Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

The data-driven future of high-energy-density physics

Abstract

High-energy-density physics is the field of physics concerned with studying matter at extremely high temperatures and densities. Such conditions produce highly nonlinear plasmas, in which several phenomena that can normally be treated independently of one another become strongly coupled. The study of these plasmas is important for our understanding of astrophysics, nuclear fusion and fundamental physics—however, the nonlinearities and strong couplings present in these extreme physical systems makes them very difficult to understand theoretically or to optimize experimentally. Here we argue that machine learning models and data-driven methods are in the process of reshaping our exploration of these extreme systems that have hitherto proved far too nonlinear for human researchers. From a fundamental perspective, our understanding can be improved by the way in which machine learning models can rapidly discover complex interactions in large datasets. From a practical point of view, the newest generation of extreme physics facilities can perform experiments multiple times a second (as opposed to approximately daily), thus moving away from human-based control towards automatic control based on real-time interpretation of diagnostic data and updates of the physics model. To make the most of these emerging opportunities, we suggest proposals for the community in terms of research design, training, best practice and support for synthetic diagnostics and data analysis.

Access options

Rent or Buy article

Get time limited or full article access on ReadCube.

from$8.99

All prices are NET prices.

Fig. 1: Shot rates and energy of large high-powered laser facilities in different eras.
Fig. 2: Integration of astrophysical information.
Fig. 3: Integrating information sources in ICF studies.
Fig. 4: High-repetition workflow.

References

  1. 1.

    Rose, S. Set the controls for the heart of the Sun. Contemp. Phys. 45, 109–121 (2004).

    ADS  CAS  Google Scholar 

  2. 2.

    Spears, B. K. et al. Deep learning: a guide for practitioners in the physical sciences. Phys. Plasmas 25, 080901 (2018). This tutorial paper gives an introduction to scientific machine learning, with examples taken from ICF research.

    ADS  Google Scholar 

  3. 3.

    Wang, Z., Peterson, J. L., Rea, C. & Humphreys, D. Special issue on machine learning, data science, and artificial intelligence in plasma research. IEEE Trans. Plasma Sci. 48, 1–2 (2020).

    ADS  Google Scholar 

  4. 4.

    Colvin, J. & Larsen, J. Extreme Physics (Cambridge Univ. Press, 2013).

  5. 5.

    Graziani, F., Desjarlais, M. P., Redmer, R. & Trickey, S. B. (eds) Frontiers and Challenges in Warm Dense Matter Lecture Notes in Computational Science and Engineering Vol. 96 (Springer, 2014).

  6. 6.

    Gould, O., Mangles, S., Rajantie, A., Rose, S. & Xie, C. Observing thermal Schwinger pair production. Phys. Rev. A 99, 052120 (2019).

    ADS  CAS  Google Scholar 

  7. 7.

    Millot, M. et al. Experimental evidence for superionic water ice using shock compression. Nat. Phys. 14, 297–302 (2018).

    CAS  Google Scholar 

  8. 8.

    Celliers, P. M. et al. Insulator−metal transition in dense fluid deuterium. Science 361, 677–682 (2018).

    ADS  CAS  PubMed  PubMed Central  Google Scholar 

  9. 9.

    Joshi, C. & Malka, V. Focus on laser- and beam-driven plasma accelerators. New J. Phys. 12, 045003 (2010).

    ADS  Google Scholar 

  10. 10.

    Hidding, B., Foster, B., Hogan, M. J., Muggli, P. & Rosenzweig, J. B. Directions in plasma wakefield acceleration. Phil. Trans. R. Soc. Math. Phys. Eng. Sci. 377, 20190215 (2019).

    ADS  CAS  Google Scholar 

  11. 11.

    Wang, W.-M. et al. Collimated ultrabright gamma rays from electron wiggling along a petawatt laser-irradiated wire in the QED regime. Proc. Natl Acad. Sci. USA 115, 9911–9916 (2018).

    ADS  CAS  PubMed  PubMed Central  Google Scholar 

  12. 12.

    Badziak, J. Laser-driven ion acceleration: methods, challenges and prospects. J. Phys. Conf. Ser. 959, 012001 (2018).

