WG3 explores the use of Machine Learning (ML) techniques in the control and noise mitigation strategies of scientific experiments, specifically for Gravitational Wave (GW) detectors. GW detectors, both those currently running and those foreseen to be spaceborne, are uniquely complex instruments with specific and new challenges in terms of control and noise issues. These challenges call for significant adaptation and ingenuity in the ML approaches, which are seldom used as textbook cases and are often coupled with simulations and burden with heavy experimental constraints. These developments need diverse expertise and interaction, which is the benefit of the current COST action. This working group’s goal is to develop ML algorithms as part of the detectors’ feedback-control systems as well as for the feed-forward cancellation of noise.
In this workshop we address the following WG3’s tasks:
• Laser cavity control to optimise locking time and stability
• ML for glitch removal
• Deep learning for noise removal
• Newtonian noise cancellation with ML
• Data preprocessing with reinforcement learning
The workshop is organised ONLINE over two days, namely 22-23 March 2021, so that it accommodates both European and American participants. We will delve into the first three WG3 tasks in detail, with the help of the following invited presentations:
• Dr. Diego Bersanetti (INFN, Italy) "Interferometer Cavities: locking strategies and improvement possibilities"
• Dr. Fiodor Sorrentino (INFN, Italy) "Sqeezed light benches and optical alignment issues"
• Prof. Marco Cavaglia (Missouri Univeristy of Science and Technology, US) "Glitch removal in ground-based gravitational-wave interferometric detectors"
• Dr. Gabriele Vajente (Caltech, US) “Non stationary noise removal from LIGO data”
These speakers will also oversee a round table discussion on each of their topics, mainly on investigating the machine learning potential in their topics, but also discussing other topics of interest.
We encourage the submission of short contributions and/or posters on all five WG3 tasks mentioned above by everyone interested, in particular the WG3 members. These contributions could be original or already submitted/accepted/presented/published elsewhere.
We encourage communication and cooperation, especially during this pandemic-driven period, when we seldomly travel anymore and online conferences are attended by small audiences only.
Please send your title and abstract in advance, by March 15, to either/both Luigia and Andrea (email@example.com, firstname.lastname@example.org).