Parameterized Local Reduced Order Model of Stimulated Volume Evolution in Reservoirs
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
ABSTRACT Real‐time simulation of large‐scale geomechanics problems, such as hydraulic dilation stimulation, is computationally expensive as they must span multiple spatial and temporal length scales, often including nonlinearities and thermo‐hydromechanical processes. This paper introduces a novel local reduced order model (LROM) to enhance computational efficiency for nonlinear and fully‐coupled hydromechanical simulations. The model employs finite element analysis of a two‐dimensional deformable porous media with Drucker–Prager plasticity and stress‐induced permeability enhancement models to describe behavior of sandstone. LROM combines various reduced order models (ROMs), including proper orthogonal decomposition‐Galerkin (POD‐G) to reduce number of degrees of freedom (DoFs), discrete empirical interpolation method (DEIM) to accelerate computation of nonlinear terms, and local POD and local DEIM (LPOD/LDEIM) for further performance enhancements. LPOD and LDEIM classify parameterized training data, obtained from offline coupled full order model (CFOM) runs, into multiple subspaces with similar dynamic features. A new strategy for clustering and classification techniques that align with coupled formulation framework is proposed. The advantages of LROM are demonstrated in a large‐scale application: hydraulic dilation stimulation. LROM exhibits stable, accurate, and efficient online phase, while ROM built with classical POD/DEIM lacks efficiency and stability in Newton–Raphson solver. First, performance of LROM, parameterized by hardening modulus and initial permeability, is evaluated for inputs within training domain. Under CFOMs with DoFs, LROM speed‐up is 400 times. LROM is then parameterized by three inputs, including injection rate and two material properties. Results show that LROM maintains efficiency even for injection rates that extend beyond the training regime.
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.
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 | 0.000 | 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 it