Practical application of neural networks in assessing completion effectiveness in the Montney unconventional gas play in northeast British Columbia, Canada
Bibliographic record
Abstract
Abstract A methodology leveraging Neural Networks has been developed to identify completion optimization potential in the development of a mature Montney Gas Asset providing well specific and field-wide completion effectiveness analysis. This paper presents an approach that can be applied to obtain a better understanding of the relationship between practices used in hydraulic fracturing and well performance, and to highlight methods to optimise well production, based upon a dataset of 56 wells, all completed in the same stratigraphic zone of the Upper Montney, within a developed area of 200 km2 in NE British Columbia. A combined Principal Component analysis — Artificial Neural Network modelling technique (PCA-ANN) has been used in this work to identify key completion-related drivers of well performance, along with some geologically related indicators, and apply neural network modelling to predict well performance as defined by estimated ultimate recovery (EUR), from a “matrix” of completion related data. The results can be used to identify optimal hydraulic fracture design parameters for new wells to enhance production, and potentially also wells that may be candidates for recompletion. Eight key completion-related variables are identified by the PCA method from a total of 31 considered: these include geologically related ones of breakdown pressure (BrdPr) and instantaneous shut-in pressure (ISIP), along with engineering/operational parameters including cluster spacing, perforation number, proppant amount, sand concentration, fluid volume and pumping rate. Using these variables in a sensitivity analysis to measure/predict the EUR shows that for the dataset studied, the dominant production drivers are cluster spacing and proppant amount, which are related to controllable aspects of the hydraulic fracturing process. When applied to evaluate existing producing wells and optimise completions, the approach identifies the lower performing wells that potentially could have better performance if their completion parameters were optimised. Furthermore, the PCA-ANN technique indicates how to achieve optimal results by identifying which parameters should be changed and by how much. As such, this predictive model delivers a series of charts for selecting and evaluating different completion parameters and designs.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".