The goal of this project is to apply machine learning techniques to various science applications at LBNL. Several examples that we are investigating include climate modeling, supernova recognition, combustion, and track reconstruction in high energy physics.

My own involvement includes work on the track reconstruction problem in high-energy physics. An excellent introducution to this problem can be found at the wiki on Pattern Recognition in Particle Physics. Our participation has been to investigate machine learning techniques for improving the performance of standard pattern recognition methods for these types of problems. You can check out the activities of our group at our web pages. I've also compiled a short overview of ensemble methods for machine learning at Ensemble Methods for Machine Learning .