- Physical Review Journals
All JournalsPhysics Magazine
Access Provided by Xinjiang University

Physical Review E

Export citation

Export citation

Choose format for download:

Download Citation
  • Access by Xinjiang University

Opacity predictions in plasmas under stellar conditions using deep learning

Djamel Benredjem*

Jean-Christophe Pain

  • *Contact author: djamel.benredjem@universite-paris-saclay.fr
PDF

Phys. Rev. E 114, 015204 – Published 6 July, 2026

DOI: https://doi.org/10.1103/f237-bqz2

Abstract

The aim of this work is to predict the opacity of plasmas under stellar conditions. We focus on iron and nickel, as these elements have been extensively investigated both theoretically and experimentally. In certain regimes, notably under nonlocal thermodynamic equilibrium, calculating the spectral opacity can be computationally demanding. To mitigate this difficulty, we employ deep learning models to predict accurate opacities while achieving a substantial reduction in computational cost. Specifically, we develop and train a hybrid model that combines a convolutional neural network with a multilayer perceptron. The proposed approach provides both the spectral opacity over the 0–10 000 eV energy range, and the corresponding mean opacities for large sets of temperatures and mass densities, in close agreement with standard computational methods. The agreement is very satisfactory, except in the L- and M-shell energy ranges for nickel at high temperatures, where a very large number of emerging transitions leads to substantial discrepancies.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (38)

