Quantum deep field: data-driven wave function, electron density generation, and atomization energy prediction and extrapolation with machine learning

Abstract

Deep neural networks (DNNs) have been used to successfully predict molecular properties calculated based on the Kohn--Sham density functional theory (KS-DFT). Although this prediction is fast and accurate, we believe that a DNN model for KS-DFT must not only predict the properties but also provide the electron density of a molecule. This letter presents the quantum deep field (QDF), which provides the electron density with an unsupervised but end-to-end physics-informed modeling by learning the atomization energy on a large-scale dataset. QDF performed well at atomization energy prediction, generated valid electron density, and demonstrated extrapolation. Our QDF implementation is available at https://github.com/masashitsubaki/QuantumDeepField_molecule.

References in corpus (15)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• SchNet - a deep learning architecture for molecules and materials
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• By-passing the Kohn-Sham equations with machine learning
• Machine learning prediction errors better than DFT accuracy
• Mayavi: a package for 3D visualization of scientific data
• Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
• Physically-informed artificial neural networks for atomistic modeling of materials
• Embedded Atom Neural Network Potentials: Efficient and Accurate Machine Learning with a Physically Inspired Representation
• A Transferable Machine-Learning Model of the Electron Density
• Deep Learning and Density Functional Theory
• Predicting charge density distribution of materials using a local-environment-based graph convolutional network
• Deep learning the Hohenberg-Kohn maps of Density Functional Theory

Cited by in corpus (15)

• Deep-Learning Density Functional Theory Hamiltonian for Efficient ab initio Electronic-Structure Calculation
• Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physics
• A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
• Predicting electronic structures at any length scale with machine learning
• Equivariant graph neural networks for fast electron density estimation of molecules, liquids, and solids
• Machine learning nonequilibrium electron forces for adiabatic spin dynamics
• Transferable empirical pseudopotenials from machine learning
• A Tutorial on the Use of Physics-Informed Neural Networks to Compute the Spectrum of Quantum Systems
• Training-free hyperparameter optimization of neural networks for electronic structures in matter
• Addressing the Non-perturbative Regime of the Quantum Anharmonic Oscillator by Physics-Informed Neural Networks
• Shifting computational boundaries for complex organic materials
• Machine learning the electronic structure of matter across temperatures
• Ab-Initio Potential Energy Surfaces by Pairing GNNs with Neural Wave Functions
• Properties of fermionic systems with the Path-integral ground state method
• Machine learning based prediction of the electronic structure of quasi-one-dimensional materials under strain