A Fast and Scalable Transformer Pipeline for Binary Black Hole Detection
Abstract
With the projected increase in the detection rate of compact-binary coalescences in the coming decade, there is critical need to develop fast, robust, and scalable alternatives to matched filtering for gravitational-wave searches. Transformer models have revolutionized natural language and audio processing but their application to gravitational-wave astronomy is still largely unexplored. In this work, we introduce \castor, a transformer-based coincident search pipeline for detecting binary black hole gravitational-wave signals from Advanced LIGO detectors. One of the major features of our model is that it allows the false-alarm rate to be estimated via time slides cheaply without requiring repeated evaluations of the neural network. We evaluate \castor\ on datasets from the Machine-Learning Gravitational-Wave Search Challenge (MLGWSC-1) and on approximately five months of real O3b observing strain. When tested on benchmark datasets, \castor\ ranks among the most sensitive machine-learning pipelines and successfully recovers the majority of confident events from the GWTC-3 catalog that lie within its training range. We also benchmark \castor\ against another transformer architecture, GW-Whisper, a domain-adaptation of OpenAI's audio foundation model. We find that \castor\ substantially outperforms the repurposed audio model in sensitivity and also reduces the computational cost of background estimation by a factor of 20. Our results demonstrate a highly practical, scalable approach for deep-learning gravitational wave searches and empirical background estimation for future observing runs.
Related
- Making Euclid VIS Imaging AI-Ready: A Scalable Pipeline for Morphology, Anomaly Detection, and Similarity Search
- Making Euclid VIS Imaging AI-ready: A Scalable Pipeline for Morphology, Anomaly Detection, and Similarity Search
- Transformers with Physics-Informed Encodings and Simulation-Based Inference for Robust Detection of Eccentric Binary Black Holes in Pulsar Timing Array Data
- One Merger, Three Bands: Multiband Detection Rates and Parameter Estimation of Stellar-mass Binary Black Hole Coalescences from Millihertz to Kilohertz
- Spectropolarimetric detection of baryonic mass loading in a transient relativistic jet: application to the black hole X-ray binary Swift J1727.8−1613
BibTeX
@misc{chatterjee2026fast,
title = {{A Fast and Scalable Transformer Pipeline for Binary Black Hole Detection}},
author = {Chayan Chatterjee and Abigail Petulante and Haowei Fu and Yang Hu and Roy Lau and Karan Jani},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.00339},
eprint = {2609.00339},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.00339},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - A Fast and Scalable Transformer Pipeline for Binary Black Hole Detection
AU - Chayan Chatterjee
AU - Abigail Petulante
AU - Haowei Fu
AU - Yang Hu
AU - Roy Lau
AU - Karan Jani
PY - 2026
DA - 2026/09/23
PB - arXiv
DO - 10.48550/arxiv.2609.00339
UR - https://arxiv.org/abs/2609.00339
AB - With the projected increase in the detection rate of compact-binary coalescences in the coming decade, there is critical need to develop fast, robust, and scalable alternatives to matched filtering for gravitational-wave searches. Transformer models have revolutionized natural language and audio processing but their application to gravitational-wave astronomy is still largely unexplored. In this work, we introduce \castor, a transformer-based coincident search pipeline for detecting binary black hole gravitational-wave signals from Advanced LIGO detectors. One of the major features of our model is that it allows the false-alarm rate to be estimated via time slides cheaply without requiring repeated evaluations of the neural network. We evaluate \castor\ on datasets from the Machine-Learning Gravitational-Wave Search Challenge (MLGWSC-1) and on approximately five months of real O3b observing strain. When tested on benchmark datasets, \castor\ ranks among the most sensitive machine-learning pipelines and successfully recovers the majority of confident events from the GWTC-3 catalog that lie within its training range. We also benchmark \castor\ against another transformer architecture, GW-Whisper, a domain-adaptation of OpenAI's audio foundation model. We find that \castor\ substantially outperforms the repurposed audio model in sensitivity and also reduces the computational cost of background estimation by a factor of 20. Our results demonstrate a highly practical, scalable approach for deep-learning gravitational wave searches and empirical background estimation for future observing runs.
ER -