Despite the tremendous amount of knowledge that current-generation gravitational-wave (GW) observatories have already provided, they only probe the “tip of the iceberg” of the  GW Universe. The next generation of ground- and space-based detectors, such as the Einstein Telescope (ET) and the Laser Interferometer Space Antenna (LISA), will vastly expand the range of observable astrophysical systems, from white dwarfs all the way to super-massive black holes, while also enabling detections at truly cosmological scales and with rates up to a million per year. GW-Learn is an ambitious project that brings together an interdisciplinary team of leading experts, across six institutions, in order to develop techniques, theories, algorithms, and simulations that will allow for optimal knowledge acquisition from the next-generation GW observatories. It is composed of three highly interconnected work packages, with Machine Learning as the common thread that ties together the different scientific disciplines of this project, including astrophysics, cosmology, fundamental gravity, and experimental physics.

Scientific topics of the project

The GW-Learn Team

Know more about the members and the GW-Learn Team here.

Participating Institutions

Department of Astronomy,
Department of Theoretical Physics,
& Department of Particle Physics

University of Geneva

Institute of Computational Sciences,
& Institute of Physics

Centre for Artificial Intelligence,
& Institute of Geophysics

Project funded by: