- Physical Review Journals
All JournalsPhysics Magazine

Physical Review C

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Letter
  • Open Access

Physically interpretable machine learning for nuclear masses

M. R. Mumpower*, T. M. Sprouse, and A. E. Lovell

A. T. Mohan

  • Theoretical Division, Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA

  • Computer, Computational and Statistical Sciences Division, Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA

PDF

Phys. Rev. C 106, L021301 – Published 1 August, 2022

DOI: https://doi.org/10.1103/PhysRevC.106.L021301

Abstract

We present an approach to modeling the ground-state mass of atomic nuclei based directly on a probabilistic neural network constrained by relevant physics. Our physically interpretable machine learning (PIML) approach incorporates knowledge of physics by using a physically motivated feature space in addition to a soft physics constraint that is implemented as a penalty to the loss function. We train our PIML model on a random set of approximately 20% of the atomic mass evaluation (AME) and predict the remaining 80%. The success of our methodology is exhibited by a σrms≈186 keV match to data for the training set and σrms≈316 keV for the entire AME with Z≥20. We show that our general methodology can be interpreted using feature importance.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (54)

  1. M. Thoennessen, Plans for the facility for rare isotope beams, Nucl. Phys. A 834, 688c (2010).
  2. P. Talou, I. Stetcu, and T. Kawano, Modeling the emission of prompt fission gamma-rays for fundamental physics and applications, Phys. Procedia 59, 83 (2014).
  3. F. Kondev, M. Wang, W. Huang, S. Naimi, and G. Audi, The NUBASE2020 evaluation of nuclear physics properties, Chin. Phys. C 45, 030001 (2021).
  4. T. Kawano, R. Capote, S. Hilaire, and P. Chau Huu-Tai, Statistical hauser-feshbach theory with width-fluctuation correction including direct reaction channels for neutron-induced reactions at low energies, Phys. Rev. C 94, 014612 (2016).
  5. J. Randrup and R. Vogt, Generation of Fragment Angular Momentum in Fission, Phys. Rev. Lett. 127, 062502 (2021).
  6. A. W. Steiner, Deep crustal heating in a multicomponent accreted neutron star crust, Phys. Rev. C 85, 055804 (2012).
  7. G. W. Misch, B. A. Brown, and G. M. Fuller, Neutrino-pair emission from hot nuclei during stellar collapse, Phys. Rev. C 88, 015807 (2013).
  8. M. Mumpower, R. Surman, G. McLaughlin, and A. Aprahamian, The impact of individual nuclear properties on r-process nucleosynthesis, Prog. Part. Nucl. Phys. 86, 86 (2016).
  9. T. M. Sprouse, R. Navarro Perez, R. Surman, M. R. Mumpower, G. C. McLaughlin, and N. Schunck, Propagation of statistical uncertainties of skyrme mass models to simulations of r-process nucleosynthesis, Phys. Rev. C 101, 055803 (2020).
  10. Y. L. Zhu, K. A. Lund, J. Barnes, T. M. Sprouse, N. Vassh, G. C. McLaughlin, M. R. Mumpower, and R. Surman, Modeling Kilonova Light Curves: Dependence on Nuclear Inputs, Astrophys. J. 906, 94 (2021).
  11. P. Möller, A. J. Sierk, T. Ichikawa, and H. Sagawa, Nuclear ground-state masses and deformations: FRDM(2012), At. Data Nucl. Data Tables 109-110, 1 (2016).
  12. S. Goriely, S. Hilaire, M. Girod, and S. Péru, First Gogny-Hartree-Fock-Bogoliubov Nuclear Mass Model, Phys. Rev. Lett. 102, 242501 (2009).
  13. R. Utama, J. Piekarewicz, and H. B. Prosper, Nuclear mass predictions for the crustal composition of neutron stars: A bayesian neural network approach, Phys. Rev. C 93, 014311 (2016).
  14. L. Neufcourt, Y. Cao, W. Nazarewicz, and F. Viens, Bayesian approach to model-based extrapolation of nuclear observables, Phys. Rev. C 98, 034318 (2018).
