Saved in:
Bibliographic Details
Main Authors: Matseiko, A., Plotnikov, G., Kharuk, I.
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.11176
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917482043801600
author Matseiko, A.
Plotnikov, G.
Kharuk, I.
author_facet Matseiko, A.
Plotnikov, G.
Kharuk, I.
contents We present a neural-network-based data processing pipeline for Baikal-GVD, designed to improve event reconstruction quality and accelerate neutrino candidates selection. The pipeline comprises three stages: fast suppression of extensive air shower events, suppression of noise optical modules activations, and extraction of high confidence neutrino candidates. All three networks employ a transformer architecture that exploits inter-hit correlations through the attention mechanism. Applied sequentially, the pipeline achieves orders-of-magnitude speedup over the standard reconstruction chain. Moreover, noise suppression neural network surpasses the accuracy of algorithmic noise suppression algorithms and provides estimate for time residuals of the signal hits, which is crucial for identification of track-like hits. We address the domain shift between Monte Carlo simulations and experimental data by incorporating a domain adaptation technique, demonstrating improved agreement between the two domains. The resulting framework enables near-real-time event classification, with direct applications to multi-messenger alert systems and diffuse neutrino flux measurements.
format Preprint
id arxiv_https___arxiv_org_abs_2605_11176
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From raw data to neutrino candidates: a neural-network pipeline for Baikal-GVD
Matseiko, A.
Plotnikov, G.
Kharuk, I.
Instrumentation and Methods for Astrophysics
Machine Learning
High Energy Physics - Experiment
We present a neural-network-based data processing pipeline for Baikal-GVD, designed to improve event reconstruction quality and accelerate neutrino candidates selection. The pipeline comprises three stages: fast suppression of extensive air shower events, suppression of noise optical modules activations, and extraction of high confidence neutrino candidates. All three networks employ a transformer architecture that exploits inter-hit correlations through the attention mechanism. Applied sequentially, the pipeline achieves orders-of-magnitude speedup over the standard reconstruction chain. Moreover, noise suppression neural network surpasses the accuracy of algorithmic noise suppression algorithms and provides estimate for time residuals of the signal hits, which is crucial for identification of track-like hits. We address the domain shift between Monte Carlo simulations and experimental data by incorporating a domain adaptation technique, demonstrating improved agreement between the two domains. The resulting framework enables near-real-time event classification, with direct applications to multi-messenger alert systems and diffuse neutrino flux measurements.
title From raw data to neutrino candidates: a neural-network pipeline for Baikal-GVD
topic Instrumentation and Methods for Astrophysics
Machine Learning
High Energy Physics - Experiment
url https://arxiv.org/abs/2605.11176