Predicting Structural Properties of Pure Silica Zeolites Using Deep Neural Network Potentials

23 December 2022, Version 2
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

Machine learning potentials (MLPs) capable of accurately describing complex ab initio potential energy surfaces (PES) have revolutionized the field of multiscale atomistic modeling. In this work, using an extensive density functional theory (DFT) dataset (denoted as Si-ZEO22) consisting of 219 unique zeolite topologies (350,000 unique DFT calculations) found in the International Zeolite Association (IZA) database, we have trained a DeePMD-kit MLP to model the dynamics of silica frameworks. The performance of our model is evaluated by calculating various properties that probe the accuracy of the energy and force predictions. This MLP demonstrates impressive agreement with DFT for predicting zeolite structural properties, energy-volume trends, and phonon density of states. Furthermore, our model achieves reasonable predictions for stress-strain relationships without including DFT stress data during training. These results highlight the ability of MLPs to capture the flexibility of zeolite frameworks and motivates further MLP development for nanoporous materials with near-ab initio accuracy.

Keywords

machine learning potential
zeolites
machine learning force field
silica

Supplementary materials

Title
Description
Actions
Title
Tabulated results and input files
Description
Tabulated results for DFT/DP calculations and training set sizes, the final DP model and corresponding DeePMD-kit training parameter file, VASP INCAR with the DFT parameters used for generating the Si-ZEO22 dataset, and example LAMMPS input and data files.
Actions
Title
DP Hyperparameter tuning
Description
DP hyperparameter tuning learning curves and model architecture cost comparison.
Actions

Supplementary weblinks

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.