Machine Learning Potential: A Combination of Reactive Force Field and Message Passing Neural Networks

2021 ◽  
Author(s):  
Liyuan Xue ◽  
Feng Guo ◽  
Yushi Wen ◽  
Shiquan Feng ◽  
Xiaona Huang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Force Field ◽  
Material Properties ◽  
Message Passing ◽  
Field Model ◽  
Reactive Force ◽  
Computational Tool ◽  
Learning Potential ◽  
Reactive Force Field

The Reactive Force Field (ReaxFF) is a powerful computational tool for exploring material properties. In this work, we proposed an enhanced reactive force field model, which using Message Passing Neural...

Defecting controllability of bombarding graphene with different energetic atoms via reactive force field model

2013 ◽  
Vol 114 (5) ◽  
pp. 054313 ◽  
Author(s):  
Xiao Yi Liu ◽  
Feng Chao Wang ◽  
Harold S. Park ◽  
Heng An Wu
Keyword(s):  
Force Field ◽  
Field Model ◽  
Reactive Force ◽  
Reactive Force Field

APT a next generation QM-based reactive force field model

2007 ◽  
Vol 105 (2-3) ◽  
pp. 301-324 ◽  
Author(s):  
A. K. Rappé ◽  
L. M. Bormann-Rochotte ◽  
D. C. Wiser ◽  
J. R. Hart ◽  
M. A. Pietsch ◽  
...  
Keyword(s):  
Force Field ◽  
Field Model ◽  
Reactive Force ◽  
Next Generation ◽  
Reactive Force Field

Intelligent-ReaxFF: Evaluating the reactive force field parameters with machine learning

2020 ◽  
Vol 172 ◽  
pp. 109393 ◽  
Author(s):  
Feng Guo ◽  
Yu-Shi Wen ◽  
Shi-Quan Feng ◽  
Xiao-Dong Li ◽  
Heng-Shuai Li ◽  
...  
Keyword(s):  
Machine Learning ◽  
Force Field ◽  
Reactive Force ◽  
Reactive Force Field ◽  
Force Field Parameters

Optimization of a New Reactive Force Field for Silver - Based Materials

2020 ◽  
Author(s):  
Clément Dulong ◽  
Bruno Madebène ◽  
Susanna Monti ◽  
Johannes Richardi
Keyword(s):  
Force Field ◽  
Self Assembled Monolayers ◽  
The Novel ◽  
Reactive Force ◽  
Reactive Force Field ◽  
Energetic Properties ◽  
Extended Training ◽  
Geometrical Features ◽  
Assembled Monolayers ◽  
Gold Thiolate

<div><div><div><p>A new reactive force field based on the ReaxFF formalism is effectively parametrized against an extended training set of quantum chemistry data (containing more than 120 different structures) to describe accurately silver- and silver-thiolate systems. The results obtained with this novel representation demonstrate that the novel ReaxFF paradigm is a powerful methodology to reproduce more appropriately average geometric and energetic properties of metal clusters and slabs when compared to the earlier ReaxFF parametrizations dealing with silver and gold. ReaxFF cannot describe adequately specific geometrical features such as the observed shorter distances between the under-coordinated atoms at the cluster edges. Geometric and energetic properties of thiolates adsorbed on a silver Ag20 pyramid are correctly represented by the new ReaxFF and compared with results for gold. The simulation of self-assembled monolayers of thiolates on a silver (111) surface does not indicate the formation of staples in contrast to the results for gold-thiolate systems.</p></div></div></div>

scholarly journals Development of a reactive force field for CaCl2·nH2O, and the application to thermochemical energy storage

2021 ◽  
Vol 197 ◽  
pp. 110595
Author(s):  
Koen Heijmans ◽  
Sophie Nab ◽  
Bern Klein Holkenborg ◽  
Amar Deep Pathak ◽  
Silvia Gaastra-Nedea ◽  
...  
Keyword(s):  
Energy Storage ◽  
Force Field ◽  
Reactive Force ◽  
Reactive Force Field
Sign in / Sign up

Export Citation Format

Share Document