A Physics-Informed Spatial-Temporal Neural Network for Reservoir Simulation and Uncertainty Quantification
Bibliographic record
Abstract
Summary Surrogate models play a vital role in reducing computational complexity and time burden for reservoir simulations. However, traditional surrogate models suffer from limitations in autonomous temporal information learning and restrictions in generalization potential, which is due to a lack of integration with physical knowledge. In response to these challenges, a physics-informed spatial-temporal neural network (PI-STNN) is proposed in this work, which incorporates flow theory into the loss function and uniquely integrates a deep convolutional encoder-decoder (DCED) with a convolutional long short-term memory (ConvLSTM) network. To demonstrate the robustness and generalization capabilities of the PI-STNN model, its performance was compared against both a purely data-driven model with the same neural network architecture and the renowned Fourier neural operator (FNO) in a comprehensive analysis. Besides, by adopting a transfer learning strategy, the trained PI-STNN model was adapted to the fractured flow fields to investigate the impact of natural fractures on its prediction accuracy. The results indicate that the PI-STNN not only excels in comparison with the purely data-driven model but also demonstrates a competitive edge over the FNO in reservoir simulation. Especially in strongly heterogeneous flow fields with fractures, the PI-STNN can still maintain high prediction accuracy. Building on this prediction accuracy, the PI-STNN model further offers a distinct advantage in efficiently performing uncertainty quantification, enabling rapid and comprehensive analysis of investment decisions in oil and gas development.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 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".