☆ 4.7 Article

Parallel Implementation of Nonadditive Gaussian Process Potentials for Monte Carlo Simulations

JOURNAL OF CHEMICAL THEORY AND COMPUTATION (2023)

Related references

Note: Only part of the references are listed.

Article Chemistry, Physical

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

Paul L. Houston et al.

Summary: Researchers have recently made further improvements to permutationally invariant polynomial (PIP) regression, including compacting purified basis and speeding up gradient evaluation using reverse differentiation method. They found that PIP computation time for energy and force evaluation is significantly faster than other machine-learning methods, and have introduced a new PIP potential energy surface (PES) for ethanol.

JOURNAL OF CHEMICAL PHYSICS (2022)

Add to Collection

Article Chemistry, Physical

REANN: A PyTorch-based end-to-end multi-functional deep neural network package for molecular, reactive, and periodic systems

Yaolong Zhang et al.

Summary: This work introduces a general deep neural network package for representing energies, forces, dipole moments, and polarizabilities of atomistic systems. The package combines physically inspired atomic descriptor based neural networks and message-passing based neural networks to achieve state-of-the-art accuracy, efficiency, scalability, and universality. An interface with LAMMPs is provided for large scale molecular dynamics simulations.

JOURNAL OF CHEMICAL PHYSICS (2022)

Add to Collection

Article Physics, Fluids & Plasmas

Thermodynamic properties of argon from Monte Carlo simulations using ab initio potentials

Philipp Stroeker et al.

Summary: Using semiclassical Monte Carlo simulations and ab initio potentials, ten different thermodynamic properties of argon in the liquid and supercritical regions were obtained. The results show a high level of agreement with experimental data, demonstrating the predictive power of ab initio potentials in molecular modeling and simulation for thermodynamic properties of fluids.

PHYSICAL REVIEW E (2022)

Add to Collection

Article Chemistry, Multidisciplinary

Machine learning for non-additive intermolecular potentials: quantum chemistry to first-principles predictions

Richard S. Graham et al.

Summary: Accurate potential energy surfaces (PES) are required for predicting thermophysical properties from molecular principles. This study presents a widely-applicable method that produces first-principles PES using Gaussian Processes (GP) as a machine learning technique. The method accurately interpolates three-body non-additive interaction data and does not require modification for different molecules. It produces highly accurate interpolation from fewer training points and enables more accurate ab initio calculations. The method is exemplified by computing the PES for CO2-Ar mixtures, which allows for accurate first-principles predictions of various thermophysical properties.

CHEMICAL COMMUNICATIONS (2022)

Add to Collection

Article Chemistry, Physical

Gaussian process models of potential energy surfaces with boundary optimization

Jack Broad et al.

Summary: This paper outlines a strategy to reduce the number of training points required to model intermolecular potentials using Gaussian processes, without compromising accuracy. By using an asymptotic function and learning the crossover distance from training data, the technique successfully reduces the number of training points by up to 49% compared to previous sequential learning methods. The approach can be easily applied to other statistical prediction or modeling problems.

JOURNAL OF CHEMICAL PHYSICS (2021)

Add to Collection

Article Multidisciplinary Sciences

SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects

Oliver T. Unke et al.

Summary: SpookyNet is a deep neural network that addresses the issue of electronic degrees of freedom and nonlocality typically ignored in machine-learned force fields. By incorporating chemically meaningful inductive biases and analytical corrections into the network architecture, SpookyNet can improve performance in quantum chemistry and fill important gaps in machine learning models.

NATURE COMMUNICATIONS (2021)

Add to Collection

Article Chemistry, Physical

Solid-liquid coexistence of neon, argon, krypton, and xenon studied by simulations

Aditya N. Singh et al.

Summary: This paper investigates noble elements neon, argon, krypton, and xenon by molecular dynamics using simplified atomic potentials, yielding insights into properties such as freezing lines and entropy of melting. The study suggests that the body-centered cubic crystal is the thermodynamically stable phase at high pressures.

JOURNAL OF CHEMICAL PHYSICS (2021)

Add to Collection

Article Chemistry, Physical

Interatomic Interactions Responsible for the Solid-Liquid and Vapor-Liquid Phase Equilibria of Neon

Ulrich K. Deiters et al.

Summary: The study investigates the role of interatomic interactions on the solid-liquid and vapor-liquid equilibria of neon using molecular simulation. It is found that a combination of two-body plus quantum influences has the greatest impact on the accuracy of solid-liquid equilibrium prediction. However, a combination of two-body + three-body + quantum interactions is required to approach experimental accuracy for solid-liquid equilibria as well as predict vapor-liquid equilibria to a high degree of accuracy.

JOURNAL OF PHYSICAL CHEMISTRY B (2021)

Add to Collection

Article Chemistry, Physical

Machine learning for interatomic potential models

Tim Mueller et al.

JOURNAL OF CHEMICAL PHYSICS (2020)

Add to Collection

Article Chemistry, Physical

Interpolation and Extrapolation of Global Potential Energy Surfaces for Polyatomic Systems by Gaussian Processes with Composite Kernels

J. Dai et al.

JOURNAL OF CHEMICAL THEORY AND COMPUTATION (2020)

Add to Collection

Article Chemistry, Physical

Performance and Cost Assessment of Machine Learning Interatomic Potentials

Yunxing Zuo et al.

JOURNAL OF PHYSICAL CHEMISTRY A (2020)

Add to Collection

Article Chemistry, Physical

Machine-learned interatomic potentials by active learning: amorphous and liquid hafnium dioxide

Ganesh Sivaraman et al.

