Physics Attention Transformer Surrogate for Rapid Vertical Instability Growth Rate Prediction: Alcator C-Mod to SPARC

In this work, we investigate rapid prediction of the dominant $n{=}0$ vertical instability growth rate in C-Mod and SPARC equilibria, where nonrigid free boundary response models are too slow for control cycle use. Using a Physics Attention Transformer trained on MEQ-FGE-L labels, we predict both the scalar growth rate and the associated two dimensional perturbed toroidal current density. We find mean absolute errors of 5.4s$^{-1}$ on held out C-Mod equilibria and 12.7s$^{-1}$ on synthetic SPARC cases, with spatial eigenfunction errors near 5%. We also compared PAT with operator based ML models : FNO2D and DeepONet, where we found PAT predicts a much lower normalised growth rate error and improved spatial reconstruction. These results indicate that PAT can reproduce MEQ-FGE-L outputs at control relevant latency and could support future studies of growth rate headroom monitoring and proximity aware shape control.

Source: arXiv:2608.24785v1 - http://arxiv.org/abs/2608.24785v1 PDF: https://arxiv.org/pdf/2608.24785v1 Original Link: http://arxiv.org/abs/2608.24785v1