Reconstruction of Unobserved Core Electron Density in Tokamak Plasmas with a Neural Operator Transport Surrogate and Uncertainty Quantification
Abstract
Real-time control of tokamak plasmas requires the electron density profile. However, in a reactor-relevant device, diagnostic port access is limited and the profile can be observed only partially. In the present work we reconstruct the density profile by inferring the coefficients of a physics-based one-dimensional particle transport equation, using a Fourier Neural Operator (FNO) surrogate of the transport solver as a fast differentiable forward model. The surrogate enables realtime-compatible gradient-based reconstruction and uncertainty quantification from the reflectometry and interferometry measurements. We compare four uncertainty quantification methods - multi-seed ensembles, the Laplace approximation, Metropolis-Hastings, and a Gaussian method independent of the reconstruction fit. The resulting uncertainty is scored with CRPS and coverage calibration, separately on the observed and unobserved regions. We further demonstrate advantage of our approach over standard analytical function fit on synthetic and experimental DIII-D discharges.
Related
- A differentiable PCA-GPR surrogate framework for full-transient Bayesian inverse uncertainty quantification of black-box nuclear thermal-hydraulic systems
- Bayesian Joint Reconstruction and Uncertainty Quantification for Limited-Data Multi-Contrast X-Ray CT
- A physics-informed uncertainty-aware surrogate for p-n junction diodes
- Microdroplet Generator Surrogate Enhancement and Inverse Design Through an Uncertainty-Guided Framework
- A Gaussian-Process Surrogate for Control Rod Worth with Calibrated Uncertainty: Application to VERA Core Physics Benchmark Problem 4
BibTeX
@misc{sorokin2026reconstruction,
title = {{Reconstruction of Unobserved Core Electron Density in Tokamak Plasmas with a Neural Operator Transport Surrogate and Uncertainty Quantification}},
author = {D. Sorokin and A. Granovskiy and M. Stokolesov and E. Adishchev and M. Nurgaliev and G. Subbotin},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.24525},
eprint = {2610.24525},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.24525},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Reconstruction of Unobserved Core Electron Density in Tokamak Plasmas with a Neural Operator Transport Surrogate and Uncertainty Quantification
AU - D. Sorokin
AU - A. Granovskiy
AU - M. Stokolesov
AU - E. Adishchev
AU - M. Nurgaliev
AU - G. Subbotin
PY - 2026
DA - 2026/10/17
PB - arXiv
DO - 10.48550/arxiv.2610.24525
UR - https://arxiv.org/abs/2610.24525
AB - Real-time control of tokamak plasmas requires the electron density profile. However, in a reactor-relevant device, diagnostic port access is limited and the profile can be observed only partially. In the present work we reconstruct the density profile by inferring the coefficients of a physics-based one-dimensional particle transport equation, using a Fourier Neural Operator (FNO) surrogate of the transport solver as a fast differentiable forward model. The surrogate enables realtime-compatible gradient-based reconstruction and uncertainty quantification from the reflectometry and interferometry measurements. We compare four uncertainty quantification methods - multi-seed ensembles, the Laplace approximation, Metropolis-Hastings, and a Gaussian method independent of the reconstruction fit. The resulting uncertainty is scored with CRPS and coverage calibration, separately on the observed and unobserved regions. We further demonstrate advantage of our approach over standard analytical function fit on synthetic and experimental DIII-D discharges.
ER -