scholarly journals Machine Learning Classical Interatomic Potentials for Molecular Dynamics from First-Principles Training Data

2019 ◽  
Vol 123 (12) ◽  
pp. 6941-6957 ◽  
Author(s):  
Henry Chan ◽  
Badri Narayanan ◽  
Mathew J. Cherukara ◽  
Fatih G. Sen ◽  
Kiran Sasikumar ◽  
...  
Keyword(s):  
Machine Learning ◽  
Molecular Dynamics ◽  
First Principles ◽  
Training Data ◽  
Interatomic Potentials

Machine Learning Interatomic Potentials for Global Optimization and Molecular Dynamics Simulation

2019 ◽  
pp. 253-288 ◽  
Author(s):  
Ivan A. Kruglov ◽  
Pavel E. Dolgirev ◽  
Artem R. Oganov ◽  
Arslan B. Mazitov ◽  
Sergey N. Pozdnyakov ◽  
...  
Keyword(s):  
Machine Learning ◽  
Molecular Dynamics ◽  
Global Optimization ◽  
Molecular Dynamics Simulation ◽  
Dynamics Simulation ◽  
Interatomic Potentials

scholarly journals Teaching a Neural Network to Attach and Detach Electrons from Molecules

2021 ◽  
Author(s):  
Roman Zubatyuk ◽  
Justin Smith ◽  
Benjamin T. Nebgen ◽  
Sergei Tretiak ◽  
Olexandr Isayev
Keyword(s):  
Machine Learning ◽  
Density Functional ◽  
Organic Molecules ◽  
Chemical Elements ◽  
Chemical Reactivity ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
Electrophilic Aromatic Substitution ◽  
Interatomic Potentials ◽  
Conceptual Density Functional Theory

<p></p><p>Physics-inspired Artificial Intelligence (AI) is at the forefront of methods development in molecular modeling and computational chemistry. In particular, interatomic potentials derived with Machine Learning algorithms such as Deep Neural Networks (DNNs), achieve the accuracy of high-fidelity quantum mechanical (QM) methods in areas traditionally dominated by empirical force fields and allow performing massive simulations. The applicability domain of DNN potentials is usually limited by the type of training data. As such, transferable models are aimed to be extensible in the description of chemical and conformational diversity of organic molecules. However, most DNN potentials, such as the AIMNet model we proposed previously, were parametrized for neutral molecules or closed-shell ions due to architectural limitations. In this work, we extend machine learning framework toward open-shell anions and cations. We introduce AIMNet-NSE (Neural Spin Equilibration) architecture, which being properly trained, could predict atomic and molecular properties for an arbitrary combination of molecular charge and spin multiplicity. This model explores a new dimension of transferability by adding the charge-spin space. The AIMNet-NSE model is capable of reproducing reference QM energies for cations, neutrals, and anions with errors of about 2-3 kcal/mol, compared to the reference QM simulations. The spin-charges have errors ~0.01 electrons for small organic molecules containing nine chemical elements {H, C, N, O, F, Si, P, S and Cl}. <a>The AIMNet-NSE model allows to fully bypass QM calculations and derive the ionization potential, electron affinity, and conceptual Density Functional Theory quantities like electronegativity, hardness, and condensed Fukui functions with a speed up to 10<sup>4</sup> molecules per second on a single modern GPU.</a> We show that these descriptors, along with learned atomic representations, could be used to model chemical reactivity through an example of regioselectivity in electrophilic aromatic substitution reactions.</p><p></p>

scholarly journals First‐Principles Multiscale Modeling of Mechanical Properties in Graphene/Borophene Heterostructures Empowered by Machine‐Learning Interatomic Potentials

2021 ◽  
pp. 2102807
Author(s):  
Bohayra Mortazavi ◽  
Mohammad Silani ◽  
Evgeny V. Podryabinkin ◽  
Timon Rabczuk ◽  
Xiaoying Zhuang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Mechanical Properties ◽  
Multiscale Modeling ◽  
First Principles ◽  
Interatomic Potentials

scholarly journals Density Functionals with Quantum Chemical Accuracy: From Machine Learning to Molecular Dynamics

2019 ◽  
Author(s):  
Mihail Bogojeski ◽  
Leslie Vogt-Maranto ◽  
Mark E. Tuckerman ◽  
Klaus-Robert Mueller ◽  
Kieron Burke
Keyword(s):  
Machine Learning ◽  
Molecular Dynamics ◽  
Quantum Chemical ◽  
Density Functional ◽  
Md Simulations ◽  
Training Data ◽  
Coupled Cluster ◽  
Density Functionals ◽  
Cluster Accuracy ◽  
Single Water Molecule

