Gaussian Moments as Physically Inspired Molecular Descriptors for Accurate and Scalable Machine Learning Potentials

Abstract

Machine learning techniques allow a direct mapping of atomic positions and nuclear charges to the potential energy surface with almost ab-initio accuracy and the computational efficiency of empirical potentials. In this work we propose a machine learning method for constructing high-dimensional potential energy surfaces based on feed-forward neural networks. As input to the neural network we propose an extendable invariant local molecular descriptor constructed from geometric moments. Their formulation via pairwise distance vectors and tensor contractions allows a very efficient implementation on graphical processing units (GPUs). The atomic species is encoded in the molecular descriptor, which allows the restriction to one neural network for the training of all atomic species in the data set. We demonstrate that the accuracy of the developed approach in representing both chemical and configurational spaces is comparable to the one of several established machine learning models. Due to its high accuracy and efficiency, the proposed machine-learned potentials can be used for any further tasks, for example the optimization of molecular geometries, the calculation of rate constants or molecular dynamics.

References in corpus (16)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• SchNet - a deep learning architecture for molecules and materials
• On the Convergence of Adam and Beyond
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• 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
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• Hierarchical modeling of molecular energies using a deep neural network
• Embedded Atom Neural Network Potentials: Efficient and Accurate Machine Learning with a Physically Inspired Representation
• Machine learning of molecular properties: locality and active learning
• A Novel Approach to Describe Chemical Environments in High Dimensional Neural Network Potentials

Cited by in corpus (32)

• Neuroevolution machine learning potentials: Combining high accuracy and low cost in atomistic simulations and application to heat transport
• Machine learning for electronically excited states of molecules
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Neural Network Potentials for Chemistry: Concepts, Applications and Prospects
• Strategies for the Construction of Machine-Learning Potentials for Accurate and Efficient Atomic-Scale Simulations
• Recursive evaluation and iterative contraction of $N$-body equivariant features
• Universal Machine Learning for the Response of Atomistic Systems to External Fields
• The Evolution of Machine Learning Potentials for Molecules, Reactions and Materials
• Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
• Transfer learning for chemically accurate interatomic neural network potentials
• Predicting Properties of Periodic Systems from Cluster Data: A Case Study of Liquid Water
• Fast and Sample-Efficient Interatomic Neural Network Potentials for Molecules and Materials Based on Gaussian Moments
• Tensor-reduced atomic density representations
• Neural-Network Assisted Study of Nitrogen Atom Dynamics on Amorphous Solid Water. I. Adsorption & Desorption
• Thermally Averaged Magnetic Anisotropy Tensors via Machine Learning Based on Gaussian Moments
• Reaction dynamics on amorphous solid water surfaces using interatomic machine learned potentials. Microscopic energy partition revealed from the P + H -> PH reaction
• Machine Learning and Data-Driven Methods in Computational Surface and Interface Science
• Modeling electronic response properties with an explicit-electron machine learning potential
• Lightweight and Effective Tensor Sensitivity for Atomistic Neural Networks
• Through the eyes of a descriptor: Constructing complete, invertible descriptions of atomic environments
• Kernel based quantum machine learning at record rate : Many-body distribution functionals as compact representations
• A machine learning potential for simulating infrared spectra of nanosilicate clusters
• FeNNol: an Efficient and Flexible Library for Building Force-field-enhanced Neural Network Potentials
• Analytical Gradients for Molecular-Orbital-Based Machine Learning
• In-Depth Exploration of Catalytic Sites on Amorphous Solid Water: I. The Astrosynthesis of Aminomethanol
• Apax: A Flexible and Performant Framework For The Development of Machine-Learned Interatomic Potentials
• CO Adsorption Sites on Interstellar Water Ices Explored with Machine Learning Potentials. Binding energy distributions and snowline
• Breaking scaling relations with inverse catalysts: a machine learning exploration of trends in $\mathrm{C}{\mathrm{O}}_2$ hydrogenation energy barriers
• Diffusive vs. non-diffusive paths to interstellar hydrogen peroxide. A machine learning-based molecular dynamics study
• Neural-Network Assisted Study of Nitrogen Atom Dynamics on Amorphous Solid Water -- II. Diffusion
• REANN: A PyTorch-based End-to-End Multi-functional Deep Neural Network Package for Molecular, Reactive and Periodic Systems
• Graph Convolutional Neural Networks for (QM)ML/MM Molecular Dynamics Simulations