Deep-learning density functional perturbation theory

Abstract

Calculating perturbation response properties of materials from first principles provides a vital link between theory and experiment, but is bottlenecked by the high computational cost. Here a general framework is proposed to perform density functional perturbation theory (DFPT) calculations by neural networks, greatly improving the computational efficiency. Automatic differentiation is applied on neural networks, facilitating accurate computation of derivatives. High efficiency and good accuracy of the approach are demonstrated by studying electron-phonon coupling and related physical quantities. This work brings deep-learning density functional theory and DFPT into a unified framework, creating opportunities for developing ab initio artificial intelligence.

References in corpus (26)

• Quantum ESPRESSO: a modular and open-source software project for quantum simulations of materials
• The SIESTA method for ab initio order-N materials simulation
• Efficient index handling of multidimensional periodic boundary conditions
• Phonons and related properties of extended systems from density-functional perturbation theory
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• SchNet - a deep learning architecture for molecules and materials
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Electron-phonon interactions from first principles
• Optimization Algorithm for the Generation of ONCV Pseudopotentials
• Graphene Bilayers with a Twist
• By-passing the Kohn-Sham equations with machine learning
• Nearsightedness of Electronic Matter
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• First-principles method for electron-phonon coupling and electron mobility: Applications to 2D materials
• Deep-Learning Density Functional Theory Hamiltonian for Efficient ab initio Electronic-Structure Calculation
• Differentiable Programming Tensor Networks
• Towards high-throughput superconductor discovery via machine learning
• Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physics
• General framework for E(3)-equivariant neural network representation of density functional theory Hamiltonian
• Automatic differentiation in quantum chemistry with an application to fully variational Hartree-Fock
• Lattice Dynamics Calculations based on Density-functional Perturbation Theory in Real Space
• Deep-learning electronic-structure calculation of magnetic superstructures
• Ab Initio Electron-Phonon Interactions Using Atomic Orbital Wavefunctions
• Electron-Phonon Interactions Using the PAW Method and Wannier Functions
• Van der Waals Coefficients of Atoms and Molecules from a Simple Approximation for the Polarizability

Cited by in corpus (8)

• AI-driven inverse design of materials: Past, present and future
• Universal materials model of deep-learning density functional theory Hamiltonian
• Neural-network Density Functional Theory Based on Variational Energy Minimization
• Superconductor discovery in the emerging paradigm of Materials Informatics
• Band gap renormalization, carrier mobility, and transport in Mg${}_2$Si and Ca${}_2$Si: \textit{Ab initio} scattering and Boltzmann transport equation study
• Electronic structures of crystalline and amorphous GeSe and GeSbTe compounds using machine learning empirical pseudopotentials
• Predicting Many Crystal Properties via an Adaptive Transformer-based Framework
• Generalized deformation potential and machine-learning approaches for electron-phonon coupling and thermoelectric transport in semiconductors