  1. J. E. Bailey, T. Nagayama, G. P. Loisel, G. A. Rochau, C. Blancard, J. Colgan, Ph. Cossé, G. Faussurier, C. J. Fontes, F. Gilleron, I. E. Golovkin, S. B. Hansen, C. A. Iglesias, D. P. Kilcrease, J. J. MacFarlane, R. C. Mancini, S. N. Nahar, C. Orban, J.-C Pain, A. K. Pradhan, M. Sherril, and B. G. Wilson, A higher-than-predicted measurement of iron opacity at solar interior temperatures, Nature (London) 517, 56 (2015).
  2. T. Nagayama, J. E. Bailey, G. P. Loisel, G. A. Rochau, J. J. MacFarlane, and I. E. Golovkin, Numerical investigations of potential systematic uncertainties in iron opacity measurements at solar interior temperatures, Phys. Rev. E 95, 063206 (2017).
  3. G. P. Loisel, J. E. Bailey, T. Nagayama, S. B. Hansen, G. S. Dunham, P. D. Gard, A. P. Colombo, A. D. Edens, R. Speas, Q. Looker, M. Kimmel, J. L. Porter, E. C. Harding, G. A. Rochau, C. J. Fontes, J. P. Colgan, C. Blancard, Ph. Cossé, G. Faussurier, F. Gilleron, J.-Ch. Pain, and D. Aberg, First measurement of Z opacity sample evolution near solar interior conditions using time-resolved spectroscopy, Phys. Rev. Lett. 134, 095101 (2025).
  4. M. Dozières, F. Thais, S. Bastiani-Ceccotti, T. Blenski, M. Comet, F. Condamine, J. Fariaut, F. Gilleron, D. Gilles, J.-C. Pain, M. Poirier, C. Reverdin, F. Rosmej, V. Silvert, G. Soullié, and B. Villette, Simultaneous X-ray and XUV absorption measurements in nickel laser-produced plasma close to LTE, High Energy Density Phys. 31, 83 (2019).
  5. D. Gilles, S. Turck-Chièze, G. Loisel, L. Piau, J.-E. Ducret, M. Poirier, T. Blenski, F. Thais, C. Blancard, P. Cossé, G. Faussurier, F. Gilleron, J-C. Pain, Q. Porcherot, J. A. Guzik, D. P. Kilcrease, N. H. Magee, J. Harris, M. Busquet, F. Delahaye, and S. Bastiani-Ceccotti, Comparison of Fe and Ni opacity calculations for a better understanding of pulsating stellar envelopes, High Energy Density Phys. 7, 312 (2011).
  6. S. Turck-Chièze, F. Delahaye, D. Gilles, G. Loisel, and L. Piau, On plasma radiative properties in stellar conditions, High Energy Density Phys. 5, 132 (2009).
  7. A. Hui-Bon-Hoa, J.-C. Pain, and O. Richard, New nickel opacities and their impact on stellar models, Astron. Astrophys. 658, A70 (2022).
  8. S. Atzeni and J. Meyer-ter Vehn, The Physics of Inertial Fusion: Beam Plasma Interaction, Hydrodynamics, Hot Dense Matter, International Series of Monographs on Physics, Vol. 125 (Oxford University Press, Oxford, 2004).
  9. H. Abu-Shawareb et al. (The Indirect Drive ICF Collaboration), Achievement of target gain larger than unity in an inertial fusion experiment, Phys. Rev. Lett. 132, 065102 (2024).
  10. M. Busquet, Radiation-dependent ionization model for laser-created plasmas, Phys. Fluids B: Plasma Phys. 5, 4191 (1993).
  11. J. Bauche, C. Bauche-Arnoult, and O. Peyrusse, Effective temperatures in hot dense plasmas, J. Quant. Spectrosc. Radiat. Transfer 99, 55 (2006).
  12. C. J. Fontes, H. L. Zhang, J. Abdallah Jr., R. E. H. Clark, D. P. Kilcrease, J. Colgan, R. T. Cunningham, P. Hakel, N. H. Magee, and M. E. Sherrill, The Los Alamos suite of relativistic atomic physics codes, J. Phys. B: At. Mol. Opt. Phys. 48, 144014 (2015).
  13. P. Hakel, M. E. Sherrill, S. Mazevet, J. Abdallah Jr., J. Colgan, D. P. Kilcrease, N. H. Magee, C. J. Fontes, and H. L. Zhang, The new Los Alamos opacity code ATOMIC, J. Quant. Spectrosc. Radiat. Transfer 99, 265 (2006).
  14. Q. Porcherot, J.-C. Pain, F. Gilleron, and T. Blenski, A consistent approach for mixed detailed and statistical calculation of opacities in hot plasmas, High Energy Density Phys. 7, 234 (2011).
  15. A. Bar-Shalom, M. Klapisch, and J. Oreg, HULLAC, an integrated computer package for atomic processes in plasmas, J. Quant. Spectrosc. Radiat. Transfer 71, 169 (2001).
  16. M. Przybyła-Kasperek and K. F. Marfo, A multi-layer perceptron neural network for varied conditional attributes in tabular dispersed data, PLoS ONE 19, e0311041 (2024).
  17. A. Abdurrakhman, L. Sutiarso, M. Ainuri, M. Ushada, and M. P. Islam, A multilayer perceptron feedforward neural network and particle swarm optimization algorithm for optimizing biogas production, Energies 18, 1002 (2025).
