Machine learning for gravitational wave physics
| advisor: | doc. Ing. Václav Šmídl, Ph.D. |
| e-mail: | show e-mail |
| type: | bachelor thesis, master thesis |
| branch of study: | MI_MM, MI_AMSM |
| key words: | bayesian ineference; machine learning; gravitational waves; simulator based inference |
| description: | The discovery of gravitational waves has revolutionized modern physics, opening a new observational window into the Universe. This thesis project offers the opportunity to contribute to this rapidly growing field by developing advanced machine learning tools for the detection and statistical analysis of gravitational waves from the mergers of black holes and neutron stars. The student will work with state-of-the-art deep learning methods in Python and integrate them with Bayesian approaches for parameter inference. The project will involve generating and analyzing realistic simulations of gravitational-wave signals in noisy detector data, and applying Bayesian techniques to quantify uncertainties and extract astrophysical parameters. These methods will be tested and benchmarked against data from current interferometers (e.g., LIGO, Virgo) and evaluated for their relevance to future space-based missions. By the end of the project, the student will gain hands-on experience with machine learning architectures, Bayesian statistical analysis, large-scale simulations, and inference techniques at the forefront of gravitational-wave astronomy. |
| references: | [1] Bishop, Christopher M.. Pattern recognition and machine learning. Vol. 4, no. 4. New York: springer, 2006. [2] Gutmann, M.U. and Corander, J., 2016. Bayesian optimization for likelihood-free inference of simulator-based statistical models. Journal of Machine Learning Research, 17(125), pp.1-47. |
| note: | Salary is provided for the duration of the thesis. |
| last update: | 19.09.2025 10:24:51 |
administrator for this page:
Ľubomíra Dvořáková | last update: 09/12/2011