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.

  • Review Article
  • Published:

Ab initio quantum chemistry with neural-network wavefunctions

Nature Reviews Chemistry volume 7, pages 692–709 (2023)Cite this article

Subjects

Abstract

Deep learning methods outperform human capabilities in pattern recognition and data processing problems and now have an increasingly important role in scientific discovery. A key application of machine learning in molecular science is to learn potential energy surfaces or force fields from ab initio solutions of the electronic Schrödinger equation using data sets obtained with density functional theory, coupled cluster or other quantum chemistry (QC) methods. In this Review, we discuss a complementary approach using machine learning to aid the direct solution of QC problems from first principles. Specifically, we focus on quantum Monte Carlo methods that use neural-network ansatzes to solve the electronic Schrödinger equation, in first and second quantization, computing ground and excited states and generalizing over multiple nuclear configurations. Although still at their infancy, these methods can already generate virtually exact solutions of the electronic Schrödinger equation for small systems and rival advanced conventional QC methods for systems with up to a few dozen electrons.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Quantum chemistry and machine learning.
Fig. 2: Electronic-structure problem and its neural-network solutions.
Fig. 3: Variational Monte Carlo with neural networks.
Fig. 4: Neural-network architectures for selected real-space wavefunctions.
Fig. 5: Automerization of cyclobutadiene with neural-network ansatzes.
Fig. 6: Electronic energies for molecules and solids in second quantization.

Similar content being viewed by others

References

  1. Carleo, G. et al. Machine learning and the physical sciences. Rev. Mod. Phys. 91, 045002 (2019).

    Article  CAS  Google Scholar 

  2. Jumper, J. et al. Highly accurate protein structure prediction with AlphaFold. Nature 596, 583–589 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  3. Deringer, V. L. et al. Origins of structural and electronic transitions in disordered silicon. Nature 589, 59–64 (2021).

    Article  CAS  PubMed  Google Scholar 

  4. Noé, F., Olsson, S., Köhler, J. & Wu, H. Boltzmann generators: sampling equilibrium states of many-body systems with deep learning. Science 365, eaaw1147 (2019).

    Article  PubMed  Google Scholar 

  5. Huang, B. & von Lilienfeld, O. A. Quantum machine learning using atom-in-molecule-based fragments selected on the fly. Nat. Chem. 12, 945–951 (2020).

    Article  CAS  PubMed  Google Scholar 

  6. Tkatchenko, A. Machine learning for chemical discovery. Nat. Commun. 11, 4125 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  7. von Lilienfeld, O. A. & Burke, K. Retrospective on a decade of machine learning for chemical discovery. Nat. Commun. 11, 4895 (2020).

    Article  Google Scholar 

  8. Noé, F., Tkatchenko, A., Müller, K.-R. & Clementi, C. Machine learning for molecular simulation. Annu. Rev. Phys. Chem. 71, 361–390 (2020).

    Article  PubMed  Google Scholar 

  9. Dral, P. O. Quantum chemistry in the age of machine learning. J. Phys. Chem. Lett. 11, 2336–2347 (2020).

    Article  CAS  PubMed  Google Scholar 

  10. Unke, O. T. et al. Machine learning force fields. Chem. Rev. 121, 10142–10186 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  11. von Lilienfeld, O. A., Müller, K.-R. & Tkatchenko, A. Exploring chemical compound space with quantum-based machine learning. Nat. Rev. Chem. 4, 347–358 (2020).

    Article  Google Scholar 

  12. Bian, Y. & Xie, X.-Q. Generative chemistry: drug discovery with deep learning generative models. J. Mol. Model. 27, 71 (2021).

    Article  CAS  PubMed  Google Scholar 

  13. Jones, R. O. Density functional theory: its origins, rise to prominence, and future. Rev. Mod. Phys. 87, 897–923 (2015).

    Article  Google Scholar 

  14. Bartlett, R. J. & Musiał, M. Coupled-cluster theory in quantum chemistry. Rev. Mod. Phys. 79, 291–352 (2007).

    Article  CAS  Google Scholar 

  15. Deringer, V. L. et al. Gaussian process regression for materials and molecules. Chem. Rev. 121, 10073–10141 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  16. Behler, J. Four generations of high-dimensional neural network potentials. Chem. Rev. 121, 10037–10072 (2021).

    Article  CAS  PubMed  Google Scholar 

  17. Musil, F. et al. Physics-inspired structural representations for molecules and materials. Chem. Rev. 121, 9759–9815 (2021).

    Article  CAS  PubMed  Google Scholar 

  18. Li, H., Collins, C., Tanha, M., Gordon, G. J. & Yaron, D. J. A density functional tight binding layer for deep learning of chemical Hamiltonians. J. Chem. Theory Comput. 14, 5764–5776 (2018).

    Article  CAS  PubMed  Google Scholar 

  19. Schütt, K. T., Gastegger, M., Tkatchenko, A., Müller, K.-R. & Maurer, R. J. Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctions. Nat. Commun. 10, 5024 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  20. Kirkpatrick, J. et al. Pushing the frontiers of density functionals by solving the fractional electron problem. Science 374, 1385–1389 (2021).

    Article  CAS  PubMed  Google Scholar 

  21. Chandrasekaran, A. et al. Solving the electronic structure problem with machine learning. Comput. Mater. 5, 1–7 (2019).

    Google Scholar 

  22. Welborn, M., Cheng, L. & Miller III, T. F. Transferability in machine learning for electronic structure via the molecular orbital basis. J. Chem. Theory Comput. 14, 4772–4779 (2018).

    Article  CAS  PubMed  Google Scholar 

  23. Nagai, R., Akashi, R. & Sugino, O. Completing density functional theory by machine learning hidden messages from molecules. Comput. Mater. 6, 1–8 (2020).

    Google Scholar 

  24. Gómez-Bombarelli, R. et al. Automatic chemical design using a data-driven continuous representation of molecules. ACS Cent. Sci. 4, 268–276 (2018).

    Article  PubMed  PubMed Central  Google Scholar 

  25. Hoogeboom, E., Satorras, V. G., Vignac, C. & Welling, M. Equivariant diffusion for molecule generation in 3D. Preprint at http://arxiv.org/abs/2203.17003 (2022).

  26. Torlai, G. et al. Neural-network quantum state tomography. Nat. Phys. 14, 447–450 (2018).

    Article  CAS  Google Scholar 

  27. Sutton, R. S. & Barto, A. G. Reinforcement Learning: An Introduction (MIT Press, 2018).

  28. Tesauro, G. TD-Gammon, a self-teaching backgammon program, achieves master-level play. Neural Comput. 6, 215–219 (1994).

    Article  Google Scholar 

  29. Mnih, V. et al. Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015).

    Article  CAS  PubMed  Google Scholar 

  30. Silver, D. et al. Mastering the game of Go with deep neural networks and tree search. Nature 529, 484–489 (2016).

    Article  CAS  PubMed  Google Scholar 

  31. Degrave, J. et al. Magnetic control of tokamak plasmas through deep reinforcement learning. Nature 602, 414–419 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  32. Heinrich, J., Lanctot, M. & Silver, D. Fictitious self-play in extensive-form games. In Proceedings of the 32nd International Conference on Machine Learning 805–813 (PMLR, 2015).

  33. Silver, D. et al. A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science 362, 1140–1144 (2018).

    Article  CAS  PubMed  Google Scholar 

  34. Battaglia, S. Machine learning wavefunction. In Quantum Chemistry in the Age of Machine Learning 577–616 (Elsevier, 2023).

  35. Manzhos, S. Machine learning for the solution of the Schrödinger equation. Mach. Learn. Sci. Techn. 1, 013002 (2020).

    Article  Google Scholar 

  36. Piela, L. Ideas of Quantum Chemistry 2nd edn (Elsevier, 2014).

  37. Foulkes, W. M. C., Mitas, L., Needs, R. J. & Rajagopal, G. Quantum Monte Carlo simulations of solids. Rev. Mod. Phys. 73, 33–83 (2001).

    Article  CAS  Google Scholar 

  38. Bajdich, M., Mitas, L., Drobný, G., Wagner, L. K. & Schmidt, K. E. Pfaffian pairing wave functions in electronic-structure quantum Monte Carlo Simulations. Phys. Rev. Lett. 96, 130201 (2006).

    Article  CAS  PubMed  Google Scholar 

  39. Han, J., Zhang, L. & Weinan, E. Solving many-electron Schrödinger equation using deep neural networks. J. Comput. Phys. 399, 108929 (2019).

    Article  CAS  Google Scholar 

  40. Acevedo, A., Curry, M., Joshi, S. H., Leroux, B. & Malaya, N. Vandermonde wave function ansatz for improved variational Monte Carlo. In 2020 IEEE/ACM Fourth Workshop on Deep Learning on Supercomputers (DLS) 40–47 (IEEE, 2020).

  41. Szabo, A. & Ostlund, N. S. Modern Quantum Chemistry (Dover Publications, 1996).

  42. Becca, F. & Sorella, S. Quantum Monte Carlo Approaches for Correlated Systems 1st edn (Cambridge Univ. Press, 2017).

  43. Teale, A. M. et al. DFT exchange: sharing perspectives on the workhorse of quantum chemistry and materials science. Phys. Chem. Chem. Phys. 24, 28700–28781 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  44. Chan, G. K.-L. & Sharma, S. The density matrix renormalization group in quantum chemistry. Annu. Rev. Phys. Chem. 62, 465 (2011).

    Article  CAS  PubMed  Google Scholar 

  45. Huron, B., Malrieu, J. P. & Rancurel, P. Iterative perturbation calculations of ground and excited state energies from multiconfigurational zeroth-order wavefunctions. J. Chem. Phys. 58, 5745–5759 (1973).

    Article  CAS  Google Scholar 

  46. Booth, G. H., Thom, A. J. W. & Alavi, A. Fermion Monte Carlo without fixed nodes: a game of life, death, and annihilation in Slater determinant space. J. Chem. Phys. 131, 054106 (2009).

    Article  PubMed  Google Scholar 

  47. Olsen, J. The CASSCF method: a perspective and commentary: CASSCF Method. Int. J. Quantum Chem. 111, 3267–3272 (2011).

    Article  CAS  Google Scholar 

  48. Carleo, G. & Troyer, M. Solving the quantum many-body problem with artificial neural networks. Science 355, 602–606 (2017).

    Article  CAS  PubMed  Google Scholar 

  49. Saito, H. Solving the Bose–Hubbard model with machine learning. J. Phys. Soc. Jpn. 86, 093001 (2017).

    Article  Google Scholar 

  50. Nomura, Y., Darmawan, A. S., Yamaji, Y. & Imada, M. Restricted Boltzmann machine learning for solving strongly correlated quantum systems. Phys. Rev. B 96, 205152 (2017).

    Article  Google Scholar 

  51. Adams, C., Carleo, G., Lovato, A. & Rocco, N. Variational Monte Carlo calculations of A≤4 nuclei with an artificial neural-network correlator ansatz. Phys. Rev. Lett. 127, 022502 (2021).

    Article  CAS  PubMed  Google Scholar 

  52. Astrakhantsev, N. et al. Broken-symmetry ground states of the Heisenberg model on the pyrochlore lattice. Phys. Rev. X 11, 041021 (2021).

    CAS  Google Scholar 

  53. Perronnin, F., Liu, Y., Sánchez, J. & Poirier, H. Large-scale image retrieval with compressed fisher vectors. In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition 3384–3391 (IEEE, 2010).

  54. Krizhevsky, A., Sutskever, I. & Hinton, G. E. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems Vol. 25, 1097–1105 (Curran Associates, 2012).

  55. Schmidhuber, J. Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015).

    Article  PubMed  Google Scholar 

  56. LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436–444 (2015).

    Article  CAS  PubMed  Google Scholar 

  57. McCulloch, W. S. & Pitts, W. A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 5, 115–133 (1943).

    Article  Google Scholar 

  58. Rosenblatt, F. The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 65, 386 (1958).

    Article  CAS  PubMed  Google Scholar 

  59. Hornik, K., Stinchcombe, M. & White, H. Multilayer feedforward networks are universal approximators. Neural Netw. 2, 359–366 (1989).

    Article  Google Scholar 

  60. Werbos, P. Beyond regression: new tools for prediction and analysis in the behavioral sciences. PhD thesis. Harvard Univ. (1974).

  61. Linnainmaa, S. The representation of the cumulative rounding error of an algorithm as a Taylor expansion of the local rounding errors. Master’s thesis (in Finnish), Univ. Helsinki (1970).

  62. Linnainmaa, S. Taylor expansion of the accumulated rounding error. BIT Numer. Math. 16, 146–160 (1976).

    Article  Google Scholar 

  63. Rumelhart, D. E., Hinton, G. E. & Williams, R. J. Learning representations by back-propagating errors. Nature 323, 533–536 (1986).

    Article  Google Scholar 

  64. Glorot, X. & Bengio, Y. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the 13th International Conference on Artificial Intelligence and Statistics 249–256 (PMLR, 2010).

  65. Hooker, S. The hardware lottery. Commun. ACM 64, 58–65 (2021).

    Article  Google Scholar 

  66. Dauphin, Y. et al. Identifying and attacking the saddle point problem in high-dimensional non-convex optimization. In Advances in Neural Information Processing Systems Vol. 27, 2933–2941 (Curran Associates, 2014).

  67. Choromanska, A., Henaff, M., Mathieu, M., Arous, G. B. & LeCun, Y. The loss surfaces of multilayer networks. In Proceedings of the 18th International Conference on Artificial Intelligence and Statistics 192–204 (PMLR, 2015).

  68. Bottou, L. & Bousquet, O. Learning using large datasets. In Mining Massive Data Sets for Security 15–26 (IOS Press, 2008).

  69. Bottou, L. & Bousquet, O. The tradeoffs of large-scale learning. In Optimization for Machine Learning, 351–368 (MIT Press, 2011).

  70. Russakovsky, O. et al. ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211–252 (2015).

    Article  Google Scholar 

  71. Abadi, M. et al. TensorFlow: a system for large-scale machine learning. In Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation 265–283 (USENIX Association, 2016).

  72. Paszke, A. et al. Automatic differentiation in PyTorch. In NIPS Workshop on Automatic Differentiation (2017).

  73. Bradbury, J. et al. JAX: Composable Transformations of Python+ NumPy Programs (GitHub, 2018); https://github.com/google/jax.

  74. Goodfellow, I. J., Shlens, J. & Szegedy, C. Explaining and harnessing adversarial examples. Third International Conference on Learning Representations (ICLR) (ICLR, 2015).

  75. LeCun, Y., Bottou, L., Bengio, Y. & Haffner, P. Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998).

    Article  Google Scholar 

  76. Shawe-Taylor, J. Building symmetries into feedforward networks. In 1989 First IEE International Conference on Artificial Neural Networks 158–162 (IET, 1989).

  77. Vaswani, A. et al. Attention is all you need. In Advances in Neural Information Processing Systems Vol. 30, 5998–6008 (Curran Associates, 2017).

  78. Schütt, K. T., Sauceda, H. E., Kindermans, P.-J., Tkatchenko, A. & Müller, K.-R. SchNet — a deep learning architecture for molecules and materials. J. Chem. Phys. 148, 241722 (2018).

    Article  PubMed  Google Scholar 

  79. Bronstein, M. M., Bruna, J., Cohen, T. & Veličković, P. Geometric deep learning: grids, groups, graphs, geodesics, and gauges. Preprint at http://arxiv.org/abs/2104.13478 (2021).

  80. Hinton, G. E. & Salakhutdinov, R. R. Reducing the dimensionality of data with neural networks. Science 313, 504–507 (2006).

    Article  CAS  PubMed  Google Scholar 

  81. Kingma, D. P. & Welling, M. Auto-encoding variational Bayes. Preprint at http://arxiv.org/abs/1312.6114 (2013).

  82. Goodfellow, I. et al. Generative adversarial nets. In Advances in Neural Information Processing Systems Vol. 27, 2672–2680 (Curran Associates, 2014).

  83. Rezende, D. & Mohamed, S. Variational inference with normalizing flows. In Proceedings of the 32nd International Conference on Machine Learning 1530–1538 (PMLR, 2015).

  84. van den Oord, A. et al. WaveNet: a generative model for raw audio. Preprint at http://arxiv.org/abs/1609.3499 (2016).

  85. van den Oord, A. et al. Conditional image generation with PixelCNN decoders. In Advances in Neural Information Processing Systems Vol. 29, 4797–4805 (Curran Associates, 2016).

  86. Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N. & Ganguli, S. Deep unsupervised learning using nonequilibrium thermodynamics. In Proceedings of the 32nd International Conference on Machine Learning 2256–2265 (PMLR, 2015).

  87. Sharir, O., Levine, Y., Wies, N., Carleo, G. & Shashua, A. Deep autoregressive models for the efficient variational simulation of many-body quantum systems. Phys. Rev. Lett. 124, 020503 (2020).

    Article  CAS  PubMed  Google Scholar 

  88. Choo, K., Neupert, T. & Carleo, G. Two-dimensional frustrated J1-J2 model studied with neural network quantum states. Phys. Rev. B 100, 125124 (2019).

    Article  CAS  Google Scholar 

  89. Hibat-Allah, M., Ganahl, M., Hayward, L. E., Melko, R. G. & Carrasquilla, J. Recurrent neural network wave functions. Phys. Rev. Res. 2, 023358 (2020).

  90. Xie, H., null, L. Z. & Wang, L. Ab-initio study of interacting fermions at finite temperature with neural canonical transformation. J. Mach. Learn. 1, 38 (2022).

    Article  Google Scholar 

  91. Behler, J. & Parrinello, M. Generalized neural-network representation of high-dimensional potential-energy surfaces. Phys. Rev. Lett. 98, 146401 (2007).

    Article  PubMed  Google Scholar 

  92. Rupp, M., Tkatchenko, A., Müller, K.-R. & von Lilienfeld, O. A. Fast and accurate modeling of molecular atomization energies with machine learning. Phys. Rev. Lett. 108, 058301 (2012).

    Article  PubMed  Google Scholar 

  93. Bartók, A. P., Kondor, R. & Csányi, G. On representing chemical environments. Phys. Rev. B 87, 184115 (2013).

    Article  Google Scholar 

  94. Schütt, K. T., Arbabzadah, F., Chmiela, S., Müller, K. R. & Tkatchenko, A. Quantum-chemical insights from deep tensor neural networks. Nat. Commun. 8, 13890 (2017).

    Article  PubMed  PubMed Central  Google Scholar 

  95. Thomas, N. et al. Tensor field networks: rotation- and translation-equivariant neural networks for 3D point clouds. Preprint at https://arxiv.org/abs/1802.08219 (2018).

  96. Schütt, K. T., Unke, O. T. & Gastegger, M. Equivariant message passing for the prediction of tensorial properties and molecular spectra. In Proceedings of the 38th International Conference on Machine Learning 9377–9388 (PMLR, 2021).

  97. Miller, B. K., Geiger, M., Smidt, T. E. & Noé, F. Relevance of rotationally equivariant convolutions for predicting molecular properties. Preprint at https://arxiv.org/abs/2008.08461 (2020).

  98. Geiger, M. & Smidt, T. e3nn: Euclidean neural networks. Preprint at http://arxiv.org/abs/2207.09453 (2022).

  99. Batzner, S. E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials. Nat. Commun. 13, 2453 (2022).

  100. Batatia, I., Kovács, D. P., Simm, G. N., Ortner, C. & Csányi, G. MACE: higher order equivariant message passing neural networks for fast and accurate force fields. In Advances in Neural Information Processing Systems Vol. 35, 11423–11436 (Curran Associates, 2022).

  101. Huang, X., Braams, B. J. & Bowman, J. M. Ab initio potential energy and dipole moment surfaces for H5O2+. J. Chem. Phys. 122, 44308 (2005).

    Article  PubMed  Google Scholar 

  102. Drautz, R. Atomic cluster expansion for accurate and transferable interatomic potentials. Phys. Rev. B 99, 014104 (2019).

    Article  CAS  Google Scholar 

  103. Allen, A. E. A., Dusson, G., Ortner, C. & Csányi, G. Atomic permutationally invariant polynomials for fitting molecular force fields. Mach. Learn.: Sci. Tech. 2, 025017 (2021).

    Google Scholar 

  104. Benali, A. et al. Toward a systematic improvement of the fixed-node approximation in diffusion Monte Carlo for solids — A case study in diamond. J. Chem. Phys. 153, 184111 (2020).

    Article  CAS  PubMed  Google Scholar 

  105. Stokes, J., Izaac, J., Killoran, N. & Carleo, G. Quantum natural gradient. Quantum 4, 269 (2020).

    Article  Google Scholar 

  106. Feynman, R. P. & Cohen, M. Energy spectrum of the excitations in liquid helium. Phys. Rev. 102, 1189–1204 (1956).

    Article  Google Scholar 

  107. Kwon, Y., Ceperley, D. M. & Martin, R. M. Effects of three-body and backflow correlations in the two-dimensional electron gas. Phys. Rev. B 48, 12037–12046 (1993).

    Article  CAS  Google Scholar 

  108. Tocchio, L. F., Becca, F., Parola, A. & Sorella, S. Role of backflow correlations for the nonmagnetic phase of the t–t’ Hubbard model. Phys. Rev. B 78, 041101 (2008).

    Article  Google Scholar 

  109. Luo, D. & Clark, B. K. Backflow transformations via neural networks for quantum many-body wave functions. Phys. Rev. Lett. 122, 226401 (2019).

    Article  CAS  PubMed  Google Scholar 

  110. Robledo Moreno, J., Carleo, G., Georges, A. & Stokes, J. Fermionic wave functions from neural-network constrained hidden states. Proc. Natl Acad. Sci. USA 119, e2122059119 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

  111. Lovato, A., Adams, C., Carleo, G. & Rocco, N. Hidden-nucleons neural-network quantum states for the nuclear many-body problem. Phys. Rev. Res. 4, 043178 (2022).

    Article  CAS  Google Scholar 

  112. Yang, Y. & Zhao, P. Deep-neural-network approach to solving the ab initio nuclear structure problem. Phys. Rev. C 107, 034320 (2023).

    Article  CAS  Google Scholar 

  113. Taddei, M., Ruggeri, M., Moroni, S. & Holzmann, M. Iterative backflow renormalization procedure for many-body ground-state wave functions of strongly interacting normal Fermi liquids. Phys. Rev. B 91, 115106 (2015).

    Article  Google Scholar 

  114. Ruggeri, M., Moroni, S. & Holzmann, M. Nonlinear network description for many-body quantum systems in continuous space. Phys. Rev. Lett. 120, 205302 (2018).

    Article  CAS  PubMed  Google Scholar 

  115. Chakravorty, S. J., Gwaltney, S. R. & Davidson, E. R. Ground-state correlation energies for atomic ions with to 18 electrons. Phys. Rev. A 44, 7071 (1991).

    Article  PubMed  Google Scholar 

  116. Hermann, J., Schätzle, Z. & Noé, F. Deep-neural-network solution of the electronic Schrödinger equation. Nat. Chem. 12, 891–897 (2020).

    Article  CAS  PubMed  Google Scholar 

  117. Ma, A., Towler, M. D., Drummond, N. D. & Needs, R. J. Scheme for adding electron–nucleus cusps to Gaussian orbitals. J. Chem. Phys. 122, 224322 (2005).

    Article  CAS  PubMed  Google Scholar 

  118. Schätzle, Z., Hermann, J. & Noé, F. Convergence to the fixed-node limit in deep variational Monte Carlo. J. Chem. Phys. 154, 124108 (2021).

    Article  PubMed  Google Scholar 

  119. Pfau, D., Spencer, J. S., Matthews, A. G. D. G. & Foulkes, W. M. C. Ab initio solution of the many-electron Schrödinger equation with deep neural networks. Phys. Rev. Res. 2, 033429 (2020).

    Article  CAS  Google Scholar 

  120. Kingma, D. P. & Ba, J. Adam: a method for stochastic optimization. Preprint at http://arxiv.org/abs/1412.6980 (2015).

  121. Martens, J. & Grosse, R. Optimizing neural networks with kronecker-factored approximate curvature. In Proceedings of the 32nd International Conference on Machine Learning 2408–2417 (PMLR, 2015).

  122. Gerard, L., Scherbela, M., Marquetand, P. & Grohs, P. Gold-standard solutions to the Schrödinger equation using deep learning: how much physics do we need? In Advances in Neural Information Processing Systems, Vol. 35, 10282–10294 (Curran Associates, 2022).

  123. von Glehn, I., Spencer, J. S. & Pfau, D. A self-attention ansatz for ab-initio quantum chemistry. In International Conference on Learning Representations (ICLR 2023) (OpenReview, 2023).

  124. Scherbela, M., Reisenhofer, R., Gerard, L., Marquetand, P. & Grohs, P. Solving the electronic Schrödinger equation for multiple nuclear geometries with weight-sharing deep neural networks. Nat. Comput. Sci. 2, 331 (2022).

    Article  Google Scholar 

  125. Yang, L., Hu, W. & Li, L. Scalable variational Monte Carlo with graph neural ansatz. Preprint at http://arxiv.org/abs/2011.12453 (2020).

  126. Gao, N. & Günnemann, S. Ab-initio potential energy surfaces by pairing GNNs with neural wave functions. In International Conference on Learning Representations (ICLR 2022) (OpenReview, 2022).

  127. Gao, N. & Günnemann, S. Sampling-free inference for ab-initio potential energy surface networks. In International Conference on Learning Representations (ICLR 2023) (OpenReview, 2023).

  128. Feynman, R. P. Forces in molecules. Phys. Rev. 56, 340 (1939).

    Article  CAS  Google Scholar 

  129. Assaraf, R. & Caffarel, M. Zero-variance zero-bias principle for observables in quantum Monte Carlo: application to forces. J. Chem. Phys. 119, 10536–10552 (2003).

    Article  CAS  Google Scholar 

  130. Umrigar, C. Two aspects of quantum Monte Carlo: determination of accurate wavefunctions and determination of potential energy surfaces of molecules. Int. J. Quantum Chem. 36, 217–230 (1989).

    Article  Google Scholar 

  131. Qian, Y., Fu, W., Ren, W. & Chen, J. Interatomic force from neural network based variational quantum Monte Carlo. J. Chem. Phys. 157, 164104 (2022).

    Article  CAS  PubMed  Google Scholar 

  132. Pescia, G., Han, J., Lovato, A., Lu, J. & Carleo, G. Neural-network quantum states for periodic systems in continuous space. Phys. Rev. Res. 4, 023138 (2022).

    Article  CAS  Google Scholar 

  133. Wilson, M. et al. Neural network ansatz for periodic wave functions and the homogeneous electron gas. Phys. Rev. B 107, 235139 (2023).

    Article  CAS  Google Scholar 

  134. Cassella, G. et al. Discovering quantum phase transitions with fermionic neural networks. Phys. Rev. Lett. 130, 036401 (2023).

    Article  CAS  PubMed  Google Scholar 

  135. Li, X., Li, Z. & Chen, J. Ab initio calculation of real solids via neural network ansatz. Nat. Commun. 13, 7895 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  136. Li, X., Fan, C., Ren, W. & Chen, J. Fermionic neural network with effective core potential. Phys. Rev. Res. 4, 013021 (2022).

    Article  CAS  Google Scholar 

  137. Needs, R. J., Towler, M. D., Drummond, N. D., López Ríos, P. & Trail, J. R. Variational and diffusion quantum Monte Carlo calculations with the CASINO code. J. Chem. Phys. 152, 154106 (2020).

    Article  CAS  PubMed  Google Scholar 

  138. Shi, H. & Zhang, S. Some recent developments in auxiliary-field quantum Monte Carlo for real materials. J. Chem. Phys. 154, 024107 (2021).

    Article  CAS  PubMed  Google Scholar 

  139. Wilson, M., Gao, N., Wudarski, F., Rieffel, E. & Tubman, N. M. Simulations of state-of-the-art fermionic neural network wave functions with diffusion Monte Carlo. Preprint at http://arxiv.org/abs/2103.12570 (2021).

  140. Ren, W., Fu, W. & Chen, J. Towards the ground state of molecules via diffusion Monte Carlo on neural networks. Nat. Commun. 14, 1860 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  141. Schautz, F. & Filippi, C. Optimized Jastrow–Slater wave functions for ground and excited states: application to the lowest states of ethene. J. Chem. Phys. 120, 10931 (2004).

    Article  CAS  PubMed  Google Scholar 

  142. Dash, M., Feldt, J., Moroni, S., Scemama, A. & Filippi, C. Excited states with selected configuration interaction-quantum Monte Carlo: chemically accurate excitation energies and geometries. J. Chem. Theory Comput. 15, 4896 (2019).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  143. Zhao, L. & Neuscamman, E. An efficient variational principle for the direct optimization of excited states. J. Chem. Theory Comput. 12, 3436 (2016).

    Article  CAS  PubMed  Google Scholar 

  144. Pathak, S., Busemeyer, B., Rodrigues, J. N. B. & Wagner, L. K. Excited states in variational Monte Carlo using a penalty method. J. Chem. Phys. 154, 034101 (2021).

    Article  CAS  PubMed  Google Scholar 

  145. Entwistle, M., Schätzle, Z., Erdman, P. A., Hermann, J. & Noé, F. Electronic excited states in deep variational Monte Carlo. Nat. Commun. 14, 274 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  146. Choo, K., Carleo, G., Regnault, N. & Neupert, T. Symmetries and many-body excitations with neural-network quantum states. Phys. Rev. Lett. 121, 167204 (2018).

    Article  CAS  PubMed  Google Scholar 

  147. Cuzzocrea, A., Scemama, A., Briels, W. J., Moroni, S. & Filippi, C. Variational principles in quantum Monte Carlo: the troubled story of variance minimization. J. Chem. Theory Comput. 16, 4203 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  148. Jordan, P. & Wigner, E. über das Paulische Äquivalenzverbot. Z. Phys. 47, 631 (1928).

    Article  CAS  Google Scholar 

  149. Bravyi, S. & Kitaev, A. Fermionic quantum computation. Ann. Phys. 298, 210–226 (2002).

    Article  CAS  Google Scholar 

  150. Sorella, S. Green function Monte Carlo with stochastic reconfiguration. Phys. Rev. Lett. 80, 4558–4561 (1998).

    Article  CAS  Google Scholar 

  151. Choo, K., Mezzacapo, A. & Carleo, G. Fermionic neural-network states for ab-initio electronic structure. Nat. Commun. 11, 2368 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  152. Yang, P.-J., Sugiyama, M., Tsuda, K. & Yanai, T. Artificial neural networks applied as molecular wave function solvers. J. Chem. Theory Comput. 16, 3513–3529 (2020).

    Article  CAS  PubMed  Google Scholar 

  153. Torlai, G., Mazzola, G., Carleo, G. & Mezzacapo, A. Precise measurement of quantum observables with neural-network estimators. Phys. Rev. Res. 2, 022060 (2020).

    Article  CAS  Google Scholar 

  154. Iouchtchenko, D., Gonthier, J. F., Perdomo-Ortiz, A. & Melko, R. G. Neural network enhanced measurement efficiency for molecular groundstates. Mach. Learn. Sci. Technol. 4, 015016 (2023).

    Article  Google Scholar 

  155. Glielmo, A., Rath, Y., Csányi, G., De Vita, A. & Booth, G. H. Gaussian process states: a data-driven representation of quantum many-body physics. Phys. Rev. X 10, 041026 (2020).

    CAS  Google Scholar 

  156. Del Re, G., Ladik, J. & Biczó, G. Self-consistent-field tight-binding treatment of polymers. I. Infinite three-dimensional case. Phys. Rev. 155, 997–1003 (1967).

    Article  Google Scholar 

  157. Yoshioka, N., Mizukami, W. & Nori, F. Solving quasiparticle band spectra of real solids using neural-network quantum states. Commun. Phys. 4, 1–8 (2021).

    Article  Google Scholar 

  158. Barrett, T. D., Malyshev, A. & Lvovsky, A. I. Autoregressive neural-network wavefunctions for ab initio quantum chemistry. Nat. Mach. Intell. 4, 351 (2022).

    Article  Google Scholar 

  159. Zhao, T., Stokes, J. & Veerapaneni, S. Scalable neural quantum states architecture for quantum chemistry. Mach. Learn. Sci. Technol. 4, 025034 (2023).

    Article  Google Scholar 

  160. Giner, E., Scemama, A. & Caffarel, M. Using perturbatively selected configuration interaction in quantum Monte Carlo calculations. Can. J. Chem. 91, 879–885 (2013).

    Article  CAS  Google Scholar 

  161. Holmes, A. A., Tubman, N. M. & Umrigar, C. Heat–bath configuration interaction: an efficient selected configuration interaction algorithm inspired by heat-bath sampling. J. Chem. Theory Comput. 12, 3674–3680 (2016).

    Article  CAS  PubMed  Google Scholar 

  162. Sharma, S., Holmes, A. A., Jeanmairet, G., Alavi, A. & Umrigar, C. J. Semistochastic heat–bath configuration interaction method: selected configuration interaction with semistochastic perturbation theory. J. Chem. Theory Comput. 13, 1595–1604 (2017).

    Article  CAS  PubMed  Google Scholar 

  163. Greer, J. Monte Carlo configuration interaction. J. Comput. Phys. 146, 181–202 (1998).

    Article  Google Scholar 

  164. Coe, J. P. Machine learning configuration interaction. J. Chem. Theory Comput. 14, 5739–5749 (2018).

    Article  CAS  PubMed  Google Scholar 

  165. Goings, J. J., Hu, H., Yang, C. & Li, X. Reinforcement learning configuration interaction. J. Chem. Theory Comput. 17, 5482–5491 (2021).

    Article  CAS  PubMed  Google Scholar 

  166. Pineda Flores, S. D. Chembot: a machine learning approach to selective configuration interaction. J. Chem. Theory Comput. 17, 4028 (2021).

    Article  CAS  PubMed  Google Scholar 

  167. Nooijen, M., Shamasundar, K. & Mukherjee, D. Reflections on size-extensivity, size-consistency and generalized extensivity in many-body theory. Mol. Phys. 103, 2277–2298 (2005).

    Article  CAS  Google Scholar 

  168. Hutter, M. On representing (anti)symmetric functions. Preprint at http://arxiv.org/abs/2007.15298 (2020).

  169. Neuscamman, E. The Jastrow antisymmetric geminal power in Hilbert space: theory, benchmarking, and application to a novel transition state. J. Chem. Phys. 139, 194105 (2013).

    Article  PubMed  Google Scholar 

  170. Sabzevari, I. & Sharma, S. Improved speed and scaling in orbital space variational Monte Carlo. J. Chem. Theory Comput. 14, 6276–6286 (2018).

    Article  CAS  PubMed  Google Scholar 

  171. Rubenstein, B. Introduction to the variational monte carlo method in quantum chemistry and physics. In Variational Methods in Molecular Modeling 285–313 (Springer, 2017).

  172. Toulouse, J., Assaraf, R. & Umrigar, C. J. Introduction to the variational and diffusion Monte Carlo methods. In Advances in Quantum Chemistry Vol. 73, 285–314 (Elsevier, 2016).

  173. Amari, S. Natural gradient works efficiently in learning. Neural Comput. 10, 251–276 (1998).

    Article  Google Scholar 

  174. Ay, N., Jost, J., Lê, H. V. & Schwachhöfer, L. Information Geometry. No. 64 in a Series of Modern Surveys in Mathematics (Springer, 2017).

  175. Spencer, J. S., Pfau, D., Botev, A. & Foulkes, W. M. C. Better, faster fermionic neural networks. Preprint at http://arxiv.org/abs/2011.07125 (2020).

Download references

Acknowledgements

The authors acknowledge funding from the German Ministry for Education and Research (Berlin Institute for the Foundations of Learning and Data, BIFOLD), the Berlin Mathematics Research Center MATH+ (AA1-6 and AA2-8) and European Commission (ERC CoG 772230 ScaleCell). G.C. is supported by the Swiss National Science Foundation under Grant No. 200021_200336, and by the NCCR MARVEL, a National Centre of Competence in Research, under Grant No. 205602. The authors are grateful to N. Yoshioka for providing us with the raw data of ref. 157. W.M.C.F. and his co-workers gratefully acknowledge PRACE for awarding them access to the JUWELS Booster supercomputer (https://apps.fz-juelich.de/jsc/hps/juwels/booster-overview.html); the HPC RIVR Consortium (https://www.hpc-rivr.si) and EuroHPC JU for providing computing resources on the Vega HPC system at the Institute of Information Science (https://www.izum.si) and the UK Engineering and Physical Sciences Research Council for providing computing resources at the Baskerville Tier 2 HPC service (https://www.baskerville.ac.uk). Baskerville was funded by the EPSRC and UKRI through the World Class Labs scheme (EP/T022221/1) and the Digital Research Infrastructure programme (EP/W032244/1) and is operated by Advanced Research Computing at the University of Birmingham.

Author information

Author notes

  1. These authors contributed equally: Jan Hermann, James Spencer, Kenny Choo.

Authors and Affiliations

  1. Microsoft Research AI4Science, Berlin, Germany

    Jan Hermann & Frank Noé

  2. FU Berlin, Department of Mathematics and Computer Science, Berlin, Germany

    Jan Hermann & Frank Noé

  3. DeepMind, London, UK

    James Spencer & David Pfau

  4. Department of Physics, University of Zurich, Zurich, Switzerland

    Kenny Choo

  5. IBM Quantum, IBM Research Zurich, Ruschlikon, Switzerland

    Kenny Choo

  6. IBM Quantum, Thomas J. Watson Research Center, New York, NY, USA

    Antonio Mezzacapo

  7. Imperial College London, Department of Physics, London, UK

    W. M. C. Foulkes & David Pfau

  8. EPFL, Institute of Physics, Lausanne, Switzerland

    Giuseppe Carleo

  9. FU Berlin, Department of Physics, Berlin, Germany

    Frank Noé

  10. Department of Chemistry,Rice University, Houston, TX, USA

    Frank Noé

Authors
  1. Jan Hermann
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. James Spencer
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Kenny Choo
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Antonio Mezzacapo
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. W. M. C. Foulkes
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. David Pfau
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Giuseppe Carleo
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Frank Noé
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

J.H., J.S. and K.C. contributed equally and all authors were part of the discussion, reviewing and editing of the manuscript.

Corresponding authors

Correspondence to David Pfau, Giuseppe Carleo or Frank Noé.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Reviews Chemistry thanks Pavlo Dral and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Additional information

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hermann, J., Spencer, J., Choo, K. et al. Ab initio quantum chemistry with neural-network wavefunctions. Nat Rev Chem 7, 692–709 (2023). https://doi.org/10.1038/s41570-023-00516-8

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41570-023-00516-8

Search

Advanced 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