Using time series to identify strongly-lensed gravitational waves with deep learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912126542544896 |
|---|---|
| author | Offermans, Arthur Li, Tjonnie G. F. |
| author_facet | Offermans, Arthur Li, Tjonnie G. F. |
| contents | The presence of a massive body between the Earth and a gravitational-wave source will produce the so-called gravitational lensing effect. In the case of strong lensing, it leads to the observation of multiple deformed copies of the initial wave. Machine-learning (ML) models have been proposed for identifying these copies much faster than optimal Bayesian methods, as will be needed with the detection rate of next-generation detector. Most of these ML models are based on a time-frequency representation of the data that discards the phase information. We introduce a neural network that directly uses the time series data to retain the phase, limit the pre-processing time and keep a one-dimensional input. We show that our model is more efficient than the base model used on time-frequency maps at any False Alarm Rate (FPR), up to $\sim 5$ times more for an FPR of $10^{-4}$. We also show that it is not significantly impacted by the choice of waveform model, by lensing-induced phase shifts and by reasonable errors on the merger time that induce a misalignment of the waves in the input. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_12453 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Using time series to identify strongly-lensed gravitational waves with deep learning Offermans, Arthur Li, Tjonnie G. F. General Relativity and Quantum Cosmology High Energy Astrophysical Phenomena The presence of a massive body between the Earth and a gravitational-wave source will produce the so-called gravitational lensing effect. In the case of strong lensing, it leads to the observation of multiple deformed copies of the initial wave. Machine-learning (ML) models have been proposed for identifying these copies much faster than optimal Bayesian methods, as will be needed with the detection rate of next-generation detector. Most of these ML models are based on a time-frequency representation of the data that discards the phase information. We introduce a neural network that directly uses the time series data to retain the phase, limit the pre-processing time and keep a one-dimensional input. We show that our model is more efficient than the base model used on time-frequency maps at any False Alarm Rate (FPR), up to $\sim 5$ times more for an FPR of $10^{-4}$. We also show that it is not significantly impacted by the choice of waveform model, by lensing-induced phase shifts and by reasonable errors on the merger time that induce a misalignment of the waves in the input. |
| title | Using time series to identify strongly-lensed gravitational waves with deep learning |
| topic | General Relativity and Quantum Cosmology High Energy Astrophysical Phenomena |
| url | https://arxiv.org/abs/2411.12453 |