    Google Scholar 

  13. 13.

    Feng, J. et al. High-efficiency neutron source generation from photonuclear reactions driven by laser plasma accelerator. High Energy Density Phys. 36, 100753 (2020).

    CAS  Google Scholar 

  14. 14.

    Hidding, B. et al. Plasma wakefield accelerator research 2019−2040: a community-driven UK roadmap compiled by the plasma wakefield accelerator steering committee (PWASC). Working Paper (2019); preprint at https://arxiv.org/abs/1904.09205.

  15. 15.

    Nuckolls, J., Wood, L., Thiessen, A. & Zimmerman, G. Laser compression of matter to super-high densities: thermonuclear applications. Nature 239, 139–142 (1972).

    ADS  CAS  Google Scholar 

  16. 16.

    Hurricane, O. A. & Program, I. Overview of progress and future prospects in indirect drive implosions on the National Ignition Facility. J. Phys. Conf. Ser. 717, 012005 (2016).

    Google Scholar 

  17. 17.

    Fournier, K. NIF Monthly Highlights for July 2019. LLNL Technical Report, LLNL-TR-785259; NIF-1006466629981592, http://www.osti.gov/servlets/purl/1548376/ (Lawrence Livermore National Laboratory, 2019).

  18. 18.

    Remington, B. A., Rudd, R. E. & Wark, J. S. From microjoules to megajoules and kilobars to gigabars: probing matter at extreme states of deformation. Phys. Plasmas 22, 090501 (2015).

    ADS  Google Scholar 

  19. 19.

    Trines, R. CLF Annual Report 2017–2018, https://www.clf.stfc.ac.uk/Pages/Annual-Report-2017-18.aspx (Science and Technology Facilities Council, 2019).

  20. 20.

    Sturm, C. & Stöcker, H. The facility for antiproton and ion research FAIR. Phys. Part. Nucl. Lett. 8, 865–868 (2011).

    Google Scholar 

  21. 21.

    MacDonald, M. J. et al. Measurement of high-dynamic range X-ray Thomson scattering spectra for the characterization of nano-plasmas at LCLS. Rev. Sci. Instrum. 87, 11E709 (2016).

    CAS  PubMed  PubMed Central  Google Scholar 

  22. 22.

    Mitchell, T. Machine Learning (McGraw-Hill, 1997).

  23. 23.

    Sivia, D. & Skilling, J. Data Analysis: A Bayesian Tutorial (Oxford Univ. Press).

  24. 24.

    Brunton, S. L. & Kutz, J. N. Data-Driven Science and Engineering (Cambridge Univ. Press, 2019).

  25. 25.

    Reichstein, M. et al. Deep learning and process understanding for data-driven Earth system science. Nature 566, 195–204 (2019).

    ADS  CAS  PubMed  PubMed Central  Google Scholar 

  26. 26.

    Fleming, S. W. & Gupta, H. V. The physics of river prediction. Phys. Today 73, 46–52 (2020).

    Google Scholar 

  27. 27.

    Streeter, M. J. V. et al. Temporal feedback control of high-intensity laser pulses to optimize ultrafast heating of atomic clusters. Appl. Phys. Lett. 112, 244101 (2018).

    ADS  Google Scholar 

  28. 28.

    Gopalaswamy, V. et al. Tripled yield in direct-drive laser fusion through statistical modelling. Nature 565, 581–586 (2019). This paper is the first to use data-driven approaches to motivate and carry out new ICF experiments.

    ADS  CAS  PubMed  PubMed Central  Google Scholar 

  29. 29.

    Hatfield, P. W., Rose, S. J. & Scott, R. H. H. The blind implosion-maker: automated inertial confinement fusion experiment design. Phys. Plasmas 26, 062706 (2019).

    ADS  Google Scholar 

  30. 30.

    Martin, M., London, R., Goluoglu, S. & Whitley, H. An automated design process for short pulse laser driven opacity experiments. High Energy Density Phys. 26, 26–37 (2018).

    ADS  CAS  Google Scholar 

  31. 31.

    Raghu, M. & Schmidt, E. A Survey of Deep Learning for Scientific Discovery (2020); preprint at http://arxiv.org/abs/2003.11755.

