Unlocking Completion Design Optimization Using an Augmented AI Approach
Bibliographic record
Abstract
Abstract An Augmented AI approach has been developed to optimize completion design parameters and access the full potential of unconventional assets by leveraging big data sculpting, domain-induced feature engineering, and robust and explainable machine learning models with quantified uncertainty. This method unlocks the full potential of a well using completion design parameters optimization that considers all the factors that impact well performance, geological characteristics, well trajectory, spacing, etc. By leveraging basin-level knowledge captured by big data sculpting with the use of uncertainty quantification, Augmented AI can provide quick and science-based answers for completion optimization, and also assess the full potential of an asset in unconventional reservoirs. By leveraging computer vision and natural language processing techniques, unstructured data from various sources were deciphered, combined and organized into a structured database. Imputation techniques were used to fill the gaps of missing data. With the Augmented AI approach, the median accuracies of IP and EUR predictions for new drills is around 90%, which often outperforms industry-standard type curving methods. With the explainable machine learning (ML) model, the direct impact of completion design parameters on well performance is deconvoluted among other parameters, such as engineering and geological attributes. The prediction also comes with an 80% confidence interval to quantify the prediction uncertainties, which allows for better risk management and confident business decision making. With the ML model and given economic inputs and metrics, many sensitivity analyses are performed to evaluate optimized completion design parameters. The proposed Augmented AI approach has been deployed to Eagle Ford wells.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| 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) | 0.004 | 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".