Bayesian model comparison of solar flare spectra

The detailed understanding of solar flares requires an understanding of the physics of accelerated electrons, since electrons carry a large fraction of the total energy released in a flare. Hard X-ray energy flux spectral observations of solar flares can be fit with different parameterized models of the interaction of the flare-accelerated electrons with the solar plasma. Each model describes different possible physical effects that may occur in solar flares. Bayesian model comparison provides a technique for assessing which model best describes the data. The advantage of this technique over others is that it can fully account for the different number and type of parameters in each model. We demonstrate this using Ramaty High Energy Solar Spectroscopic Imager (RHESSI) spectral data from the GOES (Geostationary Operational Environmental Satellite) X4.8 flare of 23-July-2002. We suggest that the observed spectrum can be reproduced using two different parameterized models of the flare electron content. The first model assumes that the flare-accelerated electron spectrum consisting of a single power law with a fixed low energy cutoff assumed to be below the range of fitted X-ray energies, interacting with a non-uniformly ionized target. The second model assumes that the flare-accelerated electron spectrum has a broken power law and a low energy cutoff, which interacts with a fully ionized target plasma. The low energy cutoff in this model is a parameter used in fitting the data. We will introduce and use Bayesian model comparison techniques to decide which model best explains the observed data. This work is funded by the NASA Solar and Heliospheric Physics program.