  32. 32.

    Thayer, J. et al. Data systems for the Linac Coherent Light Source. Adv. Struct. Chem. Imag. 3, 3 (2017).

    CAS  Google Scholar 

  33. 33.

    Bernal, J. L., Peacock, J. A., Bernal, J. L. & Peacock, J. A. Conservative cosmology: combining data with allowance for unknown systematics. J. Cosmol. Astroparticle Phys. 2018, 002 (2018). This paper considers how to get realistic uncertainty estimates in the presence of unknown systematics.

    Google Scholar 

  34. 34.

    Osthus, D., Vander Wiel, S. A., Hoffman, N. M. & Wysocki, F. J. Prediction uncertainties beyond the range of experience: a case study in inertial confinement fusion implosion experiments. SIAM/ASA J. Uncertainty Quant. 7, 604–633 (2019).

    MathSciNet  MATH  Google Scholar 

  35. 35.

    Lang, M. & Owens, M. J. A variational approach to data assimilation in the solar wind. Space Weather 17, 59–83 (2019).

    ADS  Google Scholar 

  36. 36.

    Gaffney, J. A. et al. Making inertial confinement fusion models more predictive. Phys. Plasmas 26, 082704 (2019).

    ADS  Google Scholar 

  37. 37.

    Kasim, M. F., Galligan, T. P., Topp-Mugglestone, J., Gregori, G. & Vinko, S. M. Inverse problem instabilities in large-scale modeling of matter in extreme conditions. Phys. Plasmas 26, 112706 (2019).

    ADS  Google Scholar 

  38. 38.

    van de Plassche, K. L. et al. Fast modeling of turbulent transport in fusion plasmas using neural networks. Phys. Plasmas 27, 022310 (2020).

    ADS  Google Scholar 

  39. 39.

    Meneghini, O. et al. Self-consistent core-pedestal transport simulations with neural network accelerated models. Nucl. Fusion 57, 086034 (2017).

    ADS  Google Scholar 

  40. 40.

    Anirudh, R., Thiagarajan, J. J., Bremer, P.-T. & Spears, B. K. Improved surrogates in inertial confinement fusion with manifold and cycle consistencies. Proc. Natl Acad. Sci. USA 117, 9741–9746 (2020).

    CAS  PubMed  PubMed Central  Google Scholar 

  41. 41.

    Kluth, G. et al. Deep learning for NLTE spectral opacities. Phys. Plasmas 27, 052707 (2020). This paper uses machine learning to emulate opacity calculations, in order to speed up ICF simulations.

    ADS  CAS  Google Scholar 

  42. 42.

    Humbird, K. D., Peterson, J. L. & McClarren, R. G. Deep neural network initialization with decision trees. IEEE Trans. Neural Netw. Learn. Syst. 30, 1286–1295 (2019). This paper presents a data-driven method for selecting deep neural network architecture and hyperparameters

    PubMed  PubMed Central  Google Scholar 

  43. 43.

    Kasim, M. F. et al. Building high accuracy emulators for scientific simulations with deep neural architecture search. Preprint at https://arxiv.org/abs/2001.08055 (2020).

  44. 44.

    Kustowski, B. et al. Transfer learning as a tool for reducing simulation bias: application to inertial confinement fusion. IEEE Trans. Plasma Sci. 48, 46–53 (2020). Transfer learning updates a subset of a pre-trained deep neural network using experimental data; this paper explores its application to sparse ICF datasets.

    ADS  CAS  Google Scholar 

  45. 45.

    Bambi, C. Astrophysical black holes: a compact pedagogical review. Ann. Phys. 530, 1700430 (2018).

    MathSciNet  Google Scholar 

  46. 46.

    The National Space Weather Program Strategic Plan. Technical Report CM-P30–1995, https://www.icams-portal.gov/publications/spacewx/nswp2.html (ICAMS, 1995).

  47. 47.

    Eastwood, J. P. et al. The economic impact of space weather: where do we stand? Risk Anal. 37, 206–218 (2017).

    CAS  PubMed  PubMed Central  Google Scholar 

  48. 48.

    Camporeale, E. The challenge of machine learning in space weather: nowcasting and forecasting. Space Weather 17, 1166–1207 (2019).

    ADS  Google Scholar 

  49. 49.

    Camporeale, E., Carè, A. & Borovsky, J. E. Classification of solar wind with machine learning. J. Geophys. Res. Space Phys. 122, 10910–10920 (2017).

    ADS  Google Scholar 

  50. 50.

    Chen, Y. et al. Identifying solar flare precursors using time series of SDO/HMI images and SHARP parameters. Space Weather 17, 1404–1426 (2019).

    ADS  Google Scholar 

  51. 51.

    Campi, C. et al. Feature ranking of active region source properties in solar flare forecasting and the uncompromised stochasticity of flare occurrence. Astrophys. J. 883, 150 (2019).

    ADS  Google Scholar 

  52. 52.

    Inceoglu, F. et al. Using machine learning methods to forecast if solar flares will be associated with CMEs and SEPs. Astrophys. J. 861, 128 (2018).

    ADS  Google Scholar 

  53. 53.

    Bobra, M. G. & Ilonidis, S. Predicting coronal mass ejections using machine learning methods. Astrophys. J. 821, 127 (2016).

    ADS  Google Scholar 

  54. 54.

    Sarma, R. et al. Bayesian inference of quasi-linear radial diffusion parameters using Van Allen probes. J. Geophys. Res. Space Phys. 125, e2019JA027618 (2020).

    ADS  Google Scholar 

  55. 55.

    Camporeale, E. et al. A gray-box model for a probabilistic estimate of regional ground magnetic perturbations: enhancing the NOAA operational geospace model with machine learning. J. Geophys. Res. Space Phys. 125, e27684 (2020).

    ADS  Google Scholar 

  56. 56.

    Lamb, K. et al. Correlation of auroral dynamics and GNSS scintillation with an autoencoder. In Second Workshop on Machine Learning and the Physical Sciences (NeurIPS 2019) (2019); preprint at https://arxiv.org/abs/1910.03085.

  57. 57.

    Rowlinson, A. et al. Identifying transient and variable sources in radio images. Astron. Comput. 27, 111–129 (2019).

    ADS  Google Scholar 

  58. 58.

    Coughlin, M. W., Dietrich, T., Margalit, B. & Metzger, B. D. Multi-messenger Bayesian parameter inference of a binary neutron-star merger. Mon. Not. R. Astron. Soc. Lett. 489, L91–L96 (2019). This paper uses both gravitational-wave and multi-wavelength electromagnetic data to simultaneously constrain stellar masses, orbital parameters, and supra-nuclear density equations of state.

    ADS  Google Scholar 

  59. 59.

    Dorn, C. et al. A generalized Bayesian inference method for constraining the interiors of super Earths and sub-Neptunes. Astron. Astrophys. 597, A37 (2017).

    Google Scholar 

  60. 60.

    Bellinger, E. P. et al. Fundamental parameters of main-sequence stars in an instant with machine learning. Astrophys. J. 830, 31 (2016).

    ADS  Google Scholar 

  61. 61.

    Lochner, M., McEwen, J. D., Peiris, H. V., Lahav, O. & Winter, M. K. Photometric supernova classification with machine learning. Astrophys. J. Suppl. 225, 31 (2016).

    ADS  Google Scholar 

  62. 62.

    Kong, X. et al. Spectral feature extraction for DB white dwarfs through machine learning applied to new discoveries in the SDSS DR12 and DR14. Publ. Astron. Soc. Pacif. 130, 084203 (2018).

    ADS  Google Scholar 

  63. 63.

    Huppenkothen, D., Heil, L. M., Hogg, D. W. & Mueller, A. Using machine learning to explore the long-term evolution of GRS 1915+105. Mon. Not. R. Astron. Soc. 466, 2364–2377 (2017).

    ADS  Google Scholar 

  64. 64.

    Chardin, J. et al. A deep learning model to emulate simulations of cosmic reionization. Mon. Not. R. Astron. Soc. 490, 1055–1065 (2019).

    ADS  CAS  Google Scholar 

  65. 65.

    Saumon, D. & Guillot, T. Shock compression of deuterium and the interiors of Jupiter and Saturn. Astrophys. J. 609, 1170–1180 (2004).

    ADS  CAS  Google Scholar 

  66. 66.

    Smith, R. F. et al. Ramp compression of diamond to five terapascals. Nature 511, 330–333 (2014).

    ADS  CAS  PubMed  PubMed Central  Google Scholar 

  67. 67.

    Tzeferacos, P. et al. Laboratory evidence of dynamo amplification of magnetic fields in a turbulent plasma. Nat. Commun. 9, 591 (2018).

    ADS  CAS  PubMed  PubMed Central  Google Scholar 

  68. 68.

    Falcon, R. E. et al. Laboratory measurements of white dwarf photospheric spectral lines: Hβ. Astrophys. J. 806, 214 (2015).

    ADS  Google Scholar 

  69. 69.

    Bailey, J. E. et al. A higher-than-predicted measurement of iron opacity at solar interior temperatures. Nature 517, 56–59 (2015).

    ADS  CAS  PubMed  PubMed Central  Google Scholar 

  70. 70.

    Nagayama, T. et al. Systematic study of L-shell opacity at stellar interior temperatures. Phys. Rev. Lett. 122, 235001 (2019).

    ADS  CAS  PubMed  PubMed Central  Google Scholar 

  71. 71.

    de Souza, R. S., Boston, S. R., Coc, A. & Iliadis, C. Thermonuclear fusion rates for tritium + deuterium using Bayesian methods. Phys. Rev. C 99, 014619 (2019).

    ADS  Google Scholar 

  72. 72.

    Zhelavskaya, I. S., Shprits, Y. Y. & Spasojević, M. Empirical modeling of the plasmasphere dynamics using neural networks. J. Geophys. Res. Space Phys. 122, 11227–11244 (2017).

    ADS  Google Scholar 

  73. 73.

    Zhelavskaya, I. S., Shprits, Y. Y. & Spasojevic, M. in Machine Learning Techniques for Space Weather 301–327 (Elsevier, 2018).

  74. 74.

    Freidberg, J. Plasma Physics and Fusion Energy (Cambridge Univ. Press, 2008).

  75. 75.

    Atzeni, S., Meyer-ter Vehn, J. & Meyer-ter Vehn, J. The Physics of Inertial Fusion: BeamPlasma Interaction, Hydrodynamics, Hot Dense Matter International Series of Monographs on Physics (Clarendon Press, 2004).

  76. 76.

    Lindl, J. Inertial Confinement Fusion: The Quest for Ignition and Energy Gain Using Indirect Drive (AIP Press, 1998).

  77. 77.

    Campbell, E. M. & Hogan, W. J. The National Ignition Facility—applications for inertial fusion energy and high-energy-density science. Plasma Phys. Contr. Fusion 41, B39–B56 (1999).

    CAS  Google Scholar 

  78. 78.

    Moses, E. I. Ignition on the National Ignition Facility. J. Phys. Conf. Ser. 112, 012003 (2008).

    Google Scholar 

  79. 79.

    Boehly, T. et al. Initial performance results of the OMEGA laser system. Opt. Commun. 133, 495–506 (1997).

    ADS  CAS  Google Scholar 

  80. 80.

    Slutz, S. A. High-gain magnetized inertial fusion. Phys. Rev. Lett. 108, 025003 (2012).

    ADS  PubMed  PubMed Central  Google Scholar 

  81. 81.

    Gomez, M. R. et al. Experimental demonstration of fusion-relevant conditions in magnetized liner inertial fusion. Phys. Rev. Lett. 113, 155003 (2014).

    ADS  CAS  PubMed  PubMed Central  Google Scholar 

  82. 82.

    Dimonte, G. Quantitative metrics for evaluating thermonuclear design codes and physics models applied to the National Ignition Campaign. Phys. Plasmas 27, 052709 (2020).

    ADS  CAS  Google Scholar 

  83. 83.

