Classification of High-resolution Solar Hα Spectra using t-distributed Stochastic Neighbor Embedding

Abstract

The Hα spectral line is a well-studied absorption line revealing properties of the highly structured and dynamic solar chromosphere. Typical features with distinct spectral signatures in Hα include filaments and prominences, bright active-region plages, superpenumbrae around sunspots, surges, flares, Ellerman bombs, filigree, and mottles and rosettes, among others. This study is based on high-spectral resolution Hα spectra obtained with the echelle spectrograph of the Vacuum Tower Telescope (VTT) located at Observatorio del Teide (ODT), Tenerife, Spain. The t-distributed Stochastic Neighbor Embedding (t-SNE) is a machine learning algorithm, which is used for nonlinear dimensionality reduction. In this application, it projects Hα spectra onto a two-dimensional map, where it becomes possible to classify the spectra according to results of Cloud Model (CM) inversions. The CM parameters optical depth, Doppler width, line-of-sight velocity, and source function describe properties of the cloud material. Initial results of t-SNE indicate its strong discriminatory power to separate quiet-Sun and plage profiles from those that are suitable for CM inversions. In addition, a detailed study of various t-SNE parameters is conducted, the impact of seeing conditions on the classification is assessed, results for various types of input data are compared, and the identified clusters are linked to chromospheric features. Although t-SNE proves to be efficient in clustering high-dimensional data, human inference is required at each step to interpret the results. This exploratory study provides a framework and ideas on how to tailor a classification scheme towards specific spectral data and science questions.

16 pages, 14 figures, Accepted to be published in Astrophysical Journal

References in corpus (20)

• The Interface Region Imaging Spectrograph (IRIS)
• The Solar Optical Telescope for the Hinode Mission: An Overview
• The Radial Velocity Experiment (RAVE): first data release
• The GALAH Survey: Scientific Motivation
• Chemical abundances of 1111 FGK stars from the HARPS GTO planet search program II: Cu, Zn, Sr, Y, Zr, Ba, Ce, Nd and Eu
• Dissecting stellar chemical abundance space with t-SNE
• The Galah Survey: Classification and diagnostics with t-SNE reduction of spectral information
• Identifying typical Mg II flare spectra using machine learning
• Recovering Thermodynamics from Spectral Profiles observed by IRIS: A Machine and Deep Learning Approach
• The cool surge following flux emergence in a radiation-MHD experiment
• Stokes Inversion based on Convolutional Neural Networks
• The GALAH survey: Chemical Tagging of Star Clusters and New Members in the Pleiades
• Very metal-poor stars observed by the RAVE survey
• Real-time flare prediction based on distinctions between flaring and non-flaring active region spectra
• Strategies for Spectral Profile Inversion using Artificial Neural Networks
• Zeeman-Tomography of the Solar Photosphere -- 3-Dimensional Surface Structures Retrieved from Hinode Observations
• A giant quiescent solar filament observed with high-resolution spectroscopy
• Determining the dynamics and magnetic fields in He I 10830 Å during a solar filament eruption
• Image Quality in High-resolution and High-cadence Solar Imaging
• High-resolution spectroscopy of a surge in an emerging flux region

Cited by in corpus (10)

• StarHorse results for spectroscopic surveys + Gaia DR3: Chrono-chemical populations in the solar vicinity, the genuine thick disk, and young-alpha rich stars
• 1.5D NLTE spectral synthesis of a 3D filament/prominence simulation
• Solar surges related to UV bursts: Characterization through k-means, inversions and density diagnostics
• Galactic ArchaeoLogIcaL ExcavatiOns (GALILEO) II. t-SNE Portrait of Local Fossil Relics and Structures
• Shape-based clustering of synthetic Stokes profiles using k-means and k-Shape
• Solar active region evolution and imminent flaring activity through a color-coded visualization of photospheric vector magnetograms
• Efficient Identification of Broad Absorption Line Quasars using Dimensionality Reduction and Machine Learning
• Spectropolarimetric observations of the solar atmosphere in the H$\alpha$ 6563 Å line
• High-resolution observations of two pores with the integral field unit (IFU) of the GREGOR Infrared Spectrograph (GRIS)
• Spectral Background-Subtracted Activity Maps