The development and application of deep learning in high-energy nuclear physics

Jingzong ZHANG; Shuang GUO; Lilin ZHU; Lingxiao WANG; Guoliang MA

doi:10.11889/j.0253-3219.2025.hjs.48.250130

NUCLEAR TECHNIQUES, Volume. 48, Issue 5, 050011(2025)

The development and application of deep learning in high-energy nuclear physics

Jingzong ZHANG^1,2, Shuang GUO², Lilin ZHU¹, Lingxiao WANG^、*, and Guoliang MA^2、**

Author Affiliations

¹Department of Physics, Sichuan University, Chengdu 610064, China

²(Key Laboratory of Nuclear Physics and Ion-beam Application (MOE), Institute of Modern Physics, Fudan University, Shanghai 200433, China) 3(Shanghai Research Center for Theoretical Nuclear Physics, NSFC and Fudan University, Shanghai 200438, China)

show less

Abstract Get PDF(in Chinese)

References(77)

[1] Adams J, Aggarwal M M, Ahammed Z. Experimental and theoretical challenges in the search for the quark-gluon plasma: The STAR Collaboration's critical assessment of the evidence from RHIC collisions[J]. Nuclear Physics A, 757, 102-183(2005).

[2] Adcox K, Adler S S, Afanasiev S. Formation of dense partonic matter in relativistic nucleus-nucleus collisions at RHIC: Experimental evaluation by the PHENIX collaboration[J]. Nuclear Physics A, 757, 184-283(2005).

[3] Schenke B, Jeon S, Gale C. Elliptic and triangular flow in event-by-event D=3+1 viscous hydrodynamics[J]. Physical Review Letters, 106, 042301(2011).

[4] Heinz U, Snellings R. Collective flow and viscosity in relativistic heavy-ion collisions[J]. Annual Review of Nuclear and Particle Science, 63, 123-151(2013).

[5] Qin G Y. Theory of jet quenching in ultra-relativistic nuclear collisions[J]. Nuclear Physics A, 931, 165-175(2014).

[6] Qin G Y, Wang X N. Jet quenching in high-energy heavy-ion collisions[J]. International Journal of Modern Physics E, 24, 1530014(2015).

[7] Song H C, Bass S A, Heinz U et al. 200 AGeV Au+Au collisions serve a nearly perfect quark-gluon liquid[J]. Physical Review Letters, 106, 192301(2011).

[8] Müller B, Nagle J L. Results from the relativistic heavy ion collider[J]. Annual Review of Nuclear and Particle Science, 56, 93-135(2006).

[9] Gale C, Jeon S, Schenke B. Hydrodynamic modeling of heavy-ion collisions[J]. International Journal of Modern Physics A, 28, 1340011(2013).

[10] Karsch F, Bazavov A, Ding H T et al. Conserved charge fluctuations from lattice QCD and the beam energy scan[J]. Nuclear Physics A, 956, 352-355(2016).

[11] Xu H J, Li Z P, Song H C. High-order flow harmonics of identified hadrons in 2.76 ATeV Pb+Pb collisions[J]. Physical Review C, 93, 064905(2016).

[12] Zhu X, Zhou Y, Xu H. Correlations of flow harmonics in 2.76 ATeV Pb-Pb collisions[J]. Physical Review C, 95, 044902(2017).

[13] Chang N B, Cao S S, Qin G Y. Probing medium-induced jet splitting and energy loss in heavy-ion collisions[J]. Physics Letters B, 781, 423-432(2018).

[14] Acharya S, Adamová D, Adler A, ALICE Collaboration et al. The ALICE experiment: a journey through QCD[J]. The European Physical Journal C, 84, 813(2024).

[15] Bishop C M, Bishop H. Deep learning: Foundations and concepts[M]. Springer Nature(2023).

[16] He J J, He W B, Ma Y G et al. Machine-learning-based identification for initial clustering structure in relativistic heavy-ion collisions[J]. Physical Review C, 104, 044902(2021).

[17] WANG Lingxiao, PANG Longgang, ZHOU Kai. Applications of deep learning in high energy nuclear physics[J]. Scientia Sinica Physica, Mechanica & Astronomica, 52, 252003(2022).

[18] Zhou K, Wang L X, Pang L G et al. Exploring QCD matter in extreme conditions with Machine Learning[J]. Progress in Particle and Nuclear Physics, 135, 104084(2024).

[19] Boehnlein A, Diefenthaler M, Sato N et al. Colloquium: Machine learning in nuclear physics[J]. Reviews of Modern Physics, 94, 031003(2022).

[20] He W B, Ma Y G, Pang L G et al. High-energy nuclear physics meets machine learning[J]. Nuclear Science and Techniques, 34, 88(2023).

[21] Aarts G, Fukushima K, Hatsuda T et al. Physics-driven learning for inverse problems in quantum chromodynamics[J]. Nature Reviews Physics, 7, 154-163(2025).