    Yang, C. et al. Preparing Dense Net for Automated HYDRA Mesh Management via Reinforcement Learning. Technical Report LLNL-TR-799958, https://www.osti.gov/servlets/purl/1580017 (Lawrence Livermore National Laboratory, 2019). This report details the use of deep neural networks to automatically perform adaptive mesh refinement in radiation-hydrodynamics simulations.

  84. 84.

    Peterson, J. L. et al. Merlin: enabling machine learning-ready HPC ensembles. Preprint at https://arxiv.org/abs/1912.02892 (2019).

  85. 85.

    Peterson, J. L. et al. Zonal flow generation in inertial confinement fusion implosions. Phys. Plasmas 24, 032702 (2017). This paper presents the first novel ICF design reached using machine learning.

    ADS  Google Scholar 

  86. 86.

    Amorin, C., Kegelmeyer, L. M. & Kegelmeyer, W. P. A hybrid deep learning architecture for classification of microscopic damage on National Ignition Facility laser optics. Stat. Analysis Data Mining 12, 505–513 (2019). Here, deep neural network-based image classification is used to detect and classify damage in the NIF laser system, allowing more reliable operation at high energy.

    MathSciNet  MATH  Google Scholar 

  87. 87.

    Nora, R., Peterson, J. L., Spears, B. K., Field, J. E. & Brandon, S. Ensemble simulations of inertial confinement fusion implosions. Stat. Analysis Data Mining 10, 230–237 (2017).

    MathSciNet  MATH  Google Scholar 

  88. 88.

    Gaffney, J. A. et al. The JAG Inertial Confinement Fusion Simulation Dataset For Multi-Modal Scientific Deep Learning https://library.ucsd.edu/dc/object/bb5534097t (2020). This dataset is an example of open data practices in ICF, and is one of the first multi-modal scientific datasets to be released by the HEDP community.

  89. 89.

    Thiagarajan, J. J. et al. Designing accurate emulators for scientific processes using calibration-driven deep models. Nat. Commun. 11, 5622 (2020).

    ADS  CAS  PubMed  PubMed Central  Google Scholar 

  90. 90.

    Hatfield, P. et al. Using sparse Gaussian processes for predicting robust inertial confinement fusion implosion yields. IEEE Trans. Plasma Sci. 48, 14–21 (2020).

    ADS  Google Scholar 

  91. 91.

    Glinsky, M. E. et al. Quantification of MagLIF morphology using the Mallat scattering transformation. Phys. Plasmas 27, 112703 (2019). This paper uses a novel, physics-motivated deep neural network architecture to featurize images of ICF implosions driven on the Z pulsed-power machine.

    ADS  Google Scholar 

  92. 92.

    Palaniyappan, S. et al. Hydro-scaling of direct-drive cylindrical implosions at the OMEGA and the National Ignition Facility. Phys. Plasmas 27, 042708 (2020).

    ADS  CAS  Google Scholar 

  93. 93.

    Gaffney, J., Clark, D., Sonnad, V. & Libby, S. Development of a Bayesian method for the analysis of inertial confinement fusion experiments on the NIF. Nucl. Fusion 53, 073032 (2013).

    ADS  CAS  Google Scholar 

  94. 94.

    Gaffney, J., Clark, D., Sonnad, V. & Libby, S. Bayesian inference of inaccuracies in radiation transport physics from inertial confinement fusion experiments. High Energy Density Phys. 9, 457–461 (2013).

    ADS  CAS  Google Scholar 

  95. 95.

    Knapp, P. A Bayesian Parameter Estimation Framework for Understanding Fusion Experiments on Z. Technical Report SAND2018-1698PE663774, https://www.osti.gov/biblio/1525597 (2018).

  96. 96.

    Hsu, A., Cheng, B. & Bradley, P. A. Analysis of NIF scaling using physics informed machine learning. Phys. Plasmas 27, 012703 (2020).

    ADS  CAS  Google Scholar 

  97. 97.

    Humbird, K. D., Peterson, J. L., Spears, B. K. & McClarren, R. G. Transfer learning to model inertial confinement fusion experiments. IEEE Trans. Plasma Sci. 48, 61–70 (2020).

    ADS  Google Scholar 

  98. 98.

