# Recovering Thermodynamics from Spectral Profiles observed by IRIS: A Machine and Deep Learning Approach

## TL;DR

This paper introduces machine learning techniques to rapidly reconstruct the thermodynamic state of the solar chromosphere from IRIS spectral data, significantly reducing computation time compared to traditional inversion methods.

## Contribution

It presents a novel machine learning approach that accelerates the inversion of IRIS spectral profiles, enabling fast and accurate thermodynamic reconstructions of the solar chromosphere.

## Key findings

- Achieved a speed-up factor of 10^5 to 10^6 in inversion processing.
- Successfully reconstructed thermodynamic parameters from IRIS Mg II h&k lines.
- Provided open-source tools for the solar physics community.

## Abstract

Inversion codes allow reconstructing a model atmosphere from observations. With the inclusion of optically thick lines that form in the solar chromosphere, such modelling is computationally very expensive because a non-LTE evaluation of the radiation field is required. In this study, we combine the results provided by these traditional methods with machine and deep learning techniques to obtain similar-quality results in an easy-touse, much faster way. We have applied these new methods to Mg II h&k lines observed by IRIS. As a result, we are able to reconstruct the thermodynamic state (temperature, line-of-sight velocity, non-thermal velocities, electron density, etc.) in the chromosphere and upper photosphere of an area equivalent to an active region in a few CPU minutes, speeding up the process by a factor of $10^5$-$10^6$. The open-source code accompanying this paper will allow the community to use IRIS observations to open a new window to a host of solar phenomena.