检索结果-南通市图书馆

Bayesian force fields from active learning for simulation of inter-dimensional transformation of stanene

npj Computational Materials 2021年第1期7卷 361-370页

作者： Yu Xie Jonathan Vandermause Lixin Sun Andrea Cepellotti boris kozinsky John A.Paulson School of Engineering and Applied Sciences Harvard UniversityCambridgeMAUSA Robert Bosch LLC Research and Technology CenterCambridgeMAUSA

We present a way to dramatically accelerate Gaussian process models for interatomic force fields based on many-body kernels by mapping both forces and uncertainties onto functions of low-dimensional *** allows for automated active learning of models combining near-quantum accuracy,built-in uncertainty,and constant cost of evaluation that is comparable to classical analytical models,capable of simulating millions of *** this approach,we perform large-scale molecular dynamics simulations of the stability of the stanene *** discover an unusual phase transformation mechanism of 2D stanene,where ripples lead to nucleation of bilayer defects,densification into a disordered multilayer structure,followed by formation of bulk liquid at high temperature or nucleation and growth of the 3D bcc crystal at low *** presented method opens possibilities for rapid development of fast accurate uncertainty-aware models for simulating long-time large-scale dynamics of complex materials.

关键词： transformation dimensional fields

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Uncertainty-aware molecular dynamics from Bayesian active learning for phase transformations and thermal transport in SiC

引用

npj Computational Materials 2023年第1期9卷 2000-2007页

作者： Yu Xie Jonathan Vandermause Senja Ramakers Nakib H.Protik Anders Johansson boris kozinsky John A.Paulson School of Engineering and Applied Sciences Harvard UniversityCambridgeMAUSA Department of Physics Harvard UniversityCambridgeMAUSA Corporate Sector Research and Advance Engineering Robert Bosch GmbHRenningenUSA Interdisciplinary Centre for Advanced Materials Simulation Ruhr-Universität BochumBochumGermany Robert Bosch LLC Research and Technology CenterWatertownMAUSA

Machine learning interatomic force fields are promising for combining high computational efficiency and accuracy in modeling quantum interactions and simulating atomistic *** learning methods have been recently developed to train force fields efficiently and *** them,Bayesian active learning utilizes principled uncertainty quantification to make data acquisition *** this work,we present a general Bayesian active learning workflow,where the force field is constructed from a sparse Gaussian process regression model based on atomic cluster expansion *** circumvent the high computational cost of the sparse Gaussian process uncertainty calculation,we formulate a high-performance approximate mapping of the uncertainty and demonstrate a speedup of several orders of *** demonstrate the autonomous active learning workflow by training a Bayesian force field model for silicon carbide(SiC)polymorphs in only a few days of computer time and show that pressure-induced phase transformations are accurately *** resulting model exhibits close agreement with both ab initio calculations and experimental measurements,and outperforms existing empirical models on vibrational and thermal *** active learning workflow readily generalizes to a wide range of material systems and accelerates their computational understanding.

关键词： computer thermal utilize

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Accurate and scalable graph neural network force field and molecular dynamics with direct force architecture

引用

npj Computational Materials 2021年第1期7卷 650-658页

作者： Cheol Woo Park Mordechai Kornbluth Jonathan Vandermause Chris Wolverton boris kozinsky Jonathan P.Mailoa Robert Bosch Research and Technology Center CambridgeMA 02139USA Northwestern University EvanstonIL 60208USA Harvard School of Engineering and Applied Sciences CambridgeMA 02138USA

Recently,machine learning(ML)has been used to address the computational cost that has been limiting ab initio molecular dynamics(AIMD).Here,we present GNNFF,a graph neural network framework to directly predict atomic forces from automatically extracted features of the local atomic environment that are translationally-invariant,but rotationally-covariant to the coordinate of the *** demonstrate that GNNFF not only achieves high performance in terms of force prediction accuracy and computational speed on various materials systems,but also accurately predicts the forces of a large MD system after being trained on forces obtained from a smaller ***,we use our framework to perform an MD simulation of Li7P3S11,a superionic conductor,and show that resulting Li diffusion coefficient is within 14%of that obtained directly from *** high performance exhibited by GNNFF can be easily generalized to study atomistic level dynamics of other material systems.

关键词： neural AIMD dynamics

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

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

引用

npj Computational Materials 2020年第1期6卷 1502-1512页

作者： Jonathan Vandermause Steven B.Torrisi Simon Batzner Yu Xie Lixin Sun Alexie M.Kolpak boris kozinsky Department of Physics Harvard UniversityCambridgeMA 02138USA John A.Paulson School of Engineering and Applied Sciences Harvard UniversityCambridgeMA 02138USA Center for Computational Engineering Massachusetts Institute of TechnologyCambridgeMA 02139USA Department of Mechanical Engineering Massachusetts Institute of TechnologyCambridgeMA 02139USA Bosch Research CambridgeMA 02139USA

Machine learned force fields typically require manual construction of training sets consisting of thousands of first principles calculations,which can result in low training efficiency and unpredictable errors when applied to structures not represented in the training set of the *** severely limits the practical application of these models in systems with dynamics governed by important rare events,such as chemical reactions and *** present an adaptive Bayesian inference method for automating the training of interpretable,low-dimensional,and multi-element interatomic force fields using structures drawn on the fly from molecular dynamics *** an active learning framework,the internal uncertainty of a Gaussian process regression model is used to decide whether to accept the model prediction or to perform a first principles calculation to augment the training set of the *** method is applied to a range of single-and multi-element systems and shown to achieve a favorable balance of accuracy and computational efficiency,while requiring a minimal amount of ab initio training *** provide a fully opensource implementation of our method,as well as a procedure to map trained models to computationally efficient tabulated force fields.

关键词： fields element typically

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：