Inverting the Kohn-Sham equations with physics-informed machine learning
arXiv:2312.15301 · doi:10.1088/2632-2153/ad3159
Abstract
Electronic structure theory calculations offer an understanding of matter at the quantum level, complementing experimental studies in materials science and chemistry. One of the most widely used methods, density functional theory (DFT), maps a set of real interacting electrons to a set of fictitious non-interacting electrons that share the same probability density. Ensuring that the density remains the same depends on the exchange-correlation (XC) energy and, by a derivative, the XC potential. Inversions provide a method to obtain exact XC potentials from target electronic densities, in hopes of gaining insights into accuracy-boosting approximations. Neural networks provide a new avenue to perform inversions by learning the mapping from density to potential. In this work, we learn this mapping using physics-informed machine learning (PIML) methods, namely physics informed neural networks (PINNs) and Fourier neural operators (FNOs). We demonstrate the capabilities of these two methods on a dataset of one-dimensional atomic and molecular models. The capabilities of each approach are discussed in conjunction with this proof-of-concept presentation. The primary finding of our investigation is that the combination of both approaches has the greatest potential for inverting the Kohn-Sham equations at scale.
References in corpus (30)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Restoring the density-gradient expansion for exchange in solids and surfaces
- Generalized gradient approximation for solids and their surfaces
- Climbing the Density Functional Ladder: Non-Empirical Meta-Generalized Gradient Approximation Designed for Molecules and Solids
- B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Data
- Physics-informed neural networks for inverse problems in nano-optics and metamaterials
- Empirical Double-Hybrid Density Functional Theory: A 'Third Way' In Between WFT and DFT
- DFT: A Theory Full of Holes?
- Multipole Graph Neural Operator for Parametric Partial Differential Equations
- Neural Operator: Graph Kernel Network for Partial Differential Equations
- Solving Inverse Problems With Deep Neural Networks -- Robustness Included?
- Machine learning and density functional theory
- A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
- Machine Learning the Physical Non-Local Exchange-Correlation Functional of Density-Functional Theory
- Universal Dynamical Steps in the Exact Time-Dependent Exchange-Correlation Potential
- Numerical Methods for the Inverse Problem of Density Functional Theory
- Design and Analysis of Machine Learning Exchange-Correlation Functionals via Rotationally Invariant Convolutional Descriptors
- Reference electronic structure calculations in one dimension
- Exact and approximate Kohn-Sham potentials in ensemble density-functional theory
- Multi-scale Convolutional Neural Networks for Inverse Problems
- Exact time-dependent density-functional potentials for strongly correlated tunneling electrons
- Machine learning density functional theory for the Hubbard model
- Derivative discontinuity and exchange-correlation potential of meta-GGAs in density-functional theory
- Machine learning the derivative discontinuity of density-functional theory
- Machine Learning Exchange-Correlation Potential in Time Dependent Density Functional Theory
- Density-inversion method for the Kohn-Sham potential: role of the screening density
- The Exact Exchange-Correlation Potential in Time-Dependent Density Functional Theory: Choreographing Electrons with Steps and Peaks
- How Well Does Kohn-Sham Regularizer Work for Weakly Correlated Systems?
- Absence of Dynamical Steps in the Exact Correlation Potential in Linear Response
- Smart energy models for atomistic simulations using a DFT-driven multifidelity approach