Equivariant analytical mapping of first principles Hamiltonians to accurate and transferable materials models

Abstract

We propose a scheme to construct predictive models for Hamiltonian matrices in atomic orbital representation from ab initio data as a function of atomic and bond environments. The scheme goes beyond conventional tight binding descriptions as it represents the ab initio model to full order, rather than in two-centre or three-centre approximations. We achieve this by introducing an extension to the Atomic Cluster Expansion (ACE) descriptor that represents Hamiltonian matrix blocks that transform equivariantly with respect to the full rotation group. The approach produces analytical linear models for the Hamiltonian and overlap matrices. Through an application to aluminium, we demonstrate that it is possible to train models from a handful of structures computed with density functional theory, and apply them to produce accurate predictions for the electronic structure. The model generalises well and is able to predict defects accurately from only bulk training data.

15 pages, 9 figures; included vacancy PDOS and restricted FCC or BCC training sets

References in corpus (5)

• Anharmonicity Measure for Materials
• Recursive evaluation and iterative contraction of $N$-body equivariant features
• Equivariant representations for molecular Hamiltonians and N-center atomic-scale properties
• A deep neural network for molecular wave functions in quasi-atomic minimal basis representation
• SE(3)-equivariant prediction of molecular wavefunctions and electronic densities

Cited by in corpus (16)

• General framework for E(3)-equivariant neural network representation of density functional theory Hamiltonian
• Transferable E(3) equivariant parameterization for Hamiltonian of molecules and solids
• Crystal Net Catalog of Model Flat Band Materials
• Deep learning tight-binding approach for large-scale electronic simulations at finite temperatures with $ab$ $initio$ accuracy
• Universal Machine Learning Kohn-Sham Hamiltonian for Materials
• Machine Learning and Data-Driven Methods in Computational Surface and Interface Science
• Assessing mixed quantum-classical molecular dynamics methods for nonadiabatic dynamics of molecules on metal surfaces
• Linear Jacobi-Legendre expansion of the charge density for machine learning-accelerated electronic structure calculations
• Predicting The One-Particle Density Matrix With Machine Learning
• Exploring the design space of machine-learning models for quantum chemistry with a fully differentiable framework
• Ab initio electron-lattice downfolding: potential energy landscapes, anharmonicity, and molecular dynamics in charge density wave materials
• Integrated workflows and interfaces for data-driven semi-empirical electronic structure calculations
• Equivariant Electronic Hamiltonian Prediction with Many-Body Message Passing
• A general formalism for machine-learning models based on multipolar-spherical harmonics
• NQCDynamics.jl: A Julia Package for Nonadiabatic Quantum Classical Molecular Dynamics in the Condensed Phase
• Machine learning of electronic structure and atomistic properties from the external potential