A Deep Learning Powered Numerical Relativity Surrogate for Binary Black Hole Waveforms
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912619278893056 |
|---|---|
| author | Freitas, Osvaldo Gramaxo Theodoropoulos, Anastasios Villanueva, Nino Fernandes, Tiago Nunes, Solange Font, José A. Onofre, Antonio Torres-Forné, Alejandro Martin-Guerrero, José D. |
| author_facet | Freitas, Osvaldo Gramaxo Theodoropoulos, Anastasios Villanueva, Nino Fernandes, Tiago Nunes, Solange Font, José A. Onofre, Antonio Torres-Forné, Alejandro Martin-Guerrero, José D. |
| contents | Gravitational-wave approximants are essential for gravitational-wave astronomy, allowing the coverage binary black hole parameter space for inference or match filtering without costly numerical relativity (NR) simulations, but generally trading some accuracy for computational efficiency. To reduce this trade-off, NR surrogate models can be constructed using interpolation within NR waveform space. We present a 2-stage training approach for neural network-based NR surrogate models. Initially trained on approximant-generated waveforms and then fine-tuned with NR data, these dual-stage artificial neural surrogate (\texttt{DANSur}) models offer rapid and competitively accurate waveform generation, generating millions in under 20ms on a GPU while keeping mean mismatches with NR around $10^{-4}$. Implemented in the \textsc{bilby} framework, we show they can be used for parameter estimation tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_06946 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Deep Learning Powered Numerical Relativity Surrogate for Binary Black Hole Waveforms Freitas, Osvaldo Gramaxo Theodoropoulos, Anastasios Villanueva, Nino Fernandes, Tiago Nunes, Solange Font, José A. Onofre, Antonio Torres-Forné, Alejandro Martin-Guerrero, José D. General Relativity and Quantum Cosmology High Energy Astrophysical Phenomena Instrumentation and Methods for Astrophysics Machine Learning Gravitational-wave approximants are essential for gravitational-wave astronomy, allowing the coverage binary black hole parameter space for inference or match filtering without costly numerical relativity (NR) simulations, but generally trading some accuracy for computational efficiency. To reduce this trade-off, NR surrogate models can be constructed using interpolation within NR waveform space. We present a 2-stage training approach for neural network-based NR surrogate models. Initially trained on approximant-generated waveforms and then fine-tuned with NR data, these dual-stage artificial neural surrogate (\texttt{DANSur}) models offer rapid and competitively accurate waveform generation, generating millions in under 20ms on a GPU while keeping mean mismatches with NR around $10^{-4}$. Implemented in the \textsc{bilby} framework, we show they can be used for parameter estimation tasks. |
| title | A Deep Learning Powered Numerical Relativity Surrogate for Binary Black Hole Waveforms |
| topic | General Relativity and Quantum Cosmology High Energy Astrophysical Phenomena Instrumentation and Methods for Astrophysics Machine Learning |
| url | https://arxiv.org/abs/2412.06946 |