Utilization of Time-Lapse Seismic Data to Semi Quantify Residual Oil Saturation by Karhunen-Loeve Transform and Neural Artificial Network during CSS
Bibliographic record
Abstract
Abstract Due to the nature of Cyclic steam stimulation (CSS), a steam chamber generated by CSS is not as consistent and detectable as SAGD's (steam assisted gravity drainage) one, which makes it challenging to predict the residual oil distribution and steam-unswept zones. Time-lapse seismic are a valuable and important method to monitor steam injection and soaking. During CSS process, rock-fluid densities and velocities are changed significantly during steam injection and oil production. These changes make time-lapse seismic monitoring feasible. The previous approaches were mainly about fluid contact determination, steam chamber supervision and field history matching. In this study, a new method using time-lapse seismic attribute differences is developed to semi quantify residual oil saturation and determine steam-unswept zones during thermal recovery. Twenty seismic attributes derived from time-lapse seismic data, which can sensitively reflect oil saturation changing, are selected as basic seismic attributes to quantify fluid saturation changes. The relationship between fluid properties and seismic attributes is complex and ambiguous. Only one seismic attribute difference between base data and monitored data is insufficient to reflect reservoir properties changes during thermal recovery process. In order to improve the accuracy of prediction, combinations of multiple seismic attributes differences are used to reflect rock-fluid properties changes such as oil saturation changes. The Karhunen-Loeve Transform is applied to squeeze twenty attributes into four new attributes by eliminating attributes correlation. Based on generated seismic attributes, the artificial neural network is implemented to illustrate the oil saturations changes, which is also constrained by the measured fluid reservoir data. Four attribute differences are tested to demonstrate the oil saturation changes. The best result only can partially match field production data. However, the residual oil saturation distribution generated by the proposed method can match the majority features of the field production data. This approach provides a reliable and valuable way to help operators monitor a CSS process and design infill well drilling.
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 | 0.000 |
| 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".