Learning pair potentials using differentiable simulations

Wujie Wang, Zhenghao Wu, Johannes C.B. Dietschreit, Rafael Gómez-Bombarelli*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

12 Citations (Scopus)

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.

Original languageEnglish
Article number044113
JournalJournal of Chemical Physics
Volume158
Issue number4
DOIs
Publication statusPublished - 28 Jan 2023
Externally publishedYes

Fingerprint

Dive into the research topics of 'Learning pair potentials using differentiable simulations'. Together they form a unique fingerprint.

Cite this