Detection of gravitational-wave signals from binary neutron star mergers using machine learning:
\nAs two neutron stars merge, they emit gravitational waves that can potentially be detected by earth bound detectors. Matched-filtering based algorithms have traditionally been used to extract quiet signals embedded in noise. We introduce a novel neural-network based machine learning algorithm that uses time series strain data from gravitational-wave detectors to detect signals from non-spinning binary neutron star mergers. For the Advanced LIGO design sensitivity, our network has an average sensitive distance of 130 Mpc at a false-alarm rate of 10 per month. Compared to other state-of-the-art machine learning algorithms, we find an improvement by a factor of 6 in sensitivity to signals with signal-to-noise ratio below 25. However, this approach is not yet competitive with traditional matched-filtering based methods. A conservative estimate indicates that our algorithm introduces on average 10.2 s of latency between signal arrival and generating an alert. We give an exact description of our testing procedure, which can not only be applied to machine learning based algorithms but all other search algorithms as well. We thereby improve the ability to compare machine learning and classical searches.
LIGO-Autoencoder: An anomaly detection algorithm for gravitational waves:
\nGravitational-Wave Detection Algorithms with Spiking Neural Networks. Download dataset containing 5,000 injection events and 20,000 noise events. Place in directory labeled 'data'. Must have GWpy package.
ggwd: generate gravitational-wave data:
\nUse PyCBC / LALSuite to generate synthetic gravitational-wave data. The purpose of this repository is to provide a starting point for generating realistic synthetic gravitational-wave data which can then be used, for example, as training data for machine learning experiments. It was originally developed for our paper Convolutional neural networks: a magic bullet for gravitational-wave detection? [arXiv:1904.08693] and used to generate the training and testing data for the network presented there.
More specifically, the methods provided in this repository here will help you with the simulation of GW signals from compact binary coalescences (e.g., binary black hole mergers), adding these signals into a pieces of background noise (either synthetic or real LIGO background recordings) and applying standard post-processing steps (e.g., whitening and band-passing) to results.
", "messages": [ { "id": "1373997", "postDate": "07/02/2021 22:54:49", "content": "Detection of gravitational-wave signals from binary neutron star mergers using machine learning:
\nAs two neutron stars merge, they emit gravitational waves that can potentially be detected by earth bound detectors. Matched-filtering based algorithms have traditionally been used to extract quiet signals embedded in noise. We introduce a novel neural-network based machine learning algorithm that uses time series strain data from gravitational-wave detectors to detect signals from non-spinning binary neutron star mergers. For the Advanced LIGO design sensitivity, our network has an average sensitive distance of 130 Mpc at a false-alarm rate of 10 per month. Compared to other state-of-the-art machine learning algorithms, we find an improvement by a factor of 6 in sensitivity to signals with signal-to-noise ratio below 25. However, this approach is not yet competitive with traditional matched-filtering based methods. A conservative estimate indicates that our algorithm introduces on average 10.2 s of latency between signal arrival and generating an alert. We give an exact description of our testing procedure, which can not only be applied to machine learning based algorithms but all other search algorithms as well. We thereby improve the ability to compare machine learning and classical searches.
LIGO-Autoencoder: An anomaly detection algorithm for gravitational waves:
\nGravitational-Wave Detection Algorithms with Spiking Neural Networks. Download dataset containing 5,000 injection events and 20,000 noise events. Place in directory labeled 'data'. Must have GWpy package.
ggwd: generate gravitational-wave data:
\nUse PyCBC / LALSuite to generate synthetic gravitational-wave data. The purpose of this repository is to provide a starting point for generating realistic synthetic gravitational-wave data which can then be used, for example, as training data for machine learning experiments. It was originally developed for our paper Convolutional neural networks: a magic bullet for gravitational-wave detection? [arXiv:1904.08693] and used to generate the training and testing data for the network presented there.
More specifically, the methods provided in this repository here will help you with the simulation of GW signals from compact binary coalescences (e.g., binary black hole mergers), adding these signals into a pieces of background noise (either synthetic or real LIGO background recordings) and applying standard post-processing steps (e.g., whitening and band-passing) to results.
", "rawMarkdown": "**[Detection of gravitational-wave signals from binary neutron star mergers using machine learning:](https://github.com/gwastro/bns-machine-learning-search)**\nAs two neutron stars merge, they emit gravitational waves that can potentially be detected by earth bound detectors. Matched-filtering based algorithms have traditionally been used to extract quiet signals embedded in noise. We introduce a novel neural-network based machine learning algorithm that uses time series strain data from gravitational-wave detectors to detect signals from non-spinning binary neutron star mergers. For the Advanced LIGO design sensitivity, our network has an average sensitive distance of 130 Mpc at a false-alarm rate of 10 per month. Compared to other state-of-the-art machine learning algorithms, we find an improvement by a factor of 6 in sensitivity to signals with signal-to-noise ratio below 25. However, this approach is not yet competitive with traditional matched-filtering based methods. A conservative estimate indicates that our algorithm introduces on average 10.2 s of latency between signal arrival and generating an alert. We give an exact description of our testing procedure, which can not only be applied to machine learning based algorithms but all other search algorithms as well. We thereby improve the ability to compare machine learning and classical searches.\n\n**[LIGO-Autoencoder: An anomaly detection algorithm for gravitational waves:](https://github.com/eric-moreno/Anomaly-Detection-Autoencoder)**\nGravitational-Wave Detection Algorithms with Spiking Neural Networks. Download dataset containing 5,000 injection events and 20,000 noise events. Place in directory labeled 'data'. Must have GWpy package.\n\n**[ggwd: generate gravitational-wave data:](https://github.com/timothygebhard/ggwd)**\nUse PyCBC / LALSuite to generate synthetic gravitational-wave data. The purpose of this repository is to provide a starting point for generating realistic synthetic gravitational-wave data which can then be used, for example, as training data for machine learning experiments. It was originally developed for our paper Convolutional neural networks: a magic bullet for gravitational-wave detection? [arXiv:1904.08693] and used to generate the training and testing data for the network presented there.\n\nMore specifically, the methods provided in this repository here will help you with the simulation of GW signals from compact binary coalescences (e.g., binary black hole mergers), adding these signals into a pieces of background noise (either synthetic or real LIGO background recordings) and applying standard post-processing steps (e.g., whitening and band-passing) to results.", "votes": null }, { "id": "1563251", "postDate": "10/28/2021 06:51:40", "content": "Hey,
\nThank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey https://forms.gle/QP9L16niPexozyhu5.
\nThank you all,
\nRegards,
\nChris
Hey,
\nThank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey https://forms.gle/QP9L16niPexozyhu5.
\nThank you all,
\nRegards,
\nChris