Prediction of critical total drawdown in sand production from gas wells: Machine learning approach
Bibliographic record
Abstract
Abstract Sand production is a critical issue in petroleum wells. The critical total drawdown (CTD) is an essential indicator of the onset of sand production. Although some models are available for CTD prediction, most of them are proven to lack accuracy or use commercial software. Furthermore, the previous correlations have not studied the trend analysis to verify the correct relationships between the parameters. Therefore, this study aims to build accurate and robust models for predicting CTD using response surface methodology (RSM) and support vector machine (SVM). The RSM is utilized to obtain the equation without using any software. The SVM model is an alternative method to predict the CTD with higher accuracy. This study used 23 datasets to develop the proposed models. The CTD is a strong function of the total vertical depth, cohesive strength, effective overburden vertical stress, and transit time with correlation coefficients ( R ) of 0.968, 0.963, 0.918, and −0.813. Different statistical methods, that is, analysis of variance (ANOVA), F ‐statistics test, fit statistics, and diagnostics plots, have shown that the RSM correlation has high accuracy and is more robust than correlations reported in the literature. Moreover, trend analysis has proven that the proposed models ideally follow the correct trend. The RSM correlation decreased the average absolute percent relative error (AAPRE) by 12.7% compared to all published correlations' AAPRE of 22.6%–30.4%. The SVM model has shown the lowest AAPRE of 6.1%, with the highest R of 0.995. The effects of all independent variables on the CTD are displayed in three‐dimensional plots and showed significant interactions.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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 teacher head, 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".