Compression of Solar Spectroscopic Observations: a Case Study of Mg II k Spectral Line Profiles Observed by NASA's IRIS Satellite

TL;DR

This paper demonstrates that Mg II k spectral line profiles from solar observations can be compressed over 27 times using autoencoders, maintaining low reconstruction error, which benefits feature extraction and data reduction in solar spectroscopy.

Contribution

It introduces the first effective autoencoder-based compression method for Mg II k spectral line profiles, achieving significant data reduction with interpretable features.

Findings

Over 27-fold compression with 4 DN reconstruction error

Features control line width, asymmetry, and dip formation

Potential for improved embeddings with advanced training strategies

Abstract

In this study we extract the deep features and investigate the compression of the Mg II k spectral line profiles observed in quiet Sun regions by NASA's IRIS satellite. The data set of line profiles used for the analysis was obtained on April 20th, 2020, at the center of the solar disc, and contains almost 300,000 individual Mg II k line profiles after data cleaning. The data are separated into train and test subsets. The train subset was used to train the autoencoder of the varying embedding layer size. The early stopping criterion was implemented on the test subset to prevent the model from overfitting. Our results indicate that it is possible to compress the spectral line profiles more than 27 times (which corresponds to the reduction of the data dimensionality from 110 to 4) while having a 4 DN average reconstruction error, which is comparable to the variations in the line continuum. The mean squared error and the reconstruction error of even statistical moments sharply decrease when the dimensionality of the embedding layer increases from 1 to 4 and almost stop decreasing for higher numbers. The observed occasional improvements in training for values higher than 4 indicate that a better compact embedding may potentially be obtained if other training strategies and longer training times are used. The features learned for the critical four-dimensional case can be interpreted. In particular, three of these four features mainly control the line width, line asymmetry, and line dip formation respectively. The presented results are the first attempt to obtain a compact embedding for spectroscopic line profiles and confirm the value of this approach, in particular for feature extraction, data compression, and denoising.