Super-Resolution Initialization of High-Fidelity CFD Simulations for Pebble-Bed Reactors

Abstract

High-order CFD simulations provide detailed resolution of the heterogeneous interstitial flow in pebble-bed reactors, but their computational cost is high, especially during the initial flow-development period required to reach statistically stationary conditions. This work investigates the use of a Super-Resolution Graph Neural Network (SR-GNN) to improve the initialization of high-order NekRS simulations. Lower-order P = 2 velocity fields are used as inputs to reconstruct higher-order representations, which are then used as initial conditions for P = 7 restart simulations. The approach is evaluated using a 146-pebble bed at Re = 1000, Re = 2500, and Re = 5000, with pressure-drop convergence used as the main figure of merit. The SR-GNN models were trained using paired low- and high-order snapshots and were first evaluated through qualitative inference comparisons. High-order restart simulations showed that, for Re = 1000 and Re = 2500, the SR-GNN initialized cases produced pressure-drop histories similar to direct restarts from true P = 2 fields. For Re = 5000, however, the super-resolved field restart approached the statistically stationary P = 7 pressure-drop range faster than both the direct P = 2 restart and the reference P = 7 simulation initialized from a uniform velocity field. The trained Re = 5000 model was also applied to a larger 1568-pebble bed, demonstrating qualitative applicability of the workflow to a significantly larger packed-bed geometry. These results indicate that SR-GNN-based initialization is a promising strategy for reducing high-order flow-development cost, while also motivating further work on broader Reynolds-number and geometry generalization.

Accelerating high-fidelity gyrokinetic fusion simulations with iGENE
Gabriele Merlo, Victor Artigues, Carl-Martin Pfeiler +1
arXiv24 Oct 2026PreprintarXiv licenceFull textPlasma physicsarXiv
Minute-Scale High-Fidelity Gyrokinetic Simulations with Portability from Laptop to Supercomputer
Jian Bao, Huasheng Xie, Ming Yang +4
arXiv3 Sep 2026PreprintCC BY 4.0Full textPlasma physicsarXiv
High-resolution in situ analysis of biomass pyrolysis by combining quantitative synchrotron μCT and 3D particle-resolved simulations
Emeric Boigné, Mohamed M. Ahmed, Collin Foster +7
arXiv27 Aug 2026PreprintCC BY-NC-ND 4.0Full textPhysical chemistry Applied physics & instrumentationarXiv
APHABAMAS: An analytical phantom-based scheme for assessing the accuracy of high-resolution 3D MRI motion-artifact simulations
Tianqi Wu, Hui Zhang
arXiv5 Oct 2026PreprintCC BY-NC-ND 4.0Full textBiological & medical physicsarXiv
Self-Organized Dynamic Reactors: Product-Condensate Feedback Accelerates Reactions
Ryosuke Nishide, Kunihiko Kaneko
arXiv7 Sep 2026PreprintCC BY 4.0Full textBiological & medical physics Condensed matterarXiv

Cite

BibTeX RIS

BibTeX

@misc{gottems2026superresolution,
  title = {{Super-Resolution Initialization of High-Fidelity CFD Simulations for Pebble-Bed Reactors}},
  author = {Guilherme Gottems and Vasil Ivakimov and Luiz Aldeia Machado and Mahmoud Yaseen and Tri Nguyen and Elia Merzari and Riccardo Balin and Dillon Shaver and Filippo Simini and Bethany Lusch and Venkatram Vishwanath and Haomin Yuan and Misun Min and Ramesh Balakrishnan and Jun Fang and Paul Fischer},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.02656},
  eprint = {2609.02656},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.02656},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - Super-Resolution Initialization of High-Fidelity CFD Simulations for Pebble-Bed Reactors
AU  - Guilherme Gottems
AU  - Vasil Ivakimov
AU  - Luiz Aldeia Machado
AU  - Mahmoud Yaseen
AU  - Tri Nguyen
AU  - Elia Merzari
AU  - Riccardo Balin
AU  - Dillon Shaver
AU  - Filippo Simini
AU  - Bethany Lusch
AU  - Venkatram Vishwanath
AU  - Haomin Yuan
AU  - Misun Min
AU  - Ramesh Balakrishnan
AU  - Jun Fang
AU  - Paul Fischer
PY  - 2026
DA  - 2026/09/01
PB  - arXiv
DO  - 10.48550/arxiv.2609.02656
UR  - https://arxiv.org/abs/2609.02656
AB  - High-order CFD simulations provide detailed resolution of the heterogeneous interstitial flow in pebble-bed reactors, but their computational cost is high, especially during the initial flow-development period required to reach statistically stationary conditions. This work investigates the use of a Super-Resolution Graph Neural Network (SR-GNN) to improve the initialization of high-order NekRS simulations. Lower-order P = 2 velocity fields are used as inputs to reconstruct higher-order representations, which are then used as initial conditions for P = 7 restart simulations. The approach is evaluated using a 146-pebble bed at Re = 1000, Re = 2500, and Re = 5000, with pressure-drop convergence used as the main figure of merit. The SR-GNN models were trained using paired low- and high-order snapshots and were first evaluated through qualitative inference comparisons. High-order restart simulations showed that, for Re = 1000 and Re = 2500, the SR-GNN initialized cases produced pressure-drop histories similar to direct restarts from true P = 2 fields. For Re = 5000, however, the super-resolved field restart approached the statistically stationary P = 7 pressure-drop range faster than both the direct P = 2 restart and the reference P = 7 simulation initialized from a uniform velocity field. The trained Re = 5000 model was also applied to a larger 1568-pebble bed, demonstrating qualitative applicability of the workflow to a significantly larger packed-bed geometry. These results indicate that SR-GNN-based initialization is a promising strategy for reducing high-order flow-development cost, while also motivating further work on broader Reynolds-number and geometry generalization.
ER  -

Abstract

Related

Cite