well selectionSelection of numerical completion design input parametersParallel Coordinates Distributions: input parameter impact analysisEvaluation of analogue fitness and subset selectionInput Optimization Distributions: input optimization process We found that the use of consistent dimensional normalization on both inputs and outcomes better isolates the impact of an input parameter. The shape and position of parallel coordinates distributions can illustrate nuances of impact that are lost in other multivariate approaches. In this paper we apply and test this methodology on three major resource plays in the Western Canadian Sedimentary Basin: a gas play, a liquids-rich gas play and an oil play.
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 | 0.008 | 0.016 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 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".