Abstract
This work presents a new two-step approach for elementary particle tracking that combines the advantages of both local and global tracking algorithms. On the first stage, where the graph of possible track-candidates is too big to fit into memory, a recurrent neural network model TrackNETv3 is used for building track candidates. On the second stage there is a graph neural network GraphNet needed for clearing the graph from the fake segments. The results of testing the proposed approach on the 3,2 GeV Ar+Pb simulation for the BM@N RUN7 are presented.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Frühwirth, R.: Application of Kalman filtering to track and vertex fitting. Nuclear Instrum. Meth. Phys. Res. Sect. A Acceler. Spectrom. Detect. Assoc. Equip. 262(2–3), 444–450 (1987)
Nikolskaia, A., et al.: TrackNETv3 with optimized inference for BM@N tracking. In: Proceedings of the 9th International Conference “Distributed Computing and Grid Technologies in Science and Education” (GRID 2021), 5–9 July 2021, vol. 3041, pp. 332–337. Dubna, Russia (2021)
Bakina, O., et al.: Global strategy of tracking on the basis of graph neural network for BES-III CGEM inner detector. In: Bakina, O., et al. (eds.) AIP Conference Proceedings, vol. 2377, no. 1, pp. 060001. AIP Publishing LLC (2021)
Amrouche, S., et al. (eds.) The Tracking Machine Learning Challenge: Accuracy Phase. In: Escalera, S., Herbrich, R. (eds.) The NeurIPS '18 Competition. SSCML, pp. 231–264. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-29135-8_9
Ju, X., et al.: Performance of a geometric deep learning pipeline for HL-LHC particle tracking. Eur. Phys. J. C 81(10), 1–14 (2021). https://doi.org/10.1140/epjc/s10052-021-09675-8
Baranov, D.A.: Novel approach to the particle track reconstruction based on deep learning methods. In: Baranov, D., Mitsyn, S., Ososkov, G., Goncharov, P., Tsytrinov, A. (eds.) Selected Papers of the 26th International Symposium on Nuclear Electronics and Computing (NEC 2017), 25–29 Sept 2017, vol. 2023, pp. 37–45. Budva, Montenegro. CEUR Proceedings (2017)
Baranov, D.A.: Catch and Prolong: recurrent neural network for seeking track-candidates. In: Baranov, D., Ososkov, G., Goncharov, P., Tsytrinov, A. (eds.) The XXII International Scientific Conference of Young Scientists and Specialists (AYSS-2018), vol. 201, pp. 05001. EPJ Web of Conferences. EDP Sciences (2019)
Goncharov, P.: Particle track reconstruction with the TrackNETv2. In: Goncharov, P., Ososkov, G., Baranov, D. (eds.) AIP Conference Proceedings, vol. 2163, no. 1, pp. 040003. AIP Publishing LLC (2019)
Goncharov, P., et al.: BM@ N tracking with novel deep learning methods. In: Goncharov, P., Shchavelev, E., Ososkov, G., Baranov, D. (eds.) EPJ Web of Conferences, vol. 226, pp. 03009. EDP Sciences (2020)
Johnson, J., Douze, M., Jégou, H.: Billion-scale similarity search with gpus. IEEE Trans. Big Data 7 (2019)
Kapishin, M., et al.: Studies of baryonic matter at the BM@N experiment (JINR). Nuclear Phys. A 982, 967–970 (2019)
Adam, G., et al.: CEUR Workshop Proc. 2267, 638–644 (2018)
Acknowledgments
The calculations were carried out on the basis of the HybriLIT heterogeneous computing platform (LIT, JINR) [12].
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Rusov, D. et al. (2023). Recurrent and Graph Neural Networks for Particle Tracking at the BM@N Experiment. In: Kryzhanovsky, B., Dunin-Barkowski, W., Redko, V., Tiumentsev, Y. (eds) Advances in Neural Computation, Machine Learning, and Cognitive Research VI. NEUROINFORMATICS 2022. Studies in Computational Intelligence, vol 1064. Springer, Cham. https://doi.org/10.1007/978-3-031-19032-2_32
Download citation
DOI: https://doi.org/10.1007/978-3-031-19032-2_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19031-5
Online ISBN: 978-3-031-19032-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)