Developing Potential Energy Surfaces for Graphene-based 2D-3D Interfaces from Modified High Dimensional Neural Networks for Applications in Energy Storage

TL;DR

This paper develops a modified high-dimensional neural network approach to accurately model potential energy surfaces for graphene-3D material interfaces, aiding energy storage device design.

Contribution

It introduces a modified HDNN method trained on total energies, improving transferability and accuracy for complex heterostructure interfaces with limited data.

Findings

Root mean squared error (RMSE) ranges from 0.01 to 0.45 eV/atom.

Modified HDNN outperforms traditional atomic energy decomposition methods.

Approach enables cost-effective design of stable energy storage interfaces.

Abstract

Mixed-dimensional heterostructures composed of two-dimensional (2D) and three-dimensional (3D) materials are undisputed next-generation materials for engineered devices due to their changeable properties. The present work computationally investigates the interface between 2D graphene and 3D tin (Sn) systems with density functional theory (DFT) method. It uses computationally demanding simulation data to develop machine learning (ML) based potential energy surfaces (PES). The approach to developing PES for complex interface systems in the light of limited data and transferability of such models has been discussed. To develop PES for graphene-tin interface systems, high dimensional neural networks (HDNN) are used that rely on atom-centered symmetry function to represent structural information. HDNN are modified to train on the total energies of the interface system rather than atomic energies. The performance of modified HDNN trained on 5789 interface structures of graphene|Sn is tested on new interfaces of the same material pair with varying levels of structural deviations from the training dataset. Root mean squared error (RMSE) for test interfaces fall in the range of 0.01-0.45 eV/atom, depending on the structural deviations from the reference training dataset. By avoiding incorrect decomposition of total energy into atomic energies, modified HDNN model is shown to obtain higher accuracy and transferability despite limited dataset. Improved accuracy in ML-based modeling approach promises cost-effective means of designing interfaces in heterostructure energy storage systems with higher cycle life and stability.