  15. J. Wu, X.-Y. Chen, H. Zhang, L.-D. Xiong, H. Lei, and S.-H. Deng, Hyperparameter optimization for machine learning models based on bayesian optimizationb, J. Electron. Sci. Technol. 17, 100007 (2019).
  16. A. Boehnlein, M. Diefenthaler, C. Fanelli, M. Hjorth-Jensen, T. Horn, M. P. Kuchera, D. Lee, W. Nazarewicz, K. Orginos, P. Ostroumov, L.-G. Pang, A. Poon, N. Sato, M. Schram, A. Scheinker, M. S. Smith, X.-N. Wang, and V. Ziegler, Machine Learning in Nuclear Physics, arXiv:2112.02309 (2021).
  17. G. A. Negoita, J. P. Vary, G. R. Luecke, P. Maris, A. M. Shirokov, I. J. Shin, Y. Kim, E. G. Ng, C. Yang, M. Lockner, and G. M. Prabhu, Deep learning: Extrapolation tool for ab initio nuclear theory, Phys. Rev. C 99, 054308 (2019).
  18. W. G. Jiang, G. Hagen, and T. Papenbrock, Extrapolation of nuclear structure observables with artificial neural networks, Phys. Rev. C 100, 054326 (2019).
  19. K. Raghavan, P. Balaprakash, A. Lovato, N. Rocco, and S. M. Wild, Machine-learning-based inversion of nuclear responses, Phys. Rev. C 103, 035502 (2021).
  20. N. Ismail and A. Gezerlis, Machine-learning approach to finite-size effects in systems with strongly interacting fermions, Phys. Rev. C 104, 055802 (2021).
  21. V. Sobes, M. Grosskopf, K. A. Wendt, D. Brown, M. Smith, and P. Talou, WANDA: AI/ML for Nuclear Data, Oak Ridge National Lab. (ORNL), Oak Ridge,Tech. Rep. No. ORNL/TM-2020/1535 (2020).
  22. K. Kolos, V. Sobes, R. Vogt, C. E. Romano, M. S. Smith, L. A. Bernstein, D. A. Brown, M. T. Burkey, Y. Danon, M. A. Elsawi, B. L. Goldblum, L. H. Heilbronn, S. L. Hogle, J. Hutchinson, B. Loer, E. A. McCutchan, M. R. Mumpower, E. M. O'Brien, C. Percher, P. N. Peplowski et al., Current nuclear data needs for applications, Phys. Rev. Research 4, 021001 (2022).
  23. L. Neufcourt, Y. Cao, W. Nazarewicz, E. Olsen, F. Viens, Neutron Drip Line in the Ca Region from Bayesian Model Averaging, Phys. Rev. Lett. 122, 062502 (2019).
  24. L. Neufcourt, Y. Cao, S. A. Giuliani, W. Nazarewicz, E. Olsen, and O. B. Tarasov, Quantified limits of the nuclear landscape, Phys. Rev. C 101, 044307 (2020).
  25. M. Shelley and A. Pastore, A new mass model for nuclear astrophysics: Crossing 200 kev accuracy, Universe 7, 131 (2021).
  26. A. Sharma, A. Gandhi, and A. Kumar, Learning correlations in nuclear masses using neural networks, Phys. Rev. C 105, L031306 (2022).
  27. A. Pastore and M. Carnini, Extrapolating from neural network models: a cautionary tale, J. Phys. G: Nucl. Part. Phys. 48, 084001 (2021).
  28. Z. Niu and H. Liang, Nuclear mass predictions based on bayesian neural network approach with pairing and shell effects, Phys. Lett. B 778, 48 (2018).
  29. U. Murarka, K. Banerjee, T. Malik, and C. Providência, The neutron star outer crust equation of state: a machine learning approach, J. Cosmol. Astropart. Phys. 2022045 (2022).
  30. H. Özdoğan, Y. A. Üncü, M. Şekerci, and A. Kaplan, Mass excess estimations using artificial neural networks, Appl. Radiat. Isot. 184, 110162 (2022).
  31. L. A. Bernstein, D. A. Brown, A. J. Koning, B. T. Rearden, C. E. Romano, A. A. Sonzogni, A. S. Voyles, and W. Younes, Our future nuclear data needs, Annu. Rev. Nucl. Part. Sci. 69, 109 (2019).
  32. A. E. Lovell, A. T. Mohan, T. M. Sprouse, and M. R. Mumpower, Nuclear masses learned from a probabilistic neural network, Phys. Rev. C 106, 014305 (2022).
  33. C. M. Bishop, Mixture Density Networks, Technical Report, Aston University 1994).
  34. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Kopf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai et al., Pytorch: An imperative style, high-performance deep learning library, in Advances in Neural Information Processing Systems 32, edited by H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alche Buc, E. Fox, and R. Garnett (Curran, Red Hook, NY, USA, 2019), pp. 8024–8035.
  35. A. E. Lovell, A. T. Mohan, and P. Talou, Quantifying uncertainties on fission fragment mass yields with mixture density networks, J. Phys. G: Nucl. Part. Phys. 47, 114001 (2020).
  36. R. Casten and N. Zamfir, The evolution of nuclear structure: The npnn scheme and related correlations, J. Phys. G: Nucl. Part. Phys. 22, 1521 (1996).
  37. R. F. Casten, D. S. Brenner, and P. E. Haustein, Valence p - n Interactions and the Development of Collectivity in Heavy Nuclei, Phys. Rev. Lett. 58, 658 (1987).
  38. M. Wang, G. Audi, F. G. Kondev, W. Huang, S. Naimi, and X. Xu, The AME2016 atomic mass evaluation (II). tables, graphs and references, Chin. Phys. C 41, 030003 (2017).
  39. G. T. Garvey, W. J. Gerace, R. L. Jaffe, I. Talmi, and I. Kelson, Set of nuclear-mass relations and a resultant mass table, Rev. Mod. Phys. 41, S1 (1969).
  40. J. Barea, A. Frank, J. G. Hirsch, P. V. Isacker, S. Pittel, and V. Velázquez, Garvey-kelson relations and the new nuclear mass tables, Phys. Rev. C 77, 041304(R) (2008).
  41. D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, arXiv:1412.6980.
  42. K. Deb, Multi-objective optimization, in Search Methodologies: Introductory Tutorials in Optimization and Decision Support Techniques, edited by E. K. Burke and G. Kendall (Springer, Boston, 2005), pp. 273–316.
  43. N. Gunantara, A review of multi-objective optimization: Methods and its applications, Cogent Eng. 5, 1502242 (2018).
  44. M. Wang, W. Huang, F. Kondev, G. Audi, and S. Naimi, The AME 2020 atomic mass evaluation (II). tables, graphs and references, Chin. Phys. C 45, 030003 (2021).
  45. R. Orford, N. Vassh, J. A. Clark, G. C. McLaughlin, M. R. Mumpower, G. Savard, R. Surman, A. Aprahamian, F. Buchinger, M. T. Burkey, D. A. Gorelov, T. Y. Hirsh, J. W. Klimes, G. E. Morgan, A. Nystrom, and K. S. Sharma, Precision Mass Measurements of Neutron-Rich Neodymium and Samarium Isotopes and Their Role in Understanding Rare-Earth Peak Formation, Phys. Rev. Lett. 120, 262702 (2018).
  46. J. Jänecke and P. Masson, Mass predictions from the garvey-kelson mass relations, At. Data Nucl. Data Tables 39, 265 (1988).
  47. D. Lunney, J. M. Pearson, and C. Thibault, Recent trends in the determination of nuclear masses, Rev. Mod. Phys. 75, 1021 (2003).
  48. I. O. Morales, J. C. López Vieyra, J. G. Hirsch, and A. Frank, How good are the Garvey-Kelson predictions of nuclear masses?, Nucl. Phys. A 828, 113 (2009).
  49. J. A. Melendez, R. J. Furnstahl, D. R. Phillips, M. T. Pratola, and S. Wesolowski, Quantifying correlated truncation errors in effective field theory, Phys. Rev. C 100, 044001 (2019).
  50. N. Schunck, J. ONeal, M. Grosskopf, E. Lawrence, and S. M. Wild, Calibration of energy density functionals with deformed nuclei, J. Phys. G: Nucl. Part. Phys. 47, 074001 (2020).
  51. S. Lundberg and S.-I. Lee, A unified approach to interpreting model predictions, arxiv:1705.07874.
  52. C. F. V. Weizsäcker, Zur Theorie der Kernmassen, Z. Phys. 96, 431 (1935).
  53. J. W. Negele, The mean-field theory of nuclear structure and dynamics, Rev. Mod. Phys. 54, 913 (1982).
  54. L. S. Shapley, 17. a value for n-person games, in Contributions to the Theory of Games (AM-28), edited by H. W. Kuhn and A. W. Tucker (Princeton University Press, Princeton, NJ, USA, 2016), Vol. II, pp. 307–318.

Outline

Information

Phys. Rev. C 106, L021301– Published 1 August, 2022
  • Received 4 March 2022
  • Revised 10 May 2022
  • Accepted 21 July 2022
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation