Neural Network Potentials for Chemistry: Concepts, Applications and Prospects

Abstract

Artificial Neural Networks (ANN) are already heavily involved in methods and applications for frequent tasks in the field of computational chemistry such as representation of potential energy surfaces (PES) and spectroscopic predictions. This perspective provides an overview of the foundations of neural network-based full-dimensional potential energy surfaces, their architectures, underlying concepts, their representation and applications to chemical systems. Methods for data generation and training procedures for PES construction are discussed and means for error assessment and refinement through transfer learning are presented. A selection of recent results illustrates the latest improvements regarding accuracy of PES representations and system size limitations in dynamics simulations, but also NN application enabling direct prediction of physical results without dynamics simulations. The aim is to provide an overview for the current state-of-the-art NN approaches in computational chemistry and also to point out the current challenges in enhancing reliability and applicability of NN methods on larger scale.

References in corpus (49)

• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Machine Learning Force Fields
• Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
• Machine learning for molecular simulation
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Machine Learning Unifies the Modelling of Materials and Molecules
• Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems
• Towards Explainable Artificial Intelligence
• A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-local Charge Transfer
• Physics-inspired structural representations for molecules and materials
• Machine learning for electronically excited states of molecules
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• ANI-1: A data set of 20M off-equilibrium DFT calculations for organic molecules
• Higher-Order Explanations of Graph Neural Networks via Relevant Walks
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
• Deep Potentials for Materials Science
• Unsupervised machine learning in atomistic simulations, between predictions and understanding
• Machine Learning in QM/MM Molecular Dynamics Simulations of Condensed-Phase Systems
• $\Delta$-Machine Learning for Potential Energy Surfaces: A PIP approach to bring a DFT-based PES to CCSD(T) Level of Theory
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• QM7-X: A comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules
• Toward Explainable AI for Regression Models
• Training neural nets to learn reactive potential energy surfaces using interactive quantum chemistry in virtual reality
• Gaussian Moments as Physically Inspired Molecular Descriptors for Accurate and Scalable Machine Learning Potentials
• Bayesian machine learning for quantum molecular dynamics
• Breaking the Coupled Cluster Barrier for Machine Learned Potentials of Large Molecules: The Case of 15-atom Acetylacetone
• The Ecological Impact of High-performance Computing in Astrophysics
• Structure, Organization and Heterogeneity of Water-Containing Deep Eutectic Solvents
• Roaming leads to amino acid photodamage: A deep learning study of tyrosine
• Permutationally invariant polynomial regression for energies and gradients, using reverse differentiation, achieves orders of magnitude speed-up with high precision compared to other machine learning methods
• BuRNN: Buffer Region Neural Network Approach for Polarizable-Embedding Neural Network / Molecular Mechanics Simulations
• 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
• The MD17 Datasets from the Perspective of Datasets for Gas-Phase "Small" Molecule Potentials
• Transferability of machine learning potentials: Protonated water neural network potential applied to the protonated water hexamer
• Manifolds of quasi-constant SOAP and ACSF fingerprints and the resulting failure to machine learn four-body interactions
• Training atomic neural networks using fragment-based data generated in virtual reality
• Double Proton Transfer in Hydrated Formic Acid Dimer: Interplay of Spatial Symmetry and Solvent-Generated Force on Reactivity
• Impact of the characteristics of quantum chemical databases on machine learning predictions of tautomerization energies
• Machine Learning Product State Distributions from Initial Reactant States for a Reactive Atom-Diatom Collision System
• Through the eyes of a descriptor: Constructing complete, invertible descriptions of atomic environments
• Prediction uncertainty validation for computational chemists
• Dynamics on Multiple Potential Energy Surfaces: Quantitative Studies of Elementary Processes Relevant to Hypersonics
• Machine Learning for Observables: Reactant to Product State Distributions for Atom-Diatom Collisions
• Wavelet Scattering Networks for Atomistic Systems with Extrapolation of Material Properties
• A Machine Learning Approach for Rate Constants III: Application to the Cl(${}^2$P) + CH${}_4$ $\to$ CH${}_3$ + HCl Reaction
• Rate Constants for Fine-Structure Excitations in O-H Collisions with Error Bars Obtained by Machine Learning

Cited by in corpus (11)

• Lifelong Machine Learning Potentials
• ArcaNN: automated enhanced sampling generation of training sets for chemically reactive machine learning interatomic potentials
• PhysNet Meets CHARMM: A Framework for Routine Machine Learning / Molecular Mechanics Simulations
• Transfer-Learned Potential Energy Surfaces: Towards Microsecond-Scale Molecular Dynamics Simulations in the Gas Phase at CCSD(T) Quality
• CoRe Optimizer: An All-in-One Solution for Machine Learning
• Aqueous Solution Chemistry In Silico and the Role of Data Driven Approaches
• Anticipating the Selectivity of Intramolecular Cyclization Reaction Pathways with Neural Network Potentials
• Hierarchical quantum embedding by machine learning for large molecular assemblies
• Atomistic Simulations of Oxide-Water Interfaces using Machine Learning Potentials
• Lifelong Machine Learning Potentials for Chemical Reaction Network Explorations
• A Simple and Scalable Kernel Density Approach for Reliable Uncertainty Quantification in Atomistic Machine Learning