Physical Sciences and Mathematics Commons^™

Automated Classification Of Stellar Spectra. Ii: Two-Dimensional Classification With Neural Networks And Principal Components Analysis, Ted Von Hippel, Coryn A.L. Bailer-Jones, Mike Irwin

Publications

We investigate the application of neural networks to the automation of MK spec- tral classification. The data set for this project consists of a set of over 5000 optical (3800–5200°A) spectra obtained from objective prism plates from the Michigan Spec- tral Survey. These spectra, along with their two-dimensional MK classifications listed in the Michigan Henry Draper Catalogue, were used to develop supervised neural network classifiers. We show that neural networks can give accurate spectral type classifications (68 = 0.82 subtypes, rms= 1.09 subtypes) across the full range of spectral types present in the data set (B2–M7). We show also that …