Learning pair potentials using differentiable simulations
Name
5.0126475.pdf
Description
Published version
Size
16.18 MB
Format
Adobe PDF
Checksum (MD5)
270b29be15ce35972ea79603382b8568
Author(s)
Wang, Wujie
Wu, Zhenghao
Dietschreit, Johannes CB
Gómez-Bombarelli, Rafael
Date Issued
January 28, 2023
Journal
The Journal of Chemical Physics
Publisher
AIP Publishing
Citation
Wang, Wujie, Wu, Zhenghao, Dietschreit, Johannes CB and Gómez-Bombarelli, Rafael. 2023. "Learning pair potentials using differentiable simulations." The Journal of Chemical Physics, 158 (4).
Version
Final published version
Abstract
Learning pair interactions from experimental or simulation data is of great interest for molecular simulations. We propose a general stochastic method for learning pair interactions from data using differentiable simulations (DiffSim). DiffSim defines a loss function based on structural observables, such as the radial distribution function, through molecular dynamics (MD) simulations. The interaction potentials are then learned directly by stochastic gradient descent, using backpropagation to calculate the gradient of the structural loss metric with respect to the interaction potential through the MD simulation. This gradient-based method is flexible and can be configured to simulate and optimize multiple systems simultaneously. For example, it is possible to simultaneously learn potentials for different temperatures or for different compositions. We demonstrate the approach by recovering simple pair potentials, such as Lennard-Jones systems, from radial distribution functions. We find that DiffSim can be used to probe a wider functional space of pair potentials compared with traditional methods like iterative Boltzmann inversion. We show that our methods can be used to simultaneously fit potentials for simulations at different compositions and temperatures to improve the transferability of the learned potentials.
MIT Department
Massachusetts Institute of Technology. Department of Materials Science and Engineering
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1063/5.0126475
