RADYNVERSION: Learning to Invert a Solar Flare Atmosphere with Invertible Neural Networks

Abstract

During a solar flare, it is believed that reconnection takes place in the corona followed by fast energy transport to the chromosphere. The resulting intense heating strongly disturbs the chromospheric structure, and induces complex radiation hydrodynamic effects. Interpreting the physics of the flaring solar atmosphere is one of the most challenging tasks in solar physics. Here we present a novel deep learning approach, an invertible neural network, to understanding the chromospheric physics of a flaring solar atmosphere via the inversion of observed solar line profiles in Hα and Ca II λ8542. Our network is trained using flare simulations from the 1D radiation hydrodynamics code RADYN as the expected atmosphere and line profile. This model is then applied to single pixels from an observation of an M1.1 solar flare taken with SST/CRISP instrument just after the flare onset. The inverted atmospheres obtained from observations provide physical information on the electron number density, temperature and bulk velocity flow of the plasma throughout the solar atmosphere ranging from 0-10 Mm in height. The density and temperature profiles appear consistent with the expected atmospheric response, and the bulk plasma velocity provides the gradients needed to produce the broad spectral lines whilst also predicting the expected chromospheric evaporation from flare heating. We conclude that we have taught our novel algorithm the physics of a solar flare according to RADYN and that this can be confidently used for the analysis of flare data taken in these two wavelengths. This algorithm can also be adapted for a menagerie of inverse problems providing extremely fast ($\sim$10 μs) inversion samples.

Published in ApJ

References in corpus (14)

• Deep Learning in Neural Networks: An Overview
• CRISP Spectropolarimetric Imaging of Penumbral Fine Structure
• Observing the Roots of Solar Coronal Heating - in the Chromosphere
• CRISPRED: A data pipeline for the CRISP imaging spectropolarimeter
• 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
• Temporal evolution of multiple evaporating ribbon sources in a solar flare
• The Radiated Energy Budget of Chromospheric Plasma in a Major Solar Flare Deduced From Multi-Wavelength Observations
• The Atmospheric Response to High Nonthermal Electron Beam Fluxes in Solar Flares I: Modeling the Brightest NUV Footpoints in the X1 Solar Flare of 2014 March 29
• Formation of the thermal infrared continuum in solar flares
• Radiative hydrodynamic modelling and observations of the X-class solar flare on 2011 March 9
• Spectroscopic inversions of the Ca ii 8542 Å line in a C-class solar flare
• Fast inversion of solar Ca II spectra
• Diagnostics of the Heating Processes in Solar Flares Using Chromospheric Spectral Lines

Cited by in corpus (14)

• Stokes Inversion based on Convolutional Neural Networks
• IRIS observations of short-term variability in moss associated with transient hot coronal loops
• Fast Solar Image Classification Using Deep Learning and its Importance for Automation in Solar Physics
• The F-CHROMA grid of 1D RADYN flare models
• Machine learning initialization to accelerate Stokes profile inversions
• Bayesian Stokes inversion with Normalizing flows
• Mimicking spectropolarimetric inversions using convolutional neural networks
• Fast Inversion of Solar Ca II Spectra in Non-Local Thermodynamic Equilibrium
• Improved detection of farside solar active regions using deep learning
• Understanding Heating in Active Region Cores through Machine Learning II. Classifying Observations
• SunnyNet: A neural network approach to 3D non-LTE radiative transfer
• On the Importance of Ca II Photoionisation by the Hydrogen Lyman Transitions in Solar Flare Models
• Solar activity classification based on Mg II spectra: towards classification on compressed data
• Neural translation for Stokes inversion and synthesis