[22] Ma Y G, Pang L G, Wang R et al. Phase transition study meets machine learning[J]. Chinese Physics Letters, 40, 122101(2023).

[23] Zhang R R, Guo Z Y, Gao P et al. Point-M2AE: multi-scale masked autoencoders for hierarchical point cloud pre-training[J]. Advances in Neural Information Processing Systems, 35, 27061-27074(2022).

[24] Zhang R R, Wang L H, Qiao Y et al. Learning 3D representations from 2D pre-trained models via image-to-point masked autoencoders[C], 21769-21780(2023).

[25] Yu X M, Tang L L, Rao Y M et al. Point-BERT: pre-training 3D point cloud transformers with masked point modeling[C], 19291-19300(2022).

[26] Liu H T, Cai M, Lee Y J[M]. Masked discrimination for self-supervised learning on point clouds, 657-675(2022).

[27] Mehta P, Bukov M, Wang C H et al. A high-bias, low-variance introduction to machine learning for physicists[J]. Physics Reports, 810, 1-124(2019).

[28] Buncic P, Krzewicki M, Vyvre P. Technical design report for the upgrade of the online-offline computing system[R](2015).

[29] Kain V, Hirlander S, Goddard B et al. Sample-efficient reinforcement learning for CERN accelerator control[J]. Physical Review Accelerators and Beams, 23, 124801(2020).

[30] GAO Zepeng, LI Qingfeng. Studies on several problems in nuclear physics by using machine learning[J]. Nuclear Techniques, 46, 080009(2023).

[31] LI Fupeng, PANG Longgang, WANG Xinnian. Application of machine learning to the study of QCD transition in heavy ion collisions[J]. Nuclear Techniques, 46, 040014(2023).

[32] He W B, Li Q F, Ma Y G et al. Machine learning in nuclear physics at low and intermediate energies[J]. Science China Physics, Mechanics & Astronomy, 66, 282001(2023).

[33] Bass S A, Bischoff A, Maruhn J A et al. Neural networks for impact parameter determination[J]. Physical Review C, 53, 2358-2363(1996).

[34] Gazula S, Clark J W, Bohr H. Learning and prediction of nuclear stability by neural networks[J]. Nuclear Physics A, 540, 1-26(1992).

[35] Gernoth K A, Clark J W, Prater J S et al. Neural network models of nuclear systematics[J]. Physics Letters B, 300, 0370269393907384(1993).

[36] Costiris N, Mavrommatis E, Gernoth K et al. Decoding beta-decay systematics: a global statistical model for beta- halflives[J]. Physical Review C, 80, 044332(2009).

[37] Clark J W, Li H C. Application of support vector machines to global prediction of nuclear properties[J]. International Journal of Modern Physics B, 20, 5015-5029(2006).

[38] Pang L G, Zhou K, Su N et al. An equation-of-state-meter of quantum chromodynamics transition from deep learning[J]. Nature Communications, 9, 210(2018).

[39] Du Y L, Zhou K, Steinheimer J et al. Identifying the nature of the QCD transition in relativistic collision of heavy nuclei with deep learning[J]. The European Physical Journal C, 80, 516(2020).

[40] Mikuni V, Canelli F. Point cloud transformers applied to collider physics[J]. Machine Learning: Science and Technology, 2, 035027(2021).

[41] Lin Z W, Ko C M, Li B A et al. Multiphase transport model for relativistic heavy ion collisions[J]. Physical Review C, 72, 064901(2005).

[42] Lin Z W, Zheng L. Further developments of a multi-phase transport model for relativistic nuclear collisions[J]. Nuclear Science and Techniques, 32, 113(2021).

[43] Charles R Q, Hao S, Mo K C et al. PointNet: deep learning on point sets for 3D classification and segmentation[C], 77-85(2017).

[44] Guo S, Wang H S, Zhou K et al. Machine learning study to identify collective flow in small and large colliding systems[J]. Physical Review C, 110, 024910(2024).

[45] Huang Y G, Pang L G, Luo X F et al. Probing criticality with deep learning in relativistic heavy-ion collisions[J]. Physics Letters B, 827, 137001(2022).

[46] Qu H L, Gouskos L. Jet tagging via particle clouds[J]. Physical Review D, 101, 056019(2020).

[47] Qi C R, Yi L, Su H et al. PointNet++: deep hierarchical feature learning on point sets in a metric space[J]. Advances in Neural Information Processing Systems, 30(2017).

[48] Sohail S S, Himeur Y, Kheddar H et al. Advancing 3D point cloud understanding through deep transfer learning: a comprehensive survey[J]. Information Fusion, 113, 102601(2025).

[49] Zhao H S, Jiang L, Jia J Y et al. Point transformer[C], 16239-16248(2021).

[50] Wu X, Lao Y, Jiang L et al. Point transformer v2: Grouped vector attention and partition-based pooling[J]. Advances in Neural Information Processing Systems, 35, 33330-33342(2022).

