Probabilistic Forecasting of Horizontal Well Performance in Unconventional Reservoirs Using Publicly-Available Completion Data
Bibliographic record
Abstract
Abstract In this paper, we present a methodology to predict the performance of horizontal gas wells in unconventional reservoirs using publicly available completion data. Our process combines public domain data with statistical analysis and probabilistic simulation methods to forecast well performance without a detailed reservoir characterization. We have tested our methodology using a 425-well dataset from the unconventional Montney resource play in British Columbia, Canada. We believe this workflow can be applied to other resource plays with similar data. In our SPE Paper 167154 [1], we determined the sensitivity of production performance to completion parameters using multivariate regression analysis on the same 425-well dataset from the Montney formation. We found that the number of fracture stages and the number of perforation clusters per stage were the most influential predictors of well performance. In this paper, we discuss how we combined the regression analysis results with probabilistic methods to predict well performance. The model converts the deterministic regression coefficients into probabilistic distributions to account for parameters not considered in the original regression analysis, including reservoir properties. The results of our study show that by using this model, we can match the range of actual well performance outcomes with a 95% confidence. Considering the importance of shale gas resources to the North American energy supply and the difficulty of characterizing shale gas reservoirs, this methodology offers a distinct advantage by providing a predictive model for well performance without the need for a detailed reservoir characterization. This also could be a beneficial tool to use in scoping studies where high-level, rapid evaluation is required.
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 | 0.003 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".