# Interpreting a Machine Learning Model for Detecting Gravitational Waves

arXiv: https://arxiv.org/abs/2202.07399 · HTML: https://mlsanity.com/paper/2202.07399/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 49 references that are in the map.
- First posted on arXiv 15 Feb 2022.

## Builds on (most cited first, 20 of 20)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [Benchmarking Deep Learning Interpretability in Time Series Predictions](https://mlsanity.com/paper/2010.13924/) (2020)
- [Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data](https://mlsanity.com/paper/1711.03121/) (2017)
- [Deep Neural Networks to Enable Real-time Multimessenger Astrophysics](https://mlsanity.com/paper/1701.00008/) (2016)
- [Accelerated, Scalable and Reproducible AI-driven Gravitational Wave Detection](https://mlsanity.com/paper/2012.08545/) (2020)
- [Enabling real-time multi-messenger astrophysics discoveries with deep learning](https://mlsanity.com/paper/1911.11779/) (2019)
- [A FAIR and AI-ready Higgs boson decay dataset](https://mlsanity.com/paper/2108.02214/) (2021)
- [Convergence of Artificial Intelligence and High Performance Computing on NSF-supported Cyberinfrastructure](https://mlsanity.com/paper/2003.08394/) (2020)
- [Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation with LIGO Data](https://mlsanity.com/paper/1711.07966/) (2017)
- [Deep Learning at Scale for the Construction of Galaxy Catalogs in the Dark Energy Survey](https://mlsanity.com/paper/1812.02183/) (2018)
- [Inference-optimized AI and high performance computing for gravitational wave detection at scale](https://mlsanity.com/paper/2201.11133/) (2022)
- [Infrastructure for Artificial Intelligence, Quantum and High Performance Computing](https://mlsanity.com/paper/2012.09303/) (2020)
- [Advancing Computing's Foundation of US Industry & Society](https://mlsanity.com/paper/2101.01284/) (2021)

## Built on by (most cited first, 2 of 2)

- [Applications of physics informed neural operators](https://mlsanity.com/paper/2203.12634/) (2022)
- [Interpretable Machine Learning in Physics: A Review](https://mlsanity.com/paper/2503.23616/) (2025)

## Abstract (arXiv)

We describe a case study of translational research, applying interpretability techniques developed for computer vision to machine learning models used to search for and find gravitational waves. The models we study are trained to detect black hole merger events in non-Gaussian and non-stationary advanced Laser Interferometer Gravitational-wave Observatory (LIGO) data. We produced visualizations of the response of machine learning models when they process advanced LIGO data that contains real gravitational wave signals, noise anomalies, and pure advanced LIGO noise. Our findings shed light on the responses of individual neurons in these machine learning models. Further analysis suggests that different parts of the network appear to specialize in local versus global features, and that this difference appears to be rooted in the branched architecture of the network as well as noise characteristics of the LIGO detectors. We believe efforts to whiten these "black box" models can suggest future avenues for research and help inform the design of interpretable machine learning models for gravitational wave astrophysics.