[51] Wu X Y, Jiang L, Wang P S et al. Point transformer V3: simpler, faster, stronger[C], 4840-4851(2024).

[52] Wu X Y, Xu X, Kong L D et al. Point transformer V3 extreme: 1st place solution for 2024 waymo open dataset challenge in semantic segmentation[EB/OL], 2407.15282(2024). https://arxiv.org/abs/2407.15282v1

[53] Qu H, Li C, Qian S. Particle transformer for jet tagging[C], 18281-18292(2022).

[54] Liu Z M, Zhao W B, Song H C. Principal component analysis of collective flow in relativistic heavy-ion collisions[J]. The European Physical Journal C, 79, 870(2019).

[55] Song H C, Heinz U. Causal viscous hydrodynamics in 2+1 dimensions for relativistic heavy-ion collisions[J]. Physical Review C, 77, 064901(2008).

[56] Shen C, Qiu Z, Song H C et al. The iEBE-VISHNU code package for relativistic heavy-ion collisions[J]. Computer Physics Communications, 199, 61-85(2016).

[57] Nara Y. JAM: an event generator for high energy nuclear collisions[J]. EPJ Web of Conferences, 208, 11004(2019).

[58] Wu J, Lin Y F, Wu Y F et al. Probing QCD critical fluctuations from intermittency analysis in relativistic heavy-ion collisions[J]. Physics Letters B, 801, 135186(2020).

[59] Bożek P. Principal component analysis of the nonlinear coupling of harmonic modes in heavy-ion collisions[J]. Physical Review C, 97, 034905(2018).

[60] Finke T, Krämer M, Morandini A et al. Autoencoders for unsupervised anomaly detection in high energy physics[J]. Journal of High Energy Physics, 2021, 161(2021).

[61] Wang R, Ma Y G, Wada R et al. Nuclear liquid-gas phase transition with machine learning[J]. Physical Review Research, 2, 043202(2020).

[62] Tanaka A, Tomiya A, Hashimoto K[M]. Deep learning and physics(2021).

[63] Lundberg S M, Lee S I. A unified approach to interpreting model predictions[J]. Advances in Neural Information Processing Systems, 30(2017).

[64] Pezoa R, Salinas L, Torres C. Explainability of high energy physics events classification using SHAP[J]. Journal of Physics: Conference Series, 2438, 012082(2023).

[65] Angelis D, Sofos F, Karakasidis T E. Artificial intelligence in physical sciences: symbolic regression trends and perspectives[J]. Archives of Computational Methods in Engineering, 30, 3845-3865(2023).

[66] Udrescu S M, Tegmark M. AI Feynman: a physics-inspired method for symbolic regression[J]. Science Advances, 6, eaay2631(2020).

[67] Vilalta R, Drissi Y. A perspective view and survey of meta-learning[J]. Artificial Intelligence Review, 18, 77-95(2002).

[68] Maharana K, Mondal S, Nemade B. A review: Data pre-processing and data augmentation techniques[J]. Global Transitions Proceedings, 3, 91-99(2022).

[69] Shorten C, Khoshgoftaar T M. A survey on image data augmentation for deep learning[J]. Journal of Big Data, 6, 60(2019).

[70] Mumuni A, Mumuni F. Data augmentation: a comprehensive survey of modern approaches[J]. Array, 16, 100258(2022).

[71] Biamonte J, Wittek P, Pancotti N et al. Quantum machine learning[J]. Nature, 549, 195-202(2017).

[72] Schuld M, Sinayskiy I, Petruccione F. An introduction to quantum machine learning[J]. Contemporary Physics, 56, 172-185(2015).

[73] Cerezo M, Verdon G, Huang H Y et al. Challenges and opportunities in quantum machine learning[J]. Nature Computational Science, 2, 567-576(2022).

[74] Mikuni V, Nachman B. Score-based generative models for calorimeter shower simulation[J]. Physical Review D, 106, 092009(2022).

[75] Devlin P, Qiu J W, Ringer F et al. Diffusion model approach to simulating electron-proton scattering events[J]. Physical Review D, 110, 016030(2024).

[76] Wiering M A, Van Otterlo M. Reinforcement learning[J]. Adaptation, Learning and Optimization, 12, 729(2012).

[77] Li Y X. Deep reinforcement learning: an overview[EB/OL], 1701.07274(2017). https://arxiv.org/abs/1701.07274v6

Tools

Get Citation

Copy Citation Text

Jingzong ZHANG, Shuang GUO, Lilin ZHU, Lingxiao WANG, Guoliang MA. The development and application of deep learning in high-energy nuclear physics[J]. NUCLEAR TECHNIQUES, 2025, 48(5): 050011

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Special Topics on Applications of Machine Learning in Nuclear Physics and Nuclear Data

Received: Mar. 24, 2025

Accepted: --

Published Online: Jun. 26, 2025

The Author Email: Lingxiao WANG (王凌霄), Guoliang MA (马国亮)

DOI:10.11889/j.0253-3219.2025.hjs.48.250130

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology