scholarly journals Molecular Dynamics with Neural Network Potentials

2020 ◽  
pp. 233-252 ◽  
Author(s):  
Michael Gastegger ◽  
Philipp Marquetand
Keyword(s):  
Neural Network ◽  
Molecular Dynamics

scholarly journals Ab initio structure and thermodynamics of the RPBE-D3 water/vapor interface by neural-network molecular dynamics

2020 ◽  
Vol 153 (14) ◽  
pp. 144710
Author(s):  
Oliver Wohlfahrt ◽  
Christoph Dellago ◽  
Marcello Sega
Keyword(s):  
Neural Network ◽  
Molecular Dynamics ◽  
Water Vapor ◽  
Ab Initio ◽  
Vapor Interface ◽  
Ab Initio Structure

scholarly journals Iterative training set refinement enables reactive molecular dynamics via machine learned forces

RSC Advances ◽  
2020 ◽  
Vol 10 (8) ◽  
pp. 4293-4299 ◽  
Author(s):  
Lei Chen ◽  
Ivan Sukuba ◽  
Michael Probst ◽  
Alexander Kaiser
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Molecular Dynamics ◽  
Dft Calculations ◽  
High Accuracy ◽  
Iterative Refinement ◽  
Training Set ◽  
Reactive Molecular Dynamics

Reactive self-sputtering from a Be surface is simulated using neural network trained forces with high accuracy. The key in machine learning from DFT calculations is a well-balanced and complete training set of energies and forces obtained by iterative refinement.

scholarly journals Water Dipole and Quadrupole Moment Contributions to the Ion Hydration Free Energy by the Deep Neural Network Trained with Ab Initio Molecular Dynamics Data

2020 ◽  
Author(s):  
YU SHI ◽  
Carrie C. Doyle ◽  
Thomas L. Beck
Keyword(s):  
Neural Network ◽  
Molecular Dynamics ◽  
Free Energy ◽  
Ab Initio ◽  
Deep Neural Network ◽  
Ab Initio Molecular Dynamics ◽  
Quadrupole Moments ◽  
Hydration Free Energy ◽  
Ion Hydration ◽  
Water Dipole

<div>We report a calculation scheme on water molecular dipole and quadrupole moments in the liquid phase through a Deep Neural Network (DNN) model. Employing the the Maximally Localized Wannier Functions (MLWF) for the valence electrons, we obtain the water moments through a post-process on trajectories from \textit{ab-initio} molecular dynamics (AIMD) simulations at the density functional theory (DFT) level. In the framework of the deep potential molecular dynamics (DPMD), we develop a scheme to train a DNN with the AIMD moments data. Applying the model, we calculate the contributions from water dipole and quadrupole moments to the electrostatic potential at the center of a cavity of radius 4.1 \AA\ as -3.87 V, referenced to the average potential in the bulk-like liquid region.</div><div>To unravel the ion-independent water effective local potential contribution to the ion hydration free energy, we estimate the 3rd cumulant term as -0.22 V from simulations totally over 6 ns, a time-scale inaccessible for AIMD calculations. </div>

scholarly journals Development and Application of a Single Neural Network Potential for IRMOF-n (n=1,4,6,7,10)

2021 ◽  
Author(s):  
Omer Tayfuroglu ◽  
Abdul Kadir Kocak ◽  
Yunus Zorlu
Keyword(s):  
Neural Network ◽  
Molecular Dynamics ◽  
Thermal Expansion ◽  
Density Of States ◽  
Mechanical Strain ◽  
Computational Cost ◽  
Negative Thermal Expansion ◽  
Md Simulations ◽  
Ab Initio Molecular Dynamics ◽  
Lattice Constants

Metal‑organic frameworks (MOFs) with their exceptional porous and organized structures have been subject of numerous applications. Predicting macroscopic properties from atomistic simulations require the most accurate force fields, which is still a major problem due to MOFs’ hybrid structures governed by covalent, ionic and dispersion forces. Application of ab‑initio molecular dynamics to such large periodic systems are thus beyond the current computational power. Therefore, alternative strategies must be developed to reduce computational cost without losing reliability. In this work, we describe the construction of a neural network potential (NNP) for IRMOF‑n series (n=1,4,7,10) trained by PBE-D4/def2-TZVP reference data of MOF fragments. We validated the resulting NNP on both fragments and bulk MOF structures by prediction of properties such as equilibrium lattice constants, phonon density of states and linker orientation. The energy and force RMSE values for the fragments are only 0.0017 eV/atom and 0.15 eV/Å, respectively. The NNP predicted equilibrium lattice constants of bulk structures, which are not included in training, are off by only 0.2-2.4% from experimental results. Moreover, our fragment trained NNP greatly predicts phenylene ring torsional energy barrier, equilibrium bond distances and vibrational density of states of bulk MOFs. Furthermore, NNP allows us to investigate unusual behaviors of selected MOFs such as the thermal expansion properties and the effect of mechanical strain on the adsorption of hydrogen and methane molecules. The NNP based molecular dynamics (MD) simulations suggest the IRMOF‑4 and IRMOF‑7 to have positive‑to‑negative thermal expansion coefficients while the rest to have only negative thermal expansion under the studied temperatures of 200 K to 400 K. The deformation of bulk structure by reduction of unit cell volume has shown to increase volumetric methane uptake in IRMOF‑1 but decrease in IRMOF‑7 due to the steric hindrance.

Sign in / Sign up

Export Citation Format

Share Document