Prediction of maximum slug length considering impact of well trajectories in British Columbia shale gas fields using machine learning
Bibliographic record
Abstract
In this study, the severity of slugging is assessed by predicting maximum slug lengths (MSL) quickly using the random forest (RF) algorithm based on the geometric features of well trajectories for a shale gas field. Severe slugging is one of the critical issues production engineering-wise because it causes operation shut-down. Thus it should be predicted for proactive measurements. A total of 5033 well trajectories were acquired from the northeastern area of British Columbia, Canada. The well trajectories are described using ten geometric features such as X, Y, and Z lengths in the Cartesian coordinate system, inclination, azimuth, and the other five. The 5033 well trajectories are grouped using the k-medoids clustering algorithm. The well trajectories in each group and the groups are compared visually to see if the ten features are representative enough to describe the geometric features of the well trajectories. The ten geometric features of the well trajectories are used as the input for RF, and MSL, which represents the severity of slugging, is used as the output for RF. The output data is simulation results by a pipe flow simulator, OLGA. The trained RF model provides the satisfactory prediction performance of MSL (R values, 0.866 and 0.857 for training and test data, respectively). In the trained RF model, X, Y, and Z lengths have the most significant importance among the ten geometric features. Because it is impractical to simulate all well trajectory scenarios by OLGA, the MSL values are projected onto a 3-dimensional map of which axes are X, Y, and Z lengths to visualize the trend of MSL. The 3-dimensional map showing the relation between MSL and the geometric features of well trajectories can be utilized as a quick reference to avoid severe slugging in designing well trajectories.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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".