Foundation models improve particle track finding and identification
Track finding and particle identification performance with particle physics foundation models
Machine Learning
Summary
High energy physics experiments generate huge amounts of data that are hard to analyze quickly. The authors tested a type of AI called Foundation Models to help make sense of this data by recognizing patterns of particles moving through a detector. They found these models did better than traditional methods at tracking charged particles inside a magnetic field and could also learn to identify other related features. This suggests these models may be a useful new tool for analyzing complex physics data.
What this means in practice
- •For particle physics experiment teams: Improve data analysis pipelines by using foundation models for more accurate and adaptable particle tracking and identification.
- •For medical imaging developers: Use foundation models to enhance pattern recognition in sparse, high-dimensional imaging data for better diagnostics.
Authors
Shuhang Li, Haiwang Yu, Gabor Galgoczi, Yeonju Go, Yi Huang, David Park, Michael Peters, Christof Roland, Jin Huang, Yihui Ren, Joseph D. Osborn
Abstract
Modern high energy nuclear and particle physics experiments produce large amounts of sparse data that must be reduced significantly in size before performing physics analysis. Recently, there has been an effort to evaluate Foundation Models as a potential tool for performing data analysis. These models have been shown to learn features in high dimensional datasets based on the multi-modal data they are trained on. To show their effectiveness at performing complex pattern recognition tasks, such as reconstructing charged particles in a magnetic field, we evaluated the performance of a Foundation Model based reconstruction on several downstream tasks with a dataset composed of spacepoints in a Time Projection Chamber. We show that the performance of the Foundation Model based data analysis significantly improves upon that of traditional methods, and furthermore can be adapted to learn additional tasks that are not necessarily related to the initial training objective.