Classification of gravitational-wave glitches via dictionary learning
Problem
Gravitational-wave interferometers like advanced LIGO produce transient noise signals (glitches) that must be classified and separated from real astrophysical signals.
Why it matters
Glitch misclassification can mask or mimic genuine gravitational-wave detections in observatory data.
What the AI did
A method using learned dictionaries (supervised machine learning) for signal denoising and untrained dictionaries for sparse reconstruction and classification of glitches.
Results
96% classification accuracy on 3000 simulated glitches of three morphologies embedded in simulated advanced LIGO noise
Impact
Shows dictionary learning is a promising approach for glitch classification, but only on simulated data as a preliminary step.
Record
| Venue | Classical and Quantum Gravity |
|---|---|
| Published | 2019 |
| Work type | article |
| Authors | Miquel Llorens-Monteagudo, Alejandro Torres-Forné, José A. Font, Antonio Marquina |
| Citations | 24 (OpenAlex, at import time) |
| References | 20 |
| Model or method | learned dictionaries (dictionary learning) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1088/1361-6382/ab0657 |
| Open access | green |
| Keywords | gravitational waves, glitch classification, dictionary learning, machine learning, LIGO |
Importance rating
real but narrower advance
Glitch classification supports reliable gravitational-wave observation, but the work is a preliminary step on 3000 simulated glitches; narrower technical advance within detector characterization.
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
|