Equivariant Neural Networks Utilizing Molecular Clusters for Accurate Molecular Crystal Binding Energy Predictions

01 December 2023, Version 1
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

Equivariant neural networks have emerged as prominent models in advancing the construction of interatomic potentials due to their remarkable data efficiency and generalization capabilities for out-of-distribution data. Here, we expand the utility of these networks to the prediction of crystal structures consisting of organic molecules. Traditional methods for computing crystal structure properties, such as plane-wave quantum chemical methods based on density functional theory (DFT), are prohibitively resource-intensive, often necessitating compromises in accuracy and the choice of exchange-correlation functional. We present an approach that leverages the efficiency, and transferability of equivariant neural networks, specifically Allegro, to predict molecular crystal structure energies at a reduced computational cost. Our neural network is trained on molecular clusters using a highly accurate Gaussian-type orbital (GTO)-based method as the target level of theory, eliminating the need for costly periodic DFT calculations, while providing access to all families of exchange-corelation functionals and post-Hartree Fock methods. The trained model exhibits remarkable accuracy in predicting binding energies, aligning closely with those computed by plane-wave based DFT methods, thus representing significant cost reductions. Furthermore, the Allegro network was seamlessly integrated with the USPEX framework, accelerating the discovery of low-energy crystal structures during crystal structure prediction.

Keywords

Crystal Structure Prediction
Equivariant Neural Networks
Density Functional Theory
Allegro

Supplementary materials

Title
Description
Actions
Title
Manuscript Supporting Information
Description
Parity plot comparing the binding energy predictions from Delta-ML using PBE-D3BJ and B3LYP-D4 methods. Illustration of an alternate conformation of the tetraamine molecule. Table detailing the training and validation errors for the models tested.
Actions

Comments

Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.