Astroinformatics is a rising field at the interface between Computer Science and Astronomy with new discoveries made possible by the abundance in galactic data created by the Sloan Digital Sky Survey (SDSS). This work provides the statistical framework for astronomical model checking and inference from data. The computational bottleneck in the probabilistic approaches is one of the main obstacles, with grid computing offering a promising solution. In order to use grid technologies, a middleware lay that permits decentralized resource management is necessary to deal with a variety of issues. The research focuses on the development of modular, highly customizable, decentralized coordination using peer-to-peer protocols and methods to optimize the inclusion of nodes in the network as well as generic algorithms for distribution of large problems in parallel computational environments. The project will provide a seamless framework for testing models that address fundamental questions in astronomy. The tools will enable a wide range of other parallel adaptive applications in physics, materials science and ecology. In addition, curricula and public demonstrations are part of the project.
