Segmentation of spectroscopic images of the low solar atmosphere by the Self Organizing Map technique

TL;DR

This paper demonstrates the successful application of Self Organizing Map machine learning technique for semantic segmentation of high-resolution spectroscopic images of the solar atmosphere, revealing detailed solar structures.

Contribution

It introduces the first application of SOM to astrophysical data, enabling detailed analysis of solar features in spectroscopic images.

Findings

Effective identification of solar photosphere and chromosphere structures

Demonstrates SOM's flexibility in analyzing solar activity

First successful use of SOM on astrophysical data

Abstract

We describe the application of Semantic Segmentation by using the Self Organizing Map technique to an high spatial and spectral resolution dataset acquired along the H$\alpha$ line at 656.28 nm by the Interferometric Bi-dimensional Spectrometer installed at the focus plane of the Dunn Solar Telescope. This machine learning approach allowed us to identify several features corresponding to the main structures of the solar photosphere and chromosphere. The obtained results show the capability and flexibility of this method to identifying and analyzing the fine structures which characterize the solar activity in the low atmosphere. This is a first successful application of the SOM technique to astrophysical data sets.