Orbital Mixer: Using Atomic Orbital Features for Basis Dependent Prediction of Molecular Wavefunctions
arXiv:2205.06133 · doi:10.1021/acs.jctc.2c00555
Abstract
Leveraging ab initio data at scale has enabled the development of machine learning models capable of extremely accurate and fast molecular property prediction. A central paradigm of many previous works focuses on generating predictions for only a fixed set of properties. Recent lines of research instead aim to explicitly learn the electronic structure via molecular wavefunctions from which other quantum chemical properties can directly be derived. While previous methods generate predictions as a function of only the atomic configuration, in this work we present an alternate approach that directly purposes basis dependent information to predict molecular electronic structure. The backbone of our model, Orbital Mixer, uses MLP Mixer layers within a simple, intuitive, and scalable architecture and achieves competitive Hamiltonian and molecular orbital energy and coefficient prediction accuracies compared to the state-of-the-art.
References in corpus (33)
- Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
- 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 Force Fields
- Quantum-Chemical Insights from Deep Tensor Neural Networks
- Machine Learning of Accurate Energy-Conserving Molecular Force Fields
- PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
- Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
- Comparing molecules and solids across structural and alchemical space
- 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
- Machine Learning of Molecular Electronic Properties in Chemical Compound Space
- Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
- Deep neural network solution of the electronic Schrödinger equation
- Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
- SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
- OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features
- Solving Many-Electron Schrödinger Equation Using Deep Neural Networks
- Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
- A Data Ecosystem to Support Machine Learning in Materials Science
- Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physics
- Deep Learning and Density Functional Theory
- Variational Monte Carlo calculations of nuclei with an artificial neural-network correlator ansatz
- An overview of self-consistent field calculations within finite basis sets
- Deep Learning for UV Absorption Spectra with SchNarc: First Steps Towards Transferability in Chemical Compound Space
- Equivariant representations for molecular Hamiltonians and N-center atomic-scale properties
- Wave function Ansatz (but Periodic) Networks and the Homogeneous Electron Gas
- A deep neural network for molecular wave functions in quasi-atomic minimal basis representation
- Fast Neural Network Approach for Direct Covariant Forces Prediction in Complex Multi-Element Extended Systems
- Artificial Neural Networks as Trial Wave Functions for Quantum Monte Carlo
- A community-powered search of machine learning strategy space to find NMR property prediction models
- Orbital Mixer: Using Atomic Orbital Features for Basis Dependent Prediction of Molecular Wavefunctions