Automating the Analysis of Planetary Nebulae Images
In proceedings ASE 2003.
Abstract
Scientific data analysis involves the task of fitting statistical
models of the studied processes to collected data.
Here, we take a typical task, the analysis of
planetary nebulae images taken by the Hubble Space Telescope,
and describe how the program synthesis system AutoBayes can be used
to generate the necessary analysis programs.
We describe the AutoBayes system and discuss its fully declarative model
specification language. We present the automatic derivation of the
scientists' original analysis [KnuthHajian2002] as
well as a refined analysis using image segmentation models. This demonstrates
that the AutoBayes synthesis system can be applied to realistic scientific data
analysis tasks.