Accelerating 3D Non-LTE Synthesis with Graph Neural Networks

Abstract

Spectropolarimetric interpretation of chromospheric lines requires solving the radiative transfer problem under non-local thermodynamic equilibrium (non-LTE) conditions. This means computing atomic-level populations self-consistently with the radiation field. While traditional inversion codes employ 1.5D approximations, they neglect horizontal radiative transfer, which can be significant near magnetic structures and in the chromosphere. We present a method to solve 3D atomic-level populations using Graph Neural Networks (GNNs), extending prior 1.5D work to the full 3D domain. By discretizing the solar atmosphere as a directed graph, in which nodes encode physical properties and edges encode spatial distances, an Encode-Process-Decode GNN propagates information to efficiently capture radiative coupling. The network is trained on a Bifrost simulation using Ca II populations from Multi3D as ground truth. The trained GNN accurately predicts populations of the five-level Ca II atom plus continuum. Correlations exceed 0.99 in the photosphere and mid-chromosphere; errors in the upper chromosphere remain unbiased. Inference is $\sim 10^6$ times faster than traditional iterative solvers. Spectral synthesis of the Ca II 8542 Å line yields intensity profiles with $<2\%$ mean residuals relative to the full 3D solution. This framework bypasses the computational bottleneck of iterative solvers while preserving essential non-LTE physics, including horizontal transfer, paving the way toward routine 3D non-LTE inversions.

Accepted for publication in A&A. 9 pages, 6 figures

References in corpus (20)

• The formation of the Halpha line in the solar chromosphere
• A publicly available simulation of an enhanced network region of the Sun
• An Open Source, Massively Parallel Code for Non-LTE Synthesis and Inversion of Spectral Lines and Zeeman-induced Stokes Profiles
• Advanced Forward Modeling and Inversion of Stokes Profiles Resulting from the Joint Action of the Hanle and Zeeman Effects
• STiC -- A multi-atom non-LTE PRD inversion code for full-Stokes solar observations
• PORTA: A three-dimensional multilevel radiative transfer code for modeling the intensity and polarization of spectral lines with massively parallel computers
• Numerical Simulations of Coronal Heating through Footpoint Braiding
• Spectropolarimetric NLTE inversion code SNAPI
• DeSIRe: Departure coefficient aided Stokes Inversion based on Response functions
• Inference of the chromospheric magnetic field orientation in the Ca II 8542 A line fibrils
• Three-dimensional modeling of chromospheric spectral lines in a simulated active region
• A 3D radiative transfer framework: VI. PHOENIX/3D example applications
• Stratification of physical parameters in a C-class solar flare using multi-line observations
• The Lightweaver Framework for NLTE Radiative Transfer in Python
• The effects of three-dimensional radiative transfer on the resonance polarization of the Ca I 4227 $\mathring{\mathrm{A}}$ line
• Diagnostic potential of the Ca II 8542A line for solar filaments
• Novel framework for the three-dimensional NLTE inverse problem
• Exploring spectropolarimetric inversions using neural fields. Solar chromospheric magnetic field under the weak-field approximation
• Photon mean free paths, scattering, and ever-increasing telescope resolution
• SunnyNet: A neural network approach to 3D non-LTE radiative transfer