The National Science Foundation-supported research training program Data Science in Multi-Messenger Astrophysics at the University of Minnesota is designed to train graduate students in modern data science techniques, using as a training ground the field of Multi-Messenger Astrophysics (MMA).
MMA is an emerging field of astrophysics where multiple messengers are used to study astrophysical and cosmological events and processes: light, gravitational waves, neutrino particles, cosmic rays, and gamma rays.
The MMA field is anticipating substantial increase in the data flow in the coming years, driven by the arrival of a series of new telescopes, gravitational-wave detectors, neutrino detectors, and gamma-ray detectors. Existing tools for processing astrophysical data are often not sufficient to cope with this data flow, so new, modern tools for data processing and analysis are needed, including machine learning, deep learning, Bayesian statistical methods, and others.
The Data Science in MMA program will bring together students and faculty from diverse backgrounds to enable breakthroughs in the MMA field based on deployment of modern data science tools. Students from physics and astrophysics, as well as from traditional data-science fields (statistics, computer science, electrical engineering, mathematics, and others) are encouraged to participate in the program.
What to expect:
- Opportunities to directly contribute to frontier astrophysics research, while at the same time gaining experience in working with large databases, modern statistical techniques, and machine learning algorithms
- Team-based research projects
- Mentoring by interdisciplinary teams of faculty
- Opportunities to participate in workshops focusing on technical skills (coding, machine learning algorithms and other tools)
- Opportunities to participate in workshops focusing on professional skills (communication, leadership, and team building)
- Access to seminars, internships, outreach events, and other activities
Students participating in this program will be invited to provide feedback on different aspects of the program by completing appropriate surveys at multiple junctures in the program. This feedback will be used to improve the effectiveness of the program. Student participation in these surveys will be strictly voluntary and it will not impact the status of the student in the program.
Contact: Prof. Vuk Mandic, vuk at umn.edu