Exploring gravitational-wave detection and parameter inference using deep learning methods
Problem
Detecting gravitational-wave signals from binary black hole mergers in noisy detector data and inferring their parameters.
Why it matters
Faster gravitational-wave detection could enable timely follow-up observations of cosmic events.
What the AI did
Deep learning networks trained on BBH merger waveforms injected into real LIGO/Virgo O2 data performed detection, and a regression network performed parameter inference.
Results
High detection accuracy for signals up to 2000 Mpc; combining three detectors into one RGB image improved single-detector performance by up to 70%.
Impact
Demonstrates deep learning as a viable method for gravitational-wave detection and inference on real detector data.
Record
| Venue | Classical and Quantum Gravity |
|---|---|
| Published | 2021 |
| Work type | article |
| Authors | João D Álvares, José A. Font, Felipe F Freitas, Osvaldo G Freitas, António P Morais, Solange Nunes, Antonio Onofre, Alejandro Torres-Forné |
| Citations | 21 (OpenAlex, at import time) |
| References | 59 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1088/1361-6382/ac0455 |
| Open access | bronze |
| Keywords | gravitational waves, deep learning, black hole mergers, LIGO, parameter inference |
Importance rating
significant — thousands to millions affected
Gravitational-wave detection supports a foundational scientific field (multi-messenger astronomy); abstract shows viability on real LIGO/Virgo data but states no scale of impact.
More in Physics & Astronomy
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Magnetic control of tokamak plasmas through deep reinforcement learning | 2022 | 739 |
7
|
| 2 | Solving the quantum many-body problem with artificial neural networks | 2017 | 2,205 |
7
|
| 3 | Learning high-accuracy error decoding for quantum processors | 2024 | 90 |
7
|
| 4 | Optimizing Quantum Error Correction Codes with Reinforcement Learning | 2019 | 158 |
7
|
| 5 | Machine-learning-assisted correction of correlated qubit errors in a topological code | 2018 | 141 |
7
|