    Götzfried, J. et al. Research towards high-repetition rate laser-driven X-ray sources for imaging applications. Nucl. Instrum. Meth. Phys. Res. A 909, 286–289 (2018).

    ADS  Google Scholar 

  99. 99.

    He, Z.-H. et al. Coherent control of plasma dynamics. Nat. Commun. 6, 7156 (2015).

    ADS  CAS  PubMed  PubMed Central  Google Scholar 

  100. 100.

    Dann, S. J. et al. Laser wakefield acceleration with active feedback at 5 Hz. Phys. Rev. Accel. Beams 22, 041303 (2019).

    ADS  CAS  Google Scholar 

  101. 101.

    Kirschner, J., Mutny, M. M., Hiller, N., Ischebeck, R. & Krause, A. Adaptive and safe Bayesian optimization in high dimensions via one-dimensional subspaces. In Proc. Machine Learning Res. 97, 3429–3438 (2019). This paper describes a Bayesian optimization method for a free electron laser that prevents the laser from violating any safety constraints.

    Google Scholar 

  102. 102.

    Shalloo, R. J. et al. Automation and control of laser wakefield accelerators using Bayesian optimization. Nat. Commun. 11, 6355 (2020).

    ADS  CAS  PubMed  PubMed Central  Google Scholar 

  103. 103.

    Maier, A. R. et al. Decoding sources of energy variability in a laser-plasma accelerator. Phys. Rev. X 10, 031039 (2020).

    CAS  Google Scholar 

  104. 104.

    Team, J. T. et al. Hybrid neural network for density limit disruption prediction and avoidance on J-TEXT tokamak. Nucl. Fusion 58, 056016 (2018).

    ADS  Google Scholar 

  105. 105.

    Fu, Y. et al. Machine learning control for disruption and tearing mode avoidance. Phys. Plasmas 27, 022501 (2020).

    ADS  CAS  Google Scholar 

  106. 106.

    Kates-Harbeck, J., Svyatkovskiy, A. & Tang, W. Predicting disruptive instabilities in controlled fusion plasmas through deep learning. Nature 568, 526–531 (2019).

    ADS  CAS  PubMed  PubMed Central  Google Scholar 

  107. 107.

    Wilkinson, M. D. et al. Comment: The FAIR guiding principles for scientific data management and stewardship. Sci. Data 3, 160018 (2016).

    PubMed  PubMed Central  Google Scholar 

  108. 108.

    Albertsson, K. et al. Machine learning in high energy physics community white paper. J. Phys. Conf. Ser. 1085, 022008 (2018).

    Google Scholar 

  109. 109.

    Borne, K. D. et al. The revolution in astronomy education: data science for the masses. Preprint at https://arxiv.org/abs/0909.3895 (2009).

  110. 110.

    Pasian, F. et al. Science ground segment for the ESA Euclid Mission. In Software and Cyberinfrastructure for Astronomy II (eds Radziwill, N. M. & Chiozzi, G.) Vol. 8451, 845104 (SPIE, 2012).

  111. 111.

    Lyons, L. Discovering the significance of 5 sigma. Preprint at https://arxiv.org/abs/1310.1284 (2013). This paper discusses the background, rationale, and advantages and disadvantages of the 5σ criterion commonly used in particle physics.

  112. 112.

    Roodman, A. Blind analysis in particle physics. In Proc. Conf. on Statistical Problems in Particle Physics, Astrophysics and Cosmology (SLAC, 2003).

  113. 113.

    Roso, L. High repetition rate petawatt lasers. EPJ Web Conf. 167, 01001 (2018).

    Google Scholar 

  114. 114.

    Zheng, W. et al. Laser performance of the SG-III laser facility. In High Power Laser Science and Engineering Vol. 4, e21 (Cambridge Univ. Press, 2016).

  115. 115.

    Danson, C. N. et al. Petawatt and exawatt class lasers worldwide. In High Power Laser Science and Engineering Vol. 7, e54 (Cambridge Univ. Press, 2019). This paper reviews some of the many high-powered lasers in use around the world.

  116. 116.

    Opportunities in Intense Ultrafast Lasers https://doi.org/10.17226/24939 (National Academies Press, 2018).

