Hierarchical Spectral and Spatial Modeling for the Chandra X-ray
Observatory
David A. van Dyk
Harvard University
The Chandra X-Ray Observatory, launched by the Space Shuttle Columbia
in July 1999, has taken its place with the Hubble Space Telescope and
Compton Gamma Ray Observatory in NASA's fleet of great space observatories.
As the world's premier X-ray observatory, Chandra gives astronomers a
powerful new tool to investigate black holes, exploding stars, and
colliding galaxies in the hot regions of the universe. Chandra's uses four
pairs of ultra smooth, high resolution mirrors and efficient X-ray detectors
to produce images at least thirty times sharper then any previous X-ray
telescope. Unfortunately, currently popular statistical analysis tools for
such data typically involves Gaussian approximations (e.g., chi squared
fitting) which are not justifiable for the high-resolution low-count data.
Instead, we employ modern Bayesian computational techniques (e.g.,
EM-type algorithms, the Gibbs sampler, and Metropolis-Hastings) to fit new
hierarchical models that account for the Poisson nature of photon counts,
background contamination, blurring of the image due to instrument response,
photon absorption, and source features such as spectral energy lines. This
application demonstrates the flexibility and power of modern Bayesian
methodology and algorithms to handle highly hierarchical models that account
for the complex structure in the collection of high-quality spectra.
Joint work with Vinay L. Kashyap and Aneta Siemiginowka,
Harvard-Smithsonian Center for Astrophysics and
Alanna Connors Eureka Scientific
Back to statistics seminar home page