Machine Learning for High Energy Physics
Haichen Wang, Professor
Physics
Applications for Fall 2024 are closed for this project.
High-energy physics data analysis deals with a huge amount of data. Machine learning applications are often developed to assist the analysis of data and to improve our understanding of fundamental physics laws. My research group is developing multiple applications for high energy physics experiments, such as the ATLAS experiment at the LHC. Some examples include:
1) Using Graph Neural Networks to separate signal events from background events
2) Using generative machine learning models to improve the modeling of detector performance
3) Using regression method to improve prediction of particle properties
Role: Selected students would be paired with a mentor to work on a specific project. Students are expected to attend weekly research meetings and project workshops on campus and/or at LBNL. Each specific project typically aims at producing a publication.
Qualifications: Proficient in Python. C++ experience is desirable. Experience with git. Please indicate in the statement if you have taken machine learning related courses.
9-11 hrs or 12 or more hours expected each week.
Hours: to be negotiated
Off-Campus Research Site: Meetings and workshops may take place on campus or at LBNL
Mathematical and Physical Sciences