Probabilistic and Geometry Aware Neural Surrogate of Scrape Off Layer Plasma Simulations
Abstract
Fast surrogates for tokamak boundary-plasma simulation are typically deterministic regressors mapping a global operating point to a flattened vector of cell values. Near the divertor detachment transition the steady state is not reliably single-valued. A point estimate must average over qualitatively different plasma states, and it arrives with no statement of confidence. Moreover, the flattened vector representation discards the geometric structure of the SOLPS-ITER mesh. This work addresses both problems. We unroll the curvilinear mesh into three fixed-size image tensors whose layout preserves cell adjacency and inverts exactly, letting a convolutional network act on the geometry without loss of information. A conditional flow matching model, well suited to highly sensitive systems, is then trained on this representation. The result is an efficient, scalable surrogate that captures multiple plausible outcomes even at sensitive operating points. Along a gas-puff scan, the predictive distribution splits into a hot and a cold mode across an early regime transition. A further check on synthetic data with an injected bifurcation of known size confirms the model recovers both branches rather than their average.
Related
- Airfoil2Vec: Spectral Geometry-Conditioned Neural Surrogate Models for Airfoil Aerodynamics and a Downforce-Generating CFD Dataset
- Physics-Informed Neural Networks to Infer the Perpendicular Energy Conductivity in the Scrape-Off Layer of Stellarator Devices
- Accelerating droplet-laden Stokes flow simulations with hierarchical surrogate modeling
- Platypus: a Python package for automated surrogate-assisted analysis of process-based simulations via the non-intrusive reduced-basis method
- Koopman Neural Operator-based surrogate modelling for high-frequency dynamics of high-speed rail pantographs
BibTeX
@misc{gianuzzo2026probabilistic,
title = {{Probabilistic and Geometry Aware Neural Surrogate of Scrape Off Layer Plasma Simulations}},
author = {Gabriele Gianuzzo and Stefan Dasbach and Fleur Hendriks and Sven Wiesen and Vlado Menkovski},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.28116},
eprint = {2609.28116},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.28116},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Probabilistic and Geometry Aware Neural Surrogate of Scrape Off Layer Plasma Simulations
AU - Gabriele Gianuzzo
AU - Stefan Dasbach
AU - Fleur Hendriks
AU - Sven Wiesen
AU - Vlado Menkovski
PY - 2026
DA - 2026/09/23
PB - arXiv
DO - 10.48550/arxiv.2609.28116
UR - https://arxiv.org/abs/2609.28116
AB - Fast surrogates for tokamak boundary-plasma simulation are typically deterministic regressors mapping a global operating point to a flattened vector of cell values. Near the divertor detachment transition the steady state is not reliably single-valued. A point estimate must average over qualitatively different plasma states, and it arrives with no statement of confidence. Moreover, the flattened vector representation discards the geometric structure of the SOLPS-ITER mesh. This work addresses both problems. We unroll the curvilinear mesh into three fixed-size image tensors whose layout preserves cell adjacency and inverts exactly, letting a convolutional network act on the geometry without loss of information. A conditional flow matching model, well suited to highly sensitive systems, is then trained on this representation. The result is an efficient, scalable surrogate that captures multiple plausible outcomes even at sensitive operating points. Along a gas-puff scan, the predictive distribution splits into a hot and a cold mode across an early regime transition. A further check on synthetic data with an injected bifurcation of known size confirms the model recovers both branches rather than their average.
ER -