Litcius/Paper detail

A Differentiable Neural-Network Force Field for Ionic Liquids

Hadrián Montes‐Campos, Jesús Carrete, Sebastian Bichelmaier, Luis M. Varela, Georg K. H. Madsen

2021Journal of Chemical Information and Modeling60 citationsDOIOpen Access PDF

Abstract

in the forces. We show that encoding the element-specific density in the spherical Bessel descriptors is key to achieving this. Harnessing the information provided by the forces drastically reduces the amount of atomic configurations required to train a neural network force field based on atom-centered descriptors. We choose the Swish-1 activation function and discuss the role of this choice in keeping the neural network differentiable. Furthermore, the possibility of training on small data sets allows for an ensemble-learning approach to the detection of extrapolation. Finally, we find that a separate treatment of long-range interactions is not required to achieve a high-quality representation of the potential energy surface of these dense ionic systems.

Topics & Concepts

Differentiable functionIonic liquidForce field (fiction)Field (mathematics)Artificial neural networkIonic bondingComputer scienceChemistryArtificial intelligenceMathematicsOrganic chemistryIonPure mathematicsCatalysisMachine Learning in Materials ScienceIonic liquids properties and applicationsElectrochemical Analysis and Applications
A Differentiable Neural-Network Force Field for Ionic Liquids | Litcius