  18. M. Krichen, Convolutional neural networks: A survey, Computers 12, 151 (2023).
  19. S. Back, J. Yoon, N. Tian, W. Zhong, K. Tran, and Z. W. Ulissi, Convolutional neural network of atomic surface structures to predict binding energies for high-throughput screening of catalysts, J. Phys. Chem. Lett. 10, 4401 (2019).
  20. R. M. Churchill, B. Tobias, Y. Zhu, and DIII-D team, Deep convolutional neural networks for multi-scale time-series classification and application to tokamak disruption prediction using raw, high temporal resolution diagnostic data, Phys. Plasmas 27, 062510 (2020).
  21. G. Kluth, K. D. Humbird, B. K. Spears, J. L. Peterson, H. A. Scott, M. V. Patel, J. Koning, M. Marinak, L. Divol, and C. V. Young, Deep learning for NLTE spectral opacities, Phys. Plasmas 27, 052707 (2020).
  22. M. Koubiti and M. Kerebel, Application of deep learning to spectroscopic features of the Balmer-alpha line for hydrogen isotopic ratio determination in tokamaks, Appl. Sci. 12, 9891 (2022).
  23. M. Koubiti, Application of machine learning to spectroscopic line emission by hydrogen isotopes in fusion devices for isotopic ratio determination and prediction, Eur. Phys. J. D 77, 137 (2023).
  24. C. M. Samuell, A. G. Mclean, C. A. Johnson, F. Glass, and A. E. Jaervinen, Measuring the electron temperature and identifying plasma detachment using machine learning and spectroscopy, Rev. Sci. Instrum. 92, 043520 (2021).
  25. N. Saura, M. Koubiti, and S. Benkadda, Study of line spectra emitted by hydrogen isotopes in tokamaks through deep-learning algorithms, Nucl. Mater. Energy 43, 101935 (2025).
  26. J.-C. Pain, G. Dejonghe, and T. Blenski, A self-consistent model for the study of electronic properties of hot dense plasmas in the superconfiguration approximation, J. Quant. Spectrosc. Radiat. Transfer 99, 451 (2006).
  27. J.-C. Pain, Super transition arrays: A tool for studying spectral properties of hot plasmas, Plasma 4, 42 (2021).
  28. M. Krief, Number of populated electronic configurations in a hot dense plasma, Phys. Rev. E 103, 033206 (2021).
  29. C. Bauche-Arnoult, J. Bauche, and M. Klapisch, Variance of the distributions of energy levels and of the transition arrays in atomic spectra, Phys. Rev. A 20, 2424 (1979).
  30. A. Bar-Shalom, J. Oreg, W. H. Goldstein, D. Shvarts, and A. Zigler, Super-transition-arrays: A model for the spectral analysis of hot, dense plasma, Phys. Rev. A 40, 3183 (1989).
  31. Y. Kurzweil and G. Hazak, Summation of the spectra of all partially resolved transition arrays in a supertransition array, Phys. Rev. E 94, 053210 (2016).
  32. H. Iyetomi and S. Ichimaru, Free energies of electron-screened ion plasmas in the hypernetted-chain approximation, Phys. Rev. A 34, 433 (1986).
  33. A. Bar-Shalom, J. Oreg, and W. H. Goldstein, Configuration interaction in LTE spectra of heavy elements, J. Quant. Spectrosc. Radiat. Transfer 51, 27 (1994).
  34. A. Bar-Shalom, J. Oreg, and M. Klapisch, The effect of configuration interaction on relativistic transition arrays, J. Quant. Spectrosc. Radiat. Transfer 65, 415 (2000).
  35. M.-A. Schaeuble, W. E. Lewis, S. Hansen, and T. Nagayama, Using deep learning to develop a fast, high-resolution, optically thin NLTE spectral model, Phys. Plasmas 32, 083302 (2025).
  36. E. Aymerich, G. Sias, F. Pisano, B. Cannas, S. Carcangiu, C. Sozzi, C. Stuart, P. J. Carvalho, A. Fanni, and J. E. T. Contributors, Disruption prediction at JET through deep convolutional neural networks using spatiotemporal information from plasma profiles, Nucl. Fusion 62, 066005 (2022).
  37. B. Li, W. Chen, S. Bian, A. Lusi, X. Tang, Y. Liu, J. Guo, D. Zhang, C. Yang, and F. Huang, Recognition of ethylene plasma spectra 1D data based on deep convolutional neural networks, Electronics 13, 983 (2024).
  38. S. Kiranyaz, O. Avci, O. Abdeljaber, T. Ince, M. Gabbouj, and D. J. Inman, 1D convolutional neural networks and applications: A survey, Mech. Syst. Sig. Process. 151, 107398 (2021).

Outline

Information

Phys. Rev. E 114, 015204– Published 6 July, 2026
  • Received 26 February 2026
  • Accepted 16 June 2026
Crossmark - Check for updates button

©2026 American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation