Document Type

Thesis

Date of Degree Completion

Spring 2019

Degree Name

Master of Science (MS)

Department

Computational Science

Committee Chair

Dr. Razvan Andonie

Second Committee Member

Dr. Szilard VAJDA

Third Committee Member

Dr. Boris Kovalerchuk

Abstract

The classification of stellar spectra is a fundamental task in stellar astrophysics. There have been many explorations into the automated classification of stellar spectra but few that involve the Sloan Digital Sky Survey (SDSS). Stellar spectra from the SDSS are applied to standard classification methods such as K-Nearest Neighbors, Random Forest, and Support Vector Machine to automatically classify the spectra. Stellar spectra are high dimensional data and the dimensionality is reduced using standard Feature Selection methods such as Chi-Squared and Fisher score and with domain-specific astronomical knowledge because classifiers work in low dimensional space. These methods are utilized to classify the stellar spectra into the two standard star classification schemes, the Harvard Spectral Classification and the Morgan Keenan Luminosity Classes. If a star is classified into both of these schemes, many stellar properties can be approximated with ease, whereas the direct approaches can take up to months of observations. A physical phenomenon known as redshift causes machine learning complications through the feature matrix when classifying stellar spectra. However, classifiers utilizing redshifted stellar spectra performed with high accuracy. An approach for extracting redshift using predictions from the classification models is explored.

Share

COinS