Coupled Flow-Geomechanics Surrogate Model with Flexible Boundary Conditions for Geological CO2 Storage Using Fourier Neural Operator Based Gated Recurrent Network
Bibliographic record
Abstract
Abstract Geological carbon storage (GCS) is a critical strategy for mitigating climate change, but coupled flow-geomechanics simulations remain computationally prohibitive. This study presents a Fourier Neural Operator-based Gated Recurrent Network (GRU-FNO), a novel surrogate model that achieves high prediction accuracy, efficiency, and scalability compared to existing CNN-based and FNO approaches. Two dynamic surrogate models, predicting CO2 saturation and pressure, were trained on 820 high-resolution samples from coupled flow-geomechanics simulations. The dataset integrates heterogeneous geological properties, boundary conditions, injection rates, and bottomhole pressure constraints for up to three wells. The proposed GRU-FNO model delivers over 100,000x speedup compared to traditional simulators, achieving mean relative errors of 0.610% (saturation) and 0.083% (pressure) for injection-only phases, and 6.588% (saturation) and 0.241% (pressure) for extended post-injection periods. Its superior performance is attributed to the integration of GRUs for sequential temporal modeling and Fourier layers for spatial feature extraction, which decouples spatial-temporal dependencies efficiently. To enhance generalization, Tversky loss and Intersection over Union (IoU) metrics are employed alongside relative L2 loss, ensuring improved accuracy in plume shape prediction. A normalizer stabilizes convergence for pressure data. Extensive evaluations confirm the model's robustness across unseen geological conditions, enabling real-time predictions and uncertainty quantification for diverse GCS scenarios. GRU-FNO offers a powerful, data-driven alternative to traditional simulators, empowering practicing engineers to make rapid and reliable decisions in geological carbon storage projects.
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) | 0.001 | 0.001 |
| 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".