A prototype for a real-time Gravitational Wave transient signal classifier
The Project challenge
A single GW detector typically produces data with a rate of 7-8 Tb per day with a flux of 40Mb/s, and these data need to be analysed in a fast and efficient way to increase the detection confidence and obtain relevant information.
Wavefier exploits the combination of different tools to build a pipeline capable of analysing online/offline data coming from Gravitational Wave detectors.
Wavefier is an independent platform with a simple pipeline integration and result visualisation with cutting-edge technical solutions.
It can be used and tested on cluster infrastructures, via different software architecture solutions to prototype a scalable pipeline for big data analysis in astronomy and in other domains.
COMMpla provides software development as well as architecture management.
The developed pipeline is based on multiple technologies, combined together to obtain a scalable and interoperable product, ready to be deployed in complex environments.
- Scientific algorithms to reduce noise
- Apache Kafka to have an event streaming platform
- TensorFlow to apply ML algorithms to the data
- InfluxDB to store analysis outputs
- Grafana to show time-based result dashboards
- Continuous Integration/Deployment
- Kubernetes to deploy Wavefier on complex clusters
WaveFier is the result of an industral collaboration project with “CNRS – Center National de la Recherche Scientifique in Paris” acting on behalf of the “Laboratoire d’Annecy de physique des particules – LAPP UMR n. 51814” , carried out in the context of the Asterics / Obelics project of the European Union’s H2020 Programme.
Credits: Elena Cuoco – Ph.D. researcher Head of Data Science Office @EGO-Virgo “European Gravitational Observatory” – Scientific Supervisor of the project
Do you want to learn more about how we can support you with cutting-edge technical solutions to your data visualisation needs?
Fill out the form below and let’s have a chat!