Learning from the Density to Correct Total Energy and Forces in First Principle Simulations

Abstract

We propose a new molecular simulation framework that combines the transferability, robustness and chemical flexibility of an ab initio method with the accuracy and efficiency of a machine learned force field. The key to achieve this mix is to use a standard density functional theory (DFT) simulation as a pre-processor for the atomic and molecular information, obtaining a good quality electronic density. General, symmetry preserving, atom-centered electronic descriptors are then built from this density to train a neural network to correct the baseline DFT energies and forces. These electronic descriptors encode much more information than local atomic environments, allowing a simple neural network to reach the accuracy required for the problem of study at a negligible cost. The balance between accuracy and efficiency is determined by the baseline simulation. This is shown in results where high level quantum chemical accuracy is obtained for simulations of liquid water at standard DFT cost, or where high level DFT-accuracy is achieved in simulations with a low-level baseline DFT calculation, at a significantly reduced cost.

References in corpus (28)

• The SIESTA method for ab initio order-N materials simulation
• Efficient index handling of multidimensional periodic boundary conditions
• Van der Waals Density Functional for General Geometries
• Automatic chemical design using a data-driven continuous representation of molecules
• On representing chemical environments
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• SchNet - a deep learning architecture for molecules and materials
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Perspective: How good is DFT for water?
• By-passing the Kohn-Sham equations with machine learning
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Finding Density Functionals with Machine Learning
• An exchange functional that tests the robustness of the plasmon description of the van der Waals density functional
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• Ab initio theory and modeling of water
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Understanding and reducing errors in density functional calculations
• The Individual and Collective Effects of Exact Exchange and Dispersion Interactions on the Ab Initio Structure of Liquid Water
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• A Transferable Machine-Learning Model of the Electron Density
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• Comparison of permutationally invariant polynomials, neural networks, and Gaussian approximation potentials in representing water interactions through many-body expansions
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• Neural-network Kohn-Sham exchange-correlation potential and its out-of-training transferability
• Efficient mixed-force first-principles molecular dynamics
• Optimization of an exchange-correlation density functional for water
• Completing density functional theory by machine-learning hidden messages from molecules

Cited by in corpus (11)

• Physics-inspired structural representations for molecules and materials
• A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
• An orbital-based representation for accurate Quantum Machine Learning
• Efficient Learning of a One-dimensional Density Functional Theory
• Machine learning band gaps from the electron density
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Mean-Field Density Matrix Decompositions
• Machine learning for accuracy in density functional approximations
• Embedding quantum statistical excitations in a classical force field
• Using differentiable programming to obtain an energy and density-optimized exchange-correlation functional
• Physical machine learning outperforms "human learning" in Quantum Chemistry