Rejecting noise in Baikal-GVD data with neural networks
- Resource Type
- Working Paper
- Authors
- Kharuk, I.; Rubtsov, G.; Safronov, G.
- Source
- Subject
- Astrophysics - Instrumentation and Methods for Astrophysics
Astrophysics - High Energy Astrophysical Phenomena
Computer Science - Machine Learning
- Language
Baikal-GVD is a large ($\sim$1 km$^3$) underwater neutrino telescope installed in the fresh waters of Lake Baikal. The deep lake water environment is pervaded by background light, which is detectable by Baikal-GVD's photosensors. We introduce a neural network for an efficient separation of these noise hits from the signal ones, stemming from the propagation of relativistic particles through the detector. The model has a U-net-like architecture and employs temporal (causal) structure of events. The neural network's metrics reach up to 99\% signal purity (precision) and 96\% survival efficiency (recall) on Monte-Carlo simulated dataset. We compare the developed method with the algorithmic approach to rejecting the noise and discuss other possible architectures of neural networks, including graph-based ones.