☆ 4.6 Article

Exploring the robust extrapolation of high-dimensional machine learning potentials

PHYSICAL REVIEW B (2022)

Related references

Note: Only part of the references are listed.

Article Computer Science, Interdisciplinary Applications

Atomic cluster expansion: Completeness, efficiency and stability

Genevieve Dusson et al.

Summary: This study proposes an atomic cluster expansion method that uses a precomputation algorithm to obtain a complete set of basis functions and a fast recursive algorithm for efficient evaluation. It also discusses the challenges of basis optimization and parameter estimation in order to comprehensively analyze convergence to a high-fidelity reference model.

JOURNAL OF COMPUTATIONAL PHYSICS (2022)

Add to Collection

Article Chemistry, Physical

Training algorithm matters for the performance of neural network potential: A case study of Adam and the Kalman filter optimizers

Yunqi Shao et al.

Summary: This article compares the performance of two popular training algorithms for neural network potentials on liquid water datasets, finding that NNPs trained with the extended Kalman filter algorithm (EKF) are more transferable and less sensitive to the learning rate. The study also shows that error metrics of the validation set may not accurately reflect the actual performance of NNPs, with a Fisher information based similarity measure serving as a better indicator instead.

JOURNAL OF CHEMICAL PHYSICS (2021)

Add to Collection

Review Chemistry, Multidisciplinary

Machine Learning Force Fields

Oliver T. Unke et al.

Summary: The use of machine learning in computational chemistry has led to significant advancements, particularly in the development of machine learning-based force fields to bridge the gap between accuracy and efficiency. The key concept is to learn the statistical relations between chemical structure and potential energy, without preconceived notions of fixed bonds. Challenges remain for the next generation of machine learning force fields.

CHEMICAL REVIEWS (2021)

Add to Collection

Article Chemistry, Physical

Uncertainty estimation for molecular dynamics and sampling

Giulio Imbalzano et al.

Summary: Machine-learning models are an effective strategy to bypass time-consuming electronic-structure calculations and enable accurate simulations of larger scale and complexity. Uncertainty quantification plays a crucial role in improving the accuracy and resilience of simulations, and can be applied to different types of structural and thermodynamic properties across diverse systems.

JOURNAL OF CHEMICAL PHYSICS (2021)

Add to Collection

Article Chemistry, Physical

Statistically unbiased free energy estimates from biased simulations

Matteo Carli et al.

Summary: This study introduces a new method to estimate free energy as a function of multiple collective variables, removing bias in the simulation, and validates its accuracy on model systems and a small peptide. The results show that the free energy obtained using this approach is an unbiased estimator of the ground-truth free energy, with errors predicted by the model.

MOLECULAR PHYSICS (2021)

Add to Collection

Article Multidisciplinary Sciences

Data-driven simulation and characterisation of gold nanoparticle melting

ClaudioW Zeni et al.

Summary: Efficient theoretical methods for the structural analysis of nanoparticles are crucial, and this study demonstrates the use of machine-learning force fields and a data-driven approach to investigate the thermodynamic stability and melting process of gold nanoparticles. By developing machine learning force fields based on Density Functional Theory calculations, the study accurately predicts nanoparticle melting temperatures and characterizes the solid-liquid phase change mechanism.

NATURE COMMUNICATIONS (2021)

Add to Collection

Review Chemistry, Multidisciplinary

Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems

John A. Keith et al.

Summary: The article discusses the potential impact of machine learning models on chemical sciences and emphasizes the importance of collaboration between expertise in computer science and physical sciences. It provides concise tutorials of computational chemistry and machine learning methods, and demonstrates how they can be used together to provide insightful predictions.

CHEMICAL REVIEWS (2021)

Add to Collection

Review Chemistry, Multidisciplinary

Physics-Inspired Structural Representations for Molecules and Materials

Felix Musil et al.

Summary: This review summarizes the current understanding of the nature and characteristics of the most commonly used structural and chemical descriptions of atomistic structures, emphasizing the deep underlying connections between different frameworks that lead to computationally efficient and universally applicable models. It provides examples of recent applications to a diverse set of chemical and materials science problems, and outlines the open questions and the most promising research directions in the field.

CHEMICAL REVIEWS (2021)

Add to Collection

Review Chemistry, Multidisciplinary

Gaussian Process Regression for Materials and Molecules

Volker L. Deringer et al.

Summary: This paper introduces the application of Gaussian process regression machine learning in computational materials science and chemistry, focusing on the regression of atomistic properties, including the construction of interatomic potentials, force fields, and fitting of various quantities. Methodological aspects of reference data generation, representation, regression, and model validation are reviewed, along with a survey of applications in chemistry and materials science and an outline of future development vision.

CHEMICAL REVIEWS (2021)

Add to Collection

Article Chemistry, Physical

Compact atomic descriptors enable accurate predictions via linear models

Claudio Zeni et al.

Summary: The study shows that a simple linear regression framework performs comparably with advanced machine learning methods in predicting formation energies and atomic forces, while also achieving improved computational efficiency. By utilizing principal component analysis and least absolute shrinkage operator regression, it is possible to construct descriptors that are significantly smaller yet maintain similar or improved accuracy, with shared features across multiple datasets.

JOURNAL OF CHEMICAL PHYSICS (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

DScribe: Library of descriptors for machine learning in materials science

Lauri Himanen et al.

