ELMO: An Uncertainty-Aware Simulation-to-Surrogate Workflow for Fast Pedestal Linear-Stability Prediction

Abstract

Rapid prediction of pedestal linear stability is important for exploring tokamak operating space, uncertainty quantification, and future model-informed control, but mode-resolved magnetohydrodynamic stability calculations using BOUT++ are computationally expensive. We present a focused implementation of ELMO--the Edge Learning and Modeling Orchestrator--as an uncertainty-aware simulation-to-surrogate workflow integrating equilibrium generation, field-aligned mesh construction, large-scale BOUT++ calculations, automated campaign execution and data reduction, and Gaussian Process Regression (GPR). For a single DIII-D plasma shape, 3,869 of 7,992 requested configurations completed equilibrium reconstruction, mesh generation, stability calculation, and quality control. Each retained equilibrium was evaluated at sixteen toroidal mode numbers, n=5--80 with Δn=5, using ideal-MHD and ideal-plus-diamagnetic models, producing 123,808 mode-resolved calculations. Using eight pedestal features, the GPR surrogate predicts two sixteen-mode growth-rate spectra with latent posterior uncertainty estimates. Across five independent test realizations, the maximum-growth-rate prediction achieved R²=0.978±0.013 for ideal MHD and R²=0.966±0.009 for ideal-plus-diamagnetic physics. The surrogate reproduces the spectral shape and dominant unstable mode. Calibration diagnostics indicate that posterior uncertainties are useful for relative acquisition but are underdispersed and should not be interpreted as calibrated prediction intervals. Prediction of all 32 outputs requires about 20 ms on one CPU core, compared with about 21 min using 128 CPU cores for the corresponding BOUT++ scan, giving a 6.3×10⁴-fold wall-clock speedup and an 8.1×10⁶-fold reduction in computational cost.

Surrogate Modeling and Explainable Artificial Intelligence for Complex Systems: A Workflow for Automated Simulation Exploration
Paul Saves, Pramudita Satria Palar, Muhammad Robani +7
HAL31 Oct 2026PreprintCC BY 4.0Full textGeneral mathematics Statistical & nonlinear physicsHAL
A physics-informed uncertainty-aware surrogate for p-n junction diodes
Suchita Kulkarni
arXiv29 Oct 2026PreprintCC BY 4.0Full textCondensed matterarXiv
Reconstruction of Unobserved Core Electron Density in Tokamak Plasmas with a Neural Operator Transport Surrogate and Uncertainty Quantification
D. Sorokin, A. Granovskiy, M. Stokolesov +3
arXiv17 Oct 2026PreprintCC BY-NC-SA 4.0Full textPlasma physicsarXiv
A differentiable PCA-GPR surrogate framework for full-transient Bayesian inverse uncertainty quantification of black-box nuclear thermal-hydraulic systems
Zikang Yaoa, Eugene Yeea, Fue-Sang Lien
arXiv14 Oct 2026PreprintarXiv licenceFull textComputational physics Fluid dynamicsarXiv
Microdroplet Generator Surrogate Enhancement and Inverse Design Through an Uncertainty-Guided Framework
David Gabriel Harispe, Matías Gerard, Pablo A. Kler
arXiv4 Nov 2026PreprintarXiv licenceFull textFluid dynamicsarXiv

Cite

BibTeX RIS

BibTeX

@misc{li2026elmo,
  title = {{ELMO: An Uncertainty-Aware Simulation-to-Surrogate Workflow for Fast Pedestal Linear-Stability Prediction}},
  author = {Nami Li and X. Q. Xu and T. Osborne and E. Suchyta and Y. C. Fu and N. Podhorszki and H. Wang and Z. Li},
  howpublished = {arXiv},
  year = {2026},
  month = aug,
  doi = {10.48550/arxiv.2608.28763},
  eprint = {2608.28763},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.28763},
}

RIS

TY  - UNPB
TI  - ELMO: An Uncertainty-Aware Simulation-to-Surrogate Workflow for Fast Pedestal Linear-Stability Prediction
AU  - Nami Li
AU  - X. Q. Xu
AU  - T. Osborne
AU  - E. Suchyta
AU  - Y. C. Fu
AU  - N. Podhorszki
AU  - H. Wang
AU  - Z. Li
PY  - 2026
DA  - 2026/08/28
PB  - arXiv
DO  - 10.48550/arxiv.2608.28763
UR  - https://arxiv.org/abs/2608.28763
AB  - Rapid prediction of pedestal linear stability is important for exploring tokamak operating space, uncertainty quantification, and future model-informed control, but mode-resolved magnetohydrodynamic stability calculations using BOUT++ are computationally expensive. We present a focused implementation of ELMO--the Edge Learning and Modeling Orchestrator--as an uncertainty-aware simulation-to-surrogate workflow integrating equilibrium generation, field-aligned mesh construction, large-scale BOUT++ calculations, automated campaign execution and data reduction, and Gaussian Process Regression (GPR). For a single DIII-D plasma shape, 3,869 of 7,992 requested configurations completed equilibrium reconstruction, mesh generation, stability calculation, and quality control. Each retained equilibrium was evaluated at sixteen toroidal mode numbers, n=5--80 with Δn=5, using ideal-MHD and ideal-plus-diamagnetic models, producing 123,808 mode-resolved calculations. Using eight pedestal features, the GPR surrogate predicts two sixteen-mode growth-rate spectra with latent posterior uncertainty estimates. Across five independent test realizations, the maximum-growth-rate prediction achieved R^2=0.978±0.013 for ideal MHD and R^2=0.966±0.009 for ideal-plus-diamagnetic physics. The surrogate reproduces the spectral shape and dominant unstable mode. Calibration diagnostics indicate that posterior uncertainties are useful for relative acquisition but are underdispersed and should not be interpreted as calibrated prediction intervals. Prediction of all 32 outputs requires about 20 ms on one CPU core, compared with about 21 min using 128 CPU cores for the corresponding BOUT++ scan, giving a 6.3×10^4-fold wall-clock speedup and an 8.1×10^6-fold reduction in computational cost.
ER  -

Abstract

Related

Cite