AAS 205th Meeting, 9-13 January 2005
Session 143 Quasars
Poster, Thursday, January 13, 2005, 9:20am-4:00pm, Exhibit Hall

Previous   |   Session 143   |   Next


[143.14] Quasar Spectral Fitting using a Genetic Algorithm

C. Stoughton, S. Jester (Fermilab EAG), D. E. Vanden Berk (Pennsylvania State University), R. Nichol (Univ. of Portsmouth)

We have developed a genetic algorithm for fitting UV/optical quasar spectra in detail. The continuum, emission line, and host galaxy components are fit simultaneously. The continuum is modeled with a power law and Balmer continuum. Major emission lines are modeled with one to three Gaussians per line. Iron emission complexes are modeled with multiple Gaussians, based on narrow-lined Seyfert spectra and theoretical line models. The host galaxy component is modeled using galaxy eigenvectors. A typical SDSS quasar spectrum is modeled using over 150 parameters. The fitting routine uses a "genetic" algorithm to search the parameter space to minimize the Chi-squared value of the model fit to the spectroscopic data. The algorithm requires a minimum of human supervision, and returns stable, robust results. The algorithm has been run on over 16,000 SDSS Data Release One spectra using the TeraGrid and Fermilab farms. Results of the fits are presented.


The author(s) of this abstract have provided an email address for comments about the abstract: stoughto@fnal.gov

Previous   |   Session 143   |   Next

Bulletin of the American Astronomical Society, 36 5
© 2004. The American Astronomical Society.