Simultaneous fitting of a potential-energy surface and its corresponding force fields using feedforward neural networks

2009 ◽  
Vol 130 (13) ◽  
pp. 134101 ◽  
Author(s):  
A. Pukrittayakamee ◽  
M. Malshe ◽  
M. Hagan ◽  
L. M. Raff ◽  
R. Narulkar ◽  
...  
Keyword(s):  
Neural Networks ◽  
Potential Energy ◽  
Potential Energy Surface ◽  
Energy Surface ◽  
Force Fields ◽  
Feedforward Neural Networks ◽  
Simultaneous Fitting

scholarly journals Linear Atomic Cluster Expansion Force Fields for Organic Molecules: beyond RMSE

2021 ◽  
Author(s):  
David Peter Kovacs ◽  
Cas van der Oord ◽  
Jiri Kucera ◽  
Alice Allen ◽  
Daniel Cole ◽  
...  
Keyword(s):  
Potential Energy ◽  
Potential Energy Surface ◽  
Cluster Expansion ◽  
Organic Molecules ◽  
Energy Surface ◽  
Force Fields ◽  
Atomic Cluster ◽  
Symmetric Polynomials ◽  
Benchmark Datasets ◽  
Expansion Force

We demonstrate that fast and accurate linear force fields can be built for molecules using the Atomic Cluster Expansion (ACE) framework. The ACE models parametrize the Potential Energy Surface in terms of body ordered symmetric polynomials making the functional form reminiscent of traditional molecular mechanics force fields. We show that the 4 or 5-body ACE force fields improve on the accuracy of the empirical force fields by up to a factor of 10, reaching the accuracy typical of recently proposed machine learning based approaches. We not only show state of the art accuracy and speed on the widely used MD17 and ISO17 benchmark datasets, but also go beyond RMSE by comparing a number of ML and empirical force fields to ACE on more important tasks such as normal mode prediction, high temperature molecular dynamics, dihedral torsional profile prediction and even bond breaking. We also demonstrate the smoothness, transferability and extrapolation capabilities of ACE on a new challenging benchmark dataset comprising a potential energy surface of a flexible drug-like molecule.

Sign in / Sign up

Export Citation Format

Share Document