Structural phase transition of two-dimensional monolayer SnTe from artificial neural network

TL;DR

This paper demonstrates how artificial neural networks can be trained to predict energy changes in ferroelectric materials, enabling efficient simulation of phase transitions in two-dimensional monolayer SnTe.

Contribution

It introduces a neural network-based approach for modeling phase transitions in ferroelectric materials, which can be transferred to other materials with available training data.

Findings

Successfully predicted phase transition temperature of monolayer SnTe.

Validated neural network approach against Monte Carlo simulations.

Showed transferability of the neural network model to other ferroelectric materials.

Abstract

As machine learning becomes increasingly important in engineering and science, it is inevitable that machine learning techniques will be applied to the investigation of materials, and in particular the structural phase transitions common in ferroelectric materials. Here, we build and train an artificial neural network to accurately predict the energy change associated with atom displacements and use the trained artificial neural network in Monte-Carlo simulations on ferroelectric materials to investigate their phase transitions. We apply this approach to two-dimensional monolayer SnTe and show that it can indeed be used to simulate the phase transitions and predict the transition temperature. The artificial neural network, when viewed as a universal mathematical structure, can be readily transferred to the investigation of other ferroelectric materials when training data generated with ab initio methods are available.