### Goal of the Competition
The goal of this competition is to find [continuous gravitational-wave signals](https://www.ligo.org/science/GW-Continuous.php). You will develop a model sensitive enough to detect weak yet long-lasting signals emitted by rapidly-spinning neutron stars within noisy data.
Your work will help scientists detect something new: a second class of gravitational waves! The first gravitational wave discoveries earned a Nobel Prize. Further study of these waves may enable scientists to learn about the structure of the most extreme stars in our universe.
### Context
When scientists detected the first class of gravitational waves in 2015, they expected the discoveries to continue. There are four classes, yet at present only signals from merging black holes and neutron stars have been detected. Among those remaining are *continuous* gravitational-wave signals. These are weak yet long-lasting signals emitted by rapidly-spinning neutron stars. Imagine the mass of our Sun but condensed into a ball the size of a city and spinning over 1,000 times a second. The extreme compactness of these stars, composed of the densest material in the universe, could allow continuous waves to be emitted and then detected on Earth. There are potentially many continuous signals from neutron stars in our own galaxy and the current challenge for scientists is to make the first detection, and hopefully data science can help with this mission.
This image, taken from a [2021 paper](https://arxiv.org/abs/2111.13106) by the LIGO-Virgo-KAGRA collaboration, shows the maximum amplitude of a continuous wave any of these neutron stars could emit without being found by the search analyses. Circled stars show results constraining the physical properties of specific neutron stars. Traditional approaches to detecting these weak and hard-to-find continuous signals are based on matched-filtering variants. Scientists create a bank of possible signal waveform templates and ask how correlated each waveform is with the measured noisy data. High correlation is consistent with the presence of a signal similar to that waveform. Due to the long duration of these signals, banks could easily contain hundreds of quintillions of templates; yet, with so many possible waveforms, scientists don’t have the computational power to use the approach without making approximations that weaken the sensitivity to the signals.
G2Net is a network of Gravitational Wave, Geophysics and Machine Learning. Via an Action from COST (European Cooperation in Science and Technology), a funding agency for research and innovation networks, G2Net aims to create a broad network of scientists. From four different areas of expertise, namely GW physics, Geophysics, Computing Science and Robotics, these scientists have agreed on a common goal of tackling challenges in data analysis and noise characterization for GW detectors.
By helping G2Net in this challenge you'll enable scientists to improve their sensitivity, leading to new discoveries in the field. As a result, scientists could learn more about the structure of the most extreme stars in our universe.
### Resources
Resources for the generation of background noise and continuous gravitational-wave signals can be found in [this pinned discussion](https://www.kaggle.com/competitions/g2net-detecting-continuous-gravitational-waves/discussion/347052). A brief [notebook](https://www.kaggle.com/code/rodrigotenorio/generating-continuous-gravitational-wave-signals) summarizing the very basics of generating data using [PyFstat](https://github.com/PyFstat/PyFstat) is also provided.
### Acknowledgments
We acknowledge support from the LIGO-Virgo-Kagra Collaboration of which the hosts are members. Specifically we acknowledge the use of the Gravitational Wave Open Science Centre ([GWOSC](https://www.gw-openscience.org)) and the software resources [lalsuite](https://git.ligo.org/lscsoft/lalsuite) and [PyFstat](https://github.com/PyFstat/PyFstat).
This challenge can be cited using the BibTeX entry attached below, should any of the results
here generated be useful for any specific research results:
```
@techreport{G2NetCWKaggleChallenge,
author = "Tenorio, Rodrigo and Williams, Michael J. and Messenger, Chris",
title = "Learning to detect continuous gravitational waves",
number = "LIGO-P2200295",
url = {https://dcc.ligo.org/P2200295},
year = "2022"
}
```