  117. 117.

    Lin, Z. et al. SG-II laser elementary research and precision SG-II program. Fusion Eng. Des. 44, 61–66 (1999).

    CAS  Google Scholar 

  118. 118.

    LULI2000 User Guide. https://gargantua.polytechnique.fr/siatel-web/app/linkto/mICYYYTJIe5S (Laboratoire pour l’Utilisation des Lasers Intenses, 2019).

  119. 119.

    Kirillov, G. A., Murugov, V. M., Punin, V. T. & Shemyakin, V. I. High power laser system ISKRA V. Laser Part. Beams 8, 827–831 (1990).

    ADS  CAS  Google Scholar 

  120. 120.

    Zhao, Z. & Wang, D. XFEL Projects in China. In Proc. LINAC2018 (Beijing) http://accelconf.web.cern.ch/linac2018/html/author.htm (2019).

  121. 121.

    Zhang, Z. et al. The laser beamline in SULF facility. In High Power Laser Science and Engineering Vol. 8, e4 (Cambridge Univ. Press, 2020).

  122. 122.

    Schramm, U. et al. First results with the novel petawatt laser acceleration facility in Dresden. In J. Phys. Conf. Ser. 874, 12028 (2017).

    Google Scholar 

  123. 123.

    European XFEL. Facts and Figures https://www.xfel.eu/facility/overview/facts_amp_figures/index_eng.html.

  124. 124.

    Linac Coherent Light Source. LCLS-II Design & Performance https://lcls.slac.stanford.edu/lcls-ii/design-and-performance.

  125. 125.

    Yabashi, M., Tanaka, H., Tono, K. & Ishikawa, T. Status of the SACLA facility. Appl. Sci. 7, 604 (2017).

    Google Scholar 

  126. 126.

    CERN. FAQ – LHC the Guide. Technical Report CERN-Brochure-2017–002-Eng, https://cds.cern.ch/record/2255762 (CERN, 2017).

Download references

Acknowledgements

This Perspective is the result of a meeting at the Lorentz Center, University of Leiden, 13−17 January 2020. The Lorentz Centre is funded by the Dutch Research Council (NWO) and the University of Leiden. The meeting also had support from the John Fell Oxford University Press (OUP) Research Fund. The organizers are grateful to T. Uitbeijerse (Lorentz Center) for facilitating the meeting. P.W.H. acknowledges funding from the Engineering and Physical Sciences Research Council. A portion of this work was performed under the auspices of the US Department of Energy by Lawrence Livermore National Laboratory under contract DE-AC52-07NA27344. J.A.G. and G.J.A. were supported by LLNL Laboratory Directed Research and Development project 18-SI-002. The paper has LLNL tracking number LLNL-JRNL-811857. This document was prepared as an account of work sponsored by an agency of the United States government. Neither the United States government nor Lawrence Livermore National Security, LLC, nor any of their employees makes any warranty, expressed or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process disclosed, or represents that its use would not infringe privately owned rights. Reference herein to any specific commercial product, process, or service by trade name, trademark, manufacturer, or otherwise does not necessarily constitute or imply its endorsement, recommendation, or favoring by the United States government or Lawrence Livermore National Security, LLC. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States government or Lawrence Livermore National Security, LLC, and shall not be used for advertising or product endorsement purposes. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the US Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525. This paper describes objective technical results and analysis. Any subjective views or opinions that might be expressed in the paper do not necessarily represent the views of the US Department of Energy or the United States Government.

Author information

Affiliations

Authors

Contributions

P.W.H., J.A.G. and G.J.A. conceived the work and led the writing of the manuscript. All authors contributed to the manuscript and the ideas discussed at the Lorentz Center Meeting.

Corresponding authors

Correspondence to Peter W. Hatfield or Jim A. Gaffney or Gemma J. Anderson.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Peer review information Nature thanks Paul Bradley, Michael Bussmann and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Hatfield, P.W., Gaffney, J.A., Anderson, G.J. et al. The data-driven future of high-energy-density physics. Nature 593, 351–361 (2021). https://doi.org/10.1038/s41586-021-03382-w

Download citation

Comments

By submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

Search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing