# Stokes Inversion based on Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1904.03714 · HTML: https://mlsanity.com/paper/1904.03714/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2019.

## Built on by (most cited first, 9 of 9)

- [Machine learning in solar physics](https://mlsanity.com/paper/2306.15308/) (2023)
- [Fast and Accurate Emulation of the SDO/HMI Stokes Inversion with Uncertainty Quantification](https://mlsanity.com/paper/2103.17273/) (2021)
- [Machine learning initialization to accelerate Stokes profile inversions](https://mlsanity.com/paper/2103.09651/) (2021)
- [Inferring Line-of-Sight Velocities and Doppler Widths from Stokes Profiles of GST/NIRIS Using Stacked Deep Neural Networks](https://mlsanity.com/paper/2210.04122/) (2022)
- [SynthIA: A Synthetic Inversion Approximation for the Stokes Vector Fusing SDO and Hinode into a Virtual Observatory](https://mlsanity.com/paper/2108.12421/) (2021)
- [Predicting the Radiation Field of Molecular Clouds using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2309.05811/) (2023)
- [Deep Computer Vision for Solar Physics Big Data: Opportunities and Challenges](https://mlsanity.com/paper/2409.04850/) (2024)
- [Compression Method for Solar Polarization Spectra Collected from Hinode SOT/SP Observations](https://mlsanity.com/paper/2411.09311/) (2024)
- [Category-based Galaxy Image Generation via Diffusion Models](https://mlsanity.com/paper/2506.16255/) (2025)

## Abstract (arXiv)

Spectropolarimetric inversions are routinely used in the field of Solar Physics for the extraction of physical information from observations. The application to two-dimensional fields of view often requires the use of supercomputers with parallelized inversion codes. Even in this case, the computing time spent on the process is still very large. Our aim is to develop a new inversion code based on the application of convolutional neural networks that can quickly provide a three-dimensional cube of thermodynamical and magnetic properties from the interpretation of two-dimensional maps of Stokes profiles. We train two different architectures of fully convolutional neural networks. To this end, we use the synthetic Stokes profiles obtained from two snapshots of three-dimensional magneto-hydrodynamic numerical simulations of different structures of the solar atmosphere. We provide an extensive analysis of the new inversion technique, showing that it infers the thermodynamical and magnetic properties with a precision comparable to that of standard inversion techniques. However, it provides several key improvements: our method is around one million times faster, it returns a three-dimensional view of the physical properties of the region of interest in geometrical height, it provides quantities that cannot be obtained otherwise (pressure and Wilson depression) and the inferred properties are decontaminated from the blurring effect of instrumental point spread functions for free. The code is provided for free on a specific repository, with options for training and evaluation.