Julian Chan
Postgraduate Research Student
Academic and research departments
About
My research project
Machine Learning for predicting the evolution of supermassive black hole binariesPulsar Timing Arrays detect the stochastic gravitational wave background from supermassive black hole binaries (BHBs), requiring accurate merger timescales for astrophysical insights. Machine learning techniques, such as neural ordinary differential equations and symbolic regression, are proposed to improve BHB evolution modeling by interpolating noisy orbital elements and reducing simulation times. These methods enhance merger timescale predictions, aiding in GWB interpretation.
Supervisors
Pulsar Timing Arrays detect the stochastic gravitational wave background from supermassive black hole binaries (BHBs), requiring accurate merger timescales for astrophysical insights. Machine learning techniques, such as neural ordinary differential equations and symbolic regression, are proposed to improve BHB evolution modeling by interpolating noisy orbital elements and reducing simulation times. These methods enhance merger timescale predictions, aiding in GWB interpretation.
ResearchResearch interests
- N-body simulations of galaxy mergers
- Supermassive Black Hole Binaries
- Neural ODEs
- Symbolic Regression
- Graph Neural Networks
Research interests
- N-body simulations of galaxy mergers
- Supermassive Black Hole Binaries
- Neural ODEs
- Symbolic Regression
- Graph Neural Networks