Neural Network-Based Approaches to High-Energy Physics

Year 2025, Volume: 8 Issue: 1, 1 - 10, 22.06.2025

Serpil Yalçın Kuzu , Ayben Karasu Uysal , Mustafa Kaya

Abstract

The exploration of quarkonium states at the Large Hadron Collider (LHC) plays a critical role in advancing particle physics and validating quantum theories. One of the key processes, the decay of J/ψ mesons into electron-positron pairs (J/ψ→e⁺e⁻), offers both valuable insights and challenges, particularly due to the vast datasets produced by high-energy collisions. This study focuses on enhancing the analysis of such collision events through the application of Deep Neural Networks (DNNs).By leveraging techniques such as data preprocessing, feature engineering, and hyperparameter tuning, the study demonstrates the power of DNNs in efficiently processing and classifying complex LHC datasets. The model's performance is assessed using metrics like precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC ROC). The findings underscore the potential of DNNs in improving particle identification and advancing high-energy physics data analysis.

Keywords

Quarkonium , charmonium , deep neural networks , high energy physics

Ethical Statement

There is no conflict of interest in this study.

Project Number

This work was supported by the Scientific and Technological Research Council of Turkey (TUBITAK) Project Number 123F060 and Yildiz Technical University Project Number FBA-2024-6089.

References

• A., Radovic, et al. (2018). Machine learning at the energy and intensity frontiers of particle physics. Nature, 560(7716), 41-48.
• S., Yalcin Kuzu, S. (2022). J/ψ production with machine learning at the LHC. Eur. Phys. J. Plus, 137(392).
• Smith, J., et al. (2021). Application of neural networks in high energy physics: An overview. Physics Letters B, 824, 136834.
• Kumar, P., & Banerjee, S. (2023). Deep learning approaches for quarkonium state analysis in high-energy collisions. Nuclear Physics B, 976, 115715.
• Zhang, Y., & Chen, W. (2020). Enhancing particle identification with deep learning in LHC data. Computational Physics Communications, 251, 107099.
• Trenti, M., et al. (2020). Quantum-inspired machine learning on high-energy physics data. npj Quantum Information, 7, 1-8.
• Giommi, L., et al. (2022). Cloud native approach for Machine Learning as a Service for High Energy Physics. Proceedings of ISGC2022.
• Butter, A., et al. (2022). Machine learning and LHC event generation. SciPost Physics, 14(4), 79.
• Zhao, Q., et al. (2023). Δ2 machine learning for reaction property prediction. Chemical Science, 14, 13392-13401.
• Nagano, L., et al. (2023). Quantum data learning for quantum simulations in high-energy physics. Physical Review Research, 5, 043250.
• Alnuqaydan, A., et al. (2022). SYMBA: Symbolic computation of squared amplitudes in high energy physics with machine learning. Machine Learning: Science and Technology, 4.
• Delgado, A., & Hamilton, K. E. (2022). Unsupervised quantum circuit learning in high energy physics. Physical Review D, 106, 096006.
• Nair, V., & Hinton, G. E. (2010). Rectified linear units improve restricted Boltzmann machines.In Proceedings of the 27th International Conference on Machine Learning (ICML-10) (pp. 807-814).
• Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533-536.
• Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
• Srivastava, N., Hinton, G. E., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15(1), 1929-1958.
• T. McCauley, CMS releases open data for Machine Learning, https://cms.cern/news/cms-releases-open-data-machine-learning (2014)
• T. McCauley, J/ψ to two electrons from 2010, https://opendata.cern.ch/record/302, CERN Open Data Portal, https://doi.org/10.7483/OPENDATA. CMS.97YF.C4AH (2014)
• T. McCauley, Eventswith two electrons from 2010, https://opendata.cern.ch/record/304, CERN Open Data Portal, https://doi.org/10.7483/OPENDATA. CMS.PCSW.AHVG (2014)
• Python Software Foundation. (n.d.). Python Documentation.Retrieved from https://docs.python.org/3/
• Chollet, F. (2015). Keras: The Python Deep Learning Library. Retrieved from https://keras.io
• Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., ... & Zheng, X. (2016). TensorFlow: A system for large-scale machine learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), 265-283.
• S. Nourbakhsh, Studio degli eventi J/ψ in due elettroni con i primi dati di CMS (2010).
• NA61/SHINE collaboration, Eur. Phys. J. C 80, 1151 (2020)
• CMS collaboration, Phys. Rev. C 96, 014915 (2017)
• Particle Data Group, M. Tanabashiet al., Phys. Rev. D 98, 030001 (2018).
• Keskar, N. S., & Socher, R. (2017). Improving generalization performance by switching from Adam to SGD. arXiv preprint arXiv:1712.07628.
• LeCun, Y. vd. 2015. “Deep learning”, Nature, 521, 436-444, doi: https://doi.org/10.1038/nature14539.
• Müller A. C., Guido, S., 2016. Introduction to Machine Learning with Python, O'Reilly Media Inc., USA: Sebastopol California.
• Sokolova, M. vd. 2006. “Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation”, Australasian joint conference on artificial intelligence, 1015-1021, Hobart, Australia, doi: 10.1007/11941439_114.