Physical machine learning outperforms "human learning" in Quantum Chemistry

Abstract

Two types of approaches to modeling molecular systems have demonstrated high practical efficiency. Density functional theory (DFT), the most widely used quantum chemical method, is a physical approach predicting energies and electron densities of molecules. Recently, numerous papers on machine learning (ML) of molecular properties have also been published. ML models greatly outperform DFT in terms of computational costs, and may even reach comparable accuracy, but they are missing physicality - a direct link to Quantum Physics - which limits their applicability. Here, we propose an approach that combines the strong sides of DFT and ML, namely, physicality and low computational cost. By generalizing the famous Hohenberg-Kohn theorems, we derive general equations for exact electron densities and energies that can naturally guide applications of ML in Quantum Chemistry. Based on these equations, we build a deep neural network that can compute electron densities and energies of a wide range of organic molecules not only much faster, but also closer to exact physical values than current versions of DFT. In particular, we reached a mean absolute error in energies of molecules with up to eight non-hydrogen atoms as low as 0.9 kcal/mol relative to CCSD(T) values, noticeably lower than those of DFT (down to ~3 kcal/mol on the same set of molecules) and ML (down to ~1.5 kcal/mol) methods. A simultaneous improvement in the accuracy of predictions of electron densities and energies suggests that the proposed approach describes the physics of molecules better than DFT functionals developed by "human learning" earlier. Thus, physics-based ML offers exciting opportunities for modeling, with high-theory-level quantum chemical accuracy, of much larger molecular systems than currently possible.

arXiv commentarXiv admin note: substantial text overlap with arXiv:1809.02723

References in corpus (36)

• Intriguing properties of neural networks
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• SchNet - a deep learning architecture for molecules and materials
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Long-Range Corrected Hybrid Density Functionals with Improved Dispersion Corrections
• Less is more: sampling chemical space with active learning
• By-passing the Kohn-Sham equations with machine learning
• Machine learning prediction errors better than DFT accuracy
• Finding Density Functionals with Machine Learning
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Understanding and reducing errors in density functional calculations
• ANI-1: A data set of 20M off-equilibrium DFT calculations for organic molecules
• FCHL revisited: faster and more accurate quantum machine learning
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• Embedded Atom Neural Network Potentials: Efficient and Accurate Machine Learning with a Physically Inspired Representation
• A Transferable Machine-Learning Model of the Electron Density
• Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis
• Accurate molecular polarizabilities with coupled-cluster theory and machine learning
• Quantifying Density Errors in DFT
• Using Attribution to Decode Dataset Bias in Neural Network Models for Chemistry
• The Importance of being consistent
• Deep Learning and Density Functional Theory
• Guest Editorial: Special Topic on Data-enabled Theoretical Chemistry
• Solving inverse-PDE problems with physics-aware neural networks
• Regression-clustering for Improved Accuracy and Training Cost with Molecular-Orbital-Based Machine Learning
• Equation of state of fluid methane from first principles with machine learning potentials
• Kinetic energy densities based on the fourth order gradient expansion: performance in different classes of materials and improvement via machine learning
• Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models
• Machine Learned Hückel Theory: Interfacing Physics and Deep Neural Networks
• Deep Neural Network Computes Electron Densities and Energies of a Large Set of Organic Molecules Faster than Density Functional Theory (DFT)
• Learning from the Density to Correct Total Energy and Forces in First Principle Simulations
• Machine Learning Potential Energy Surfaces