NPJ COMPUTATIONAL MATERIALS (2020)

Add to Collection

Article Chemistry, Physical

A Gaussian process regression adaptive density guided approach for potential energy surface construction

Gunnar Schmitz et al.

JOURNAL OF CHEMICAL PHYSICS (2020)

Add to Collection

Article Chemistry, Physical

Creating Gaussian process regression models for molecular simulations using adaptive sampling

Matthew J. Burn et al.

JOURNAL OF CHEMICAL PHYSICS (2020)

Add to Collection

Review Chemistry, Multidisciplinary

Water in Nanopores and Biological Channels: A Molecular Simulation Perspective

Charlotte Lynch et al.

CHEMICAL REVIEWS (2020)

Add to Collection

Article Chemistry, Physical

Gaussian process model of 51-dimensional potential energy surface for protonated imidazole dimer

Hiroki Sugisawa et al.

JOURNAL OF CHEMICAL PHYSICS (2020)

Add to Collection

Article Chemistry, Physical

Machine learning interatomic potential developed for molecular simulations on thermal properties of β-Ga2O3

Yuan-Bin Liu et al.

JOURNAL OF CHEMICAL PHYSICS (2020)

Add to Collection

Article Chemistry, Physical

Random Sampling High Dimensional Model Representation Gaussian Process Regression (RS-HDMR-GPR) for Multivariate Function Representation: Application to Molecular Potential Energy Surfaces

Mohamed Ali Boussaidi et al.

JOURNAL OF PHYSICAL CHEMISTRY A (2020)

Add to Collection

Article Chemistry, Physical

Fully a priori prediction of the vapor-liquid equilibria of Ar, Kr, and Xe from ab initio two-body plus three-body interatomic potentials

Ulrich K. Deiters et al.

JOURNAL OF CHEMICAL PHYSICS (2019)

Add to Collection

Article Chemistry, Physical

Perspective: Ab initio force field methods derived from quantum mechanics

Peng Xu et al.

JOURNAL OF CHEMICAL PHYSICS (2018)

Add to Collection

Article Chemistry, Physical

Neural networks vs Gaussian process regression for representing potential energy surfaces: A comparative study of fit quality and vibrational spectrum accuracy

Aditya Kamath et al.

JOURNAL OF CHEMICAL PHYSICS (2018)

Add to Collection

Article Chemistry, Physical

Building machine learning force fields for nanoclusters

Claudio Zeni et al.

JOURNAL OF CHEMICAL PHYSICS (2018)

Add to Collection

Article Chemistry, Physical

Active learning in Gaussian process interpolation of potential energy surfaces

Elena Uteva et al.

JOURNAL OF CHEMICAL PHYSICS (2018)

Add to Collection

Article Materials Science, Multidisciplinary

Efficient nonparametric n-body force fields from machine learning

Aldo Glielmo et al.

PHYSICAL REVIEW B (2018)

Add to Collection

Article Chemistry, Physical

Interpolation of intermolecular potentials using Gaussian processes

Elena Uteva et al.

JOURNAL OF CHEMICAL PHYSICS (2017)

Add to Collection

Article Materials Science, Multidisciplinary

Accurate interatomic force fields via machine learning with covariant kernels

Aldo Glielmo et al.

PHYSICAL REVIEW B (2017)

Add to Collection

Article Chemistry, Physical

Molecular simulation of the thermophysical properties and phase behaviour of impure CO2 relevant to CCS

Alexander J. Cresswell et al.

FARADAY DISCUSSIONS (2016)

Add to Collection

Article Chemistry, Physical

Perspective: Machine learning potentials for atomistic simulations

Joerg Behler

JOURNAL OF CHEMICAL PHYSICS (2016)

Add to Collection

Editorial Material Multidisciplinary Sciences

CLIMATE SCIENCE Hidden trends in the ocean carbon sink

Tatiana Ilyina

NATURE (2016)

Add to Collection

Article Chemistry, Physical

Molecular simulation of the thermophysical properties and phase behaviour of impure CO2 relevant to CCS

Alexander J. Cresswell et al.

FARADAY DISCUSSIONS (2016)

Add to Collection

Article Chemistry, Multidisciplinary

Accuracy and Tractability of a Kriging Model of Intramolecular Polarizable Multipolar Electrostatics and Its Application to Histidine

Shaun M. Kandathil et al.

JOURNAL OF COMPUTATIONAL CHEMISTRY (2013)

Add to Collection

Article Multidisciplinary Sciences

Selective Gas Transport Through Few-Layered Graphene and Graphene Oxide Membranes

Hyo Won Kim et al.

SCIENCE (2013)

Add to Collection

Article Chemistry, Physical

Polarisable multipolar electrostatics from the machine learning method Kriging: an application to alanine

Matthew J. L. Mills et al.

THEORETICAL CHEMISTRY ACCOUNTS (2012)

Add to Collection

Article Chemistry, Physical

Intramolecular polarisable multipolar electrostatics from the machine learning method Kriging

Matthew J. L. Mills et al.

COMPUTATIONAL AND THEORETICAL CHEMISTRY (2011)

Add to Collection

Article Computer Science, Artificial Intelligence

A Survey on Transfer Learning

Sinno Jialin Pan et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2010)

Add to Collection

Review Chemistry, Physical

Optimal construction of a fast and accurate polarisable water potential based on multipole moments trained by machine learning

Chris M. Handley et al.

PHYSICAL CHEMISTRY CHEMICAL PHYSICS (2009)

Add to Collection

© Peeref 2019-2024. All rights reserved.