COMPUTER PHYSICS COMMUNICATIONS (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

On-the-fly active learning of interpretable Bayesian force fields for atomistic rare events

Jonathan Vandermause et al.

NPJ COMPUTATIONAL MATERIALS (2020)

Add to Collection

Article Chemistry, Physical

Simulating Solvation and Acidity in Complex Mixtures with First-Principles Accuracy: The Case of CH3SO3H and H2O2 in Phenol

Kevin Rossi et al.

JOURNAL OF CHEMICAL THEORY AND COMPUTATION (2020)

Add to Collection

Article Chemistry, Physical

An entropy-maximization approach to automated training set generation for interatomic potentials

Mariia Karabin et al.

JOURNAL OF CHEMICAL PHYSICS (2020)

Add to Collection

Editorial Material Multidisciplinary Sciences

Machine learning for chemical discovery

Alexandre Tkatchenko

NATURE COMMUNICATIONS (2020)

Add to Collection

Article Multidisciplinary Sciences

Liquid water contains the building blocks of diverse ice phases

Bartomeu Monserrat et al.

NATURE COMMUNICATIONS (2020)

Add to Collection

Article Computer Science, Interdisciplinary Applications

sGDML: Constructing accurate and data efficient molecular force fields using machine learning

Stefan Chmiela et al.

COMPUTER PHYSICS COMMUNICATIONS (2019)

Add to Collection

Article Chemistry, Physical

Library-Based LAMMPS Implementation of High-Dimensional Neural Network Potentials

Andreas Singraber et al.

JOURNAL OF CHEMICAL THEORY AND COMPUTATION (2019)

Add to Collection

Article Chemistry, Physical

Atom-density representations for machine learning

Michael J. Willatt et al.

JOURNAL OF CHEMICAL PHYSICS (2019)

Add to Collection

Article Chemistry, Physical

De novo exploration and self-guided learning of potential-energy surfaces

Noam Bernstein et al.

NPJ COMPUTATIONAL MATERIALS (2019)

Add to Collection

Article Multidisciplinary Sciences

Ab initio thermodynamics of liquid and solid water

Bingqing Cheng et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2019)

Add to Collection

Article Chemistry, Physical

A Bayesian approach to NMR crystal structure determination

Edgar A. Engel et al.

PHYSICAL CHEMISTRY CHEMICAL PHYSICS (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

A fast neural network approach for direct covariant forces prediction in complex multi-element extended systems

Jonathan P. Mailoa et al.

NATURE MACHINE INTELLIGENCE (2019)

Add to Collection

Review Physics, Multidisciplinary

On machine learning force fields for metallic nanoparticles

Claudio Zeni et al.

ADVANCES IN PHYSICS-X (2019)

Add to Collection

Article Chemistry, Physical

SchNet - A deep learning architecture for molecules and materials

K. T. Schuett et al.

JOURNAL OF CHEMICAL PHYSICS (2018)

Add to Collection

Article Chemistry, Physical

Comparison of permutationally invariant polynomials, neural networks, and Gaussian approximation potentials in representing water interactions through many-body expansions

Thuong T. Nguyen et al.

JOURNAL OF CHEMICAL PHYSICS (2018)

Add to Collection

Article Chemistry, Physical

Computing the Free Energy without Collective Variables

Alex Rodriguez et al.

JOURNAL OF CHEMICAL THEORY AND COMPUTATION (2018)

Add to Collection

Article Physics, Multidisciplinary

Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties

Tian Xie et al.

PHYSICAL REVIEW LETTERS (2018)

Add to Collection

Article Multidisciplinary Sciences

Mapping uncharted territory in ice from zeolite networks to ice structures

Edgar A. Engel et al.

NATURE COMMUNICATIONS (2018)

Add to Collection

Article Materials Science, Multidisciplinary

Generalized convex hull construction for materials discovery

Andrea Anelli et al.

PHYSICAL REVIEW MATERIALS (2018)

Add to Collection

Article Multidisciplinary Sciences

Machine learning unifies the modeling of materials and molecules

Albert P. Bartok et al.

SCIENCE ADVANCES (2017)

Add to Collection

Article Multidisciplinary Sciences

Estimating the intrinsic dimension of datasets by a minimal neighborhood information

Elena Facco et al.

SCIENTIFIC REPORTS (2017)

Add to Collection

Article Materials Science, Multidisciplinary

Active learning of linearly parametrized interatomic potentials

Evgeny V. Podryabinkin et al.

COMPUTATIONAL MATERIALS SCIENCE (2017)

Add to Collection

Article Mathematics, Interdisciplinary Applications

MOMENT TENSOR POTENTIALS: A CLASS OF SYSTEMATICALLY IMPROVABLE INTERATOMIC POTENTIALS

Alexander V. Shapeev

MULTISCALE MODELING & SIMULATION (2016)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials

A. P. Thompson et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2015)

Add to Collection

Article Physics, Multidisciplinary

Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning

Matthias Rupp et al.

PHYSICAL REVIEW LETTERS (2012)

Add to Collection

Article Physics, Multidisciplinary

Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons

Albert P. Bartok et al.

PHYSICAL REVIEW LETTERS (2010)

Add to Collection

Article Physics, Multidisciplinary

Generalized neural-network representation of high-dimensional potential-energy surfaces

Joerg Behler et al.

PHYSICAL REVIEW LETTERS (2007)

Add to Collection

© Peeref 2019-2024. All rights reserved.