Accelerated Discovery of Two-Dimensional Optoelectronic Octