Deep learning electronic structure calculation of magnetic superstructure

Machine Learning


  • Nagaosa, N. & Tokura, Y. Topological properties and dynamics of magnetic skyrmions. nut. nanotech. 8899–911 (2013).

    Articles Google Scholar

  • Behler, J. & Parrinello, M. A generalized neural network representation of high-dimensional potential energy surfaces. Physics. Rev. Lett. 98146401 (2007).

    Articles Google Scholar

  • Zhang, L., Han, J., Wang, H., Car, R. & E, W. Deep potential molecular dynamics: scalable models with quantum mechanical accuracy. Physics. Rev. Lett. 120143001 (2018).

    Articles Google Scholar

  • Gilmer, J., Schoenholz, SS, Riley, PF, Vinylals, O. & Dahl, GE Neural Message Passing for Quantum Chemistry.of Proceedings The 34th International Conference on Machine Learning roll. 70, 1263–1272 (JMLR.org, 2017); http://proceedings.mlr.press/v70/gilmer17a.html

  • Schütt, KT, Sauceda, HE, Kindermans, P.-J., Tkatchenko, A. & Müller, K.-R. SchNet — A deep learning architecture for molecules and materials. J. Chem. Physics. 148241722 (2018).

    Articles Google Scholar

  • Unke, OT et al. Spookynet: Force field learning with electronic degrees of freedom and non-local effects. nut. communicate. 127273 (2021).

    Articles Google Scholar

  • Schütt, KT, Gastegger, M., Tkatchenko, A., Müller, K.-R. & Maurer, RJ Integrating Machine Learning and Quantum Chemistry with Deep Neural Networks of Molecular Wavefunctions. nut. communicate. Ten5024 (2019).

    Articles Google Scholar

  • Li, H. et al. Deep learning density functional theory Hamiltonian for efficient first-principles electronic structure calculations. nut. Calculate. Science. 2367–377 (2022).

    Articles Google Scholar

  • Li, H. & Xu, Y. Improving the efficiency of ab initio electronic structure calculations by deep learning. nut. Calculate. Science. 2418–419 (2022).

    Articles Google Scholar

  • Unke, OT et al. SE(3) equivalent predictions of molecular wavefunctions and electron densities.of The 35th Conference on Neural Information Processing Systems 14434–14447 (Karan Associates, 2021); https://openreview.net/forum?id=auGY2UQfhSu

  • Gong, X. et al. A general framework for the E(3) equivariant neural network representation of the density functional theory Hamiltonian. Preprint of https://arxiv.org/abs/2210.13955 (2022).

  • Su, M., Yang, J.-H., Xiang, H.-J. & Gong, X.-G. Efficient prediction of density functional theory Hamiltonian by graph neural networks. Preprint of https://arxiv.org/abs/2205.05475 (2022).

  • Zhong, Y., Yu, H., Su, M., Gong, X. & Xiang, H. Transferable E(3) isovariant parameterizations for molecular and solid Hamiltonians. Preprint of https://arxiv.org/abs/2210.16190 (2022).

  • Batzner, S. et al. E(3) isovariant graph neural networks for data-efficient and accurate interatomic potentials. nut. communicate. 132453 (2022).

    Articles Google Scholar

  • Musaelian, A. et al. Learning local equivariant representations in large-scale nuclear science. nut. communicate. 14579 (2023).

    Articles Google Scholar

  • Dederichs, PH, Blügel, S., Zeller, R. & Akai, H. Ground states of constrained systems: application to cerium impurities. Physics. Rev. Lett. 532512–2515 (1984).

    Articles Google Scholar

  • Wu, Q. & Van Voorhis, T. Direct optimization methods for studying constrained systems within density functional theory. Physics. Revision A 72024502 ​​(2005).

    Articles Google Scholar

  • Prodan, E. and Kohn, W. Myopia in electronic matter. Proceedings National Academy. Science.united states of america 10211635–11638 (2005).

    Articles Google Scholar

  • Unke, OT et al. Machine learning force field. Chemistry. Rev. 12110142–10186 (2021).

    Articles Google Scholar

  • Chen, Y., Zhang, L., Wang, H. & E, W. DeePKS: A Comprehensive Data-Driven Approach Towards Chemically Accurate Density Functional Theory. J. Chem. theory. Calculate. 17170–181 (2021).

    Articles Google Scholar

  • Zepeda-Núñez, L. et al. Deep Density: Avoids the Kohn-Sham equation via symmetry-preserving neural networks. J. Computer. Physics. 443110523 (2021).

    Articles MathSciNet MATH Google Scholar

  • Thomas, N. et al. Tensor Field Networks: Rotational and translational equivalent neural networks for 3D point clouds. Preprint from https://arxiv.org/abs/1802.08219 (2018).

  • Geiger, M. & Smidt, T. e3nn: Euclidean Neural Networks. Preprint of https://arxiv.org/abs/2207.09453 (2022).

  • Ozaki, T. Variationally optimized atomic orbitals for large-scale electronic structures. Physics. Revision B 67155108 (2003).

    Articles Google Scholar

  • Amoroso, D., Barone, P. & Picozzi, S. Spontaneous skyrmion lattices from anisotropic symmetric exchange in nickel halide monolayers. nut. communicate. 115784 (2020).

    Articles Google Scholar

  • Gong, C. & Zhang, X. Two-dimensional magnetic crystals and emergent heterostructure devices. chemistry 363eaav4450 (2019).

    Articles Google Scholar

  • Edström, A., Amoroso, D., Picozzi, S., Barone, P. & Stengel, M. Curved magnetism in CrI3. Physics. Rev. Lett. 128177202 (2022).

    Articles Google Scholar

  • Zheng, F. Magnetic skyrmion lattice in a new 2D twisted two-layer magnet. Advantage function. m. 332206923 (2023).

    Articles Google Scholar

  • Li, H. Datasets for deep learning electronic structure calculations of magnetic superstructures. Zenod https://doi.org/10.5281/zenodo.7561013 (2023).

  • Li, H. Code for deep learning electronic structure calculations of magnetic superstructures. Zenod https://doi.org/10.5281/zenodo.7669862 (2023).



  • Source link

    Leave a Reply

    Your email address will not be published. Required fields are marked *