ODSL Forum: Christian Haack Machine-learning based detector optimization of the future P-ONE neutrino telescope

Friday 28 Jan 2022, 14:00 → 15:00 Europe/Berlin

Presenter: Christian Haack, TUM
Title: Machine-learning based detector optimization of the future P-ONE neutrino telescope

Abstract:

P-ONE is a planned cubic-kilometer scale neutrino detector in the Pacific ocean [1, 2]. Using existing infrastructure provided by Ocean Networks Canada (ONC), P-ONE will instrument the ocean with optical modules - which host PMT's as well as readout electronics - deployed on several vertical cables. While the hardware design of a first prototype cable [3] is currently being finalized, the detector geometry of the final instrument (up to 70 cables) is not yet fixed. Traditionally, the detector geometry would be optimized using a large-scale simulation campaign, which results in detector resolutions for discrete points in the geometry phase space. 
Recently, a new approach for detector optimization (see MODE collaboration [4]) is emerging. Using ML-based surrogate models, a differentiable parameterization of the expected detector response is obtained, which can then be used, to optimize the detector design based on external constraints, such as cost and desired physics potential.
In this talk, I will discuss the prospects and current state of applying an ML-based optimization approach to P-ONE.

References:

[1] https://www.pacific-neutrino.org/p-one
[2] https://www.nature.com/articles/s41550-020-1182-4
[3] https://pos.sissa.it/395/1197/pdf
[4] https://mode-collaboration.github.io/

As usual, the format will be a short presentation followed by plenty of discussion.

Please let all interested know about the Journal Club (get them to send their Email address).  We are looking forward to lively discussions.