Abstract:
Plasma fusion is a promising source of future energy. We apply machine learning techniques to detect blob features in plasma fusion data in order to help physicists gaining deep insight into their simulations and experiments of Tokamak reactors. The blobs, which are not mathematically well-defined features, typically form on outer regions of the reactor and can possibly damage the reactor. We thus prototyped machine learning approaches to automatically detect blobs in XGC fusion simulation data.  In this talk, I will first explain the user interface we designed for domain scientists to label data for training purposes. I will then present our data preprocessing with topology analysis and the machine learning approaches based on the UNet architecture. Preliminary results are obtained with arbitrarily labeled training data. In the end, I will outline future direction with the applied concepts.

Bio:
Martin Imre is currently a Research Aide under the supervision of Dr. Hanqi Guo at the Mathematics and Computer Science division of the Argonne National lab. Afterwards he will be a third year doctoral student at the University of Notre Dame, working with Dr. Chaoli Wang on High Performance Computing and Scientific Visualization. He received his BSc (2014) and MSc (2016) in Software Engineering at the Vienna University of Technology. During his Master’s program, he conducted research at the VRVis Research Center in Vienna and continued acquiring experience during a research internship at the University of California, Irvine. His research interests are in Scientific and Information Visualization, and High Performance Computing.