<div> <div> <div> <p>Kohn-Sham density functional theory (DFT) is a standard tool in most branches of chemistry, but accuracies for many molecules are limited to 2-3 kcal/mol with presently-available functionals. <i>Ab initio </i>methods, such as coupled-cluster, routinely produce much higher accuracy, but computational costs limit their application to small molecules. We create density functionals from coupled-cluster energies, based only on DFT densities, via machine learning. These functionals attain quantum chemical accuracy (errors below 1 kcal/mol). Moreover, density-based ∆-learning (learning only the correction to a standard DFT calculation, ∆-DFT) significantly reduces the amount of training data required. We demonstrate these concepts for a single water molecule, and then illustrate how to include molecular symmetries with ethanol. Finally, we highlight the robustness of ∆-DFT by correcting DFT simulations of resorcinol on the fly to obtain molecular dynamics (MD) trajectories with coupled-cluster accuracy. Thus ∆-DFT opens the door to running gas-phase MD simulations with quantum chemical accuracy, even for strained geometries and conformer changes where standard DFT is quantitatively incorrect. </p> </div> </div> </div>

scholarly journals Machine-learning interatomic potentials enable first-principles multiscale modeling of lattice thermal conductivity in graphene/borophene heterostructures

2020 ◽  
Vol 7 (9) ◽  
pp. 2359-2367 ◽  
Author(s):  
Bohayra Mortazavi ◽  
Evgeny V. Podryabinkin ◽  
Stephan Roche ◽  
Timon Rabczuk ◽  
Xiaoying Zhuang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Thermal Conductivity ◽  
Multiscale Modeling ◽  
First Principles ◽  
Lattice Thermal Conductivity ◽  
Interatomic Potentials ◽  
The Continuum

We highlight that machine-learning interatomic potentials trained over short AIMD trajectories enable first-principles multiscale modeling, bridging DFT level accuracy to the continuum level and empowering the study of complex/novel nanostructures.

scholarly journals Metadynamics sampling in atomic environment space for collecting training data for machine learning potentials

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Dongsun Yoo ◽  
Jisu Jung ◽  
Wonseok Jeong ◽  
Seungwu Han
Keyword(s):  
Machine Learning ◽  
Sampling Method ◽  
Local Environment ◽  
Training Data ◽  
Interatomic Potentials ◽  
Mathematical Form ◽  
Training Set ◽  
Large Pool ◽  
Automatic Sampling ◽  
Proper Training

AbstractThe universal mathematical form of machine-learning potentials (MLPs) shifts the core of development of interatomic potentials to collecting proper training data. Ideally, the training set should encompass diverse local atomic environments but conventional approaches are prone to sampling similar configurations repeatedly, mainly due to the Boltzmann statistics. As such, practitioners handpick a large pool of distinct configurations manually, stretching the development period significantly. To overcome this hurdle, methods are being proposed that automatically generate training data. Herein, we suggest a sampling method optimized for gathering diverse yet relevant configurations semi-automatically. This is achieved by applying the metadynamics with the descriptor for the local atomic environment as a collective variable. As a result, the simulation is automatically steered toward unvisited local environment space such that each atom experiences diverse chemical environments without redundancy. We apply the proposed metadynamics sampling to H:Pt(111), GeTe, and Si systems. Throughout these examples, a small number of metadynamics trajectories can provide reference structures necessary for training high-fidelity MLPs. By proposing a semi-automatic sampling method tuned for MLPs, the present work paves the way to wider applications of MLPs to many challenging applications.

scholarly journals Short range order and network connectivity in amorphous AsTe3: a first principles, machine learning, and XRD study

2020 ◽  
Vol 22 (43) ◽  
pp. 24895-24906
Author(s):  
Gaëlle Delaizir ◽  
Andrea Piarristeguy ◽  
Annie Pradel ◽  
Olivier Masson ◽  
Assil Bouzid
Keyword(s):  
Machine Learning ◽  
First Principles ◽  
Short Range ◽  
Structural Models ◽  
Network Connectivity ◽  
Atomic Scale ◽  
Interatomic Potentials ◽  
X Ray Diffraction ◽  
X Ray ◽  
Xrd Study

The atomic scale structure of amorphous AsTe3 is investigated through coupling X-ray diffraction, and realistic structural models issued from ab initio molecular dynamics and machine learning based interatomic potentials.

scholarly journals Accelerating first-principles estimation of thermal conductivity by machine-learning interatomic potentials: A MTP/ShengBTE solution

2021 ◽  
Vol 258 ◽  
pp. 107583 ◽  
Author(s):  
Bohayra Mortazavi ◽  
Evgeny V. Podryabinkin ◽  
Ivan S. Novikov ◽  
Timon Rabczuk ◽  
Xiaoying Zhuang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Thermal Conductivity ◽  
First Principles ◽  
Interatomic Potentials

scholarly journals Automated calculation of thermal rate coefficients using ring polymer molecular dynamics and machine-learning interatomic potentials with active learning

2018 ◽  
Vol 20 (46) ◽  
pp. 29503-29512 ◽  
Author(s):  
I. S. Novikov ◽  
Y. V. Suleimanov ◽  
A. V. Shapeev
Keyword(s):  
Machine Learning ◽  
Molecular Dynamics ◽  
Active Learning ◽  
Gas Phase ◽  
Chemical Reactions ◽  
Rate Coefficients ◽  
Interatomic Potentials ◽  
Ring Polymer ◽  
Ring Polymer Molecular Dynamics ◽  
Phase Chemical

We propose a methodology for the fully automated calculation of thermal rate coefficients of gas phase chemical reactions, which is based on combining ring polymer molecular dynamics (RPMD) and machine-learning interatomic potentials actively learning on-the-fly.

Sign in / Sign up

Export Citation Format

Share Document