Machine Learning Techniques for Advanced Gravitational Wave Detectors
The Advanced LIGO interferometers output a vast amount of data regarding their internal states.
To further improve the sensitivity of these detectors we require new techniques to extract experimental parameters to control and diagnose issues within these complex experiments.
Key to this effort is developing an understanding of how multiple degrees of freedom and experimental parameters interact with one another in these advanced interferometers.
This project will use advanced interferometer simulation software, developed by researchers at Adelaide, coupled with machine learning and Bayesian analysis methods to develop new techniques for extracting experimental parameters within gravitational wave interferometers.
It would suit students with an interest in programming, data analysis techniques and machine learning.
This project is part of the research program within the ARC Centre of Excellence for Gravitational Wave Discovery (OzGrav), and includes research toward upgrading the sensitivity of the current generation of detectors, analysing data from those detectors and the development of technology for future detectors.
Supervisors
- Dr Daniel Brown | Professor David Ottaway
- Research Area: Ozgrav
- Recommended honours enrolment: Honours in Physics