Time Series Analysis as an Alternative for Decline Curve Analysis in Unconventional Plays
Bibliographic record
Abstract
Abstract Quick and reliable forecasting of production data is still challenging in unconventional plays, even with the variety of modifications proposed to Arps decline curve analysis (DCA). Machine learning revealed promising results when enough samples were accessible to train and validate the predictive model. However, this black-box model is inaccurate for unseen samples, challenging to generalize, and requires too much data. We attempted to present an alternative procedure to solve this problem —a fast and reliable method outperforming current approaches. In this study, we implemented univariate and multivariate times series analysis (TSA) to forecast production rate in the different scales (wellbore, field, and pad scales) where DCA failed to provide an appropriate fit beforehand. TSA is straightforward and enables recognition of the pattern in observation samples. Cyclic fluctuation due to seasonal changes in price and operational hours can be detected and indirectly considered in time series models like ETS (Exponential Smoothing) and ARIMA (Auto-Regressive Integration Moving Average). However, for the direct considerations of these critical parameters, Vector Auto-Regressive (VAR) models have the flexibility and ability to be configured with multiple variables and can capture more complexities. This simple and quick procedure applies on any scale from the wellbore to the field scales. To evaluate the performance, the TSA method has been applied and tested on data from the Duvernay shale in Western Canada. On the wellbore scale, modified DCA models forecast production rate with over/underestimation, even where enough observations are available, and if the well has shown a declining trend in the production. In the same wells, TSA provides a better fit and outperforms the DCA. In the field and pad scales, DCA could not draw a fitting model as production had a growing trend due to ongoing field developments. In contrast, TSA could realize the trend in the production data and successfully create the forecasting model. Price and production hours were added to the time series model as influential features on production. The model could forecast all the parameters simultaneously. In sum, TSA is a reliable and flexible alternative for DCA and can be implemented on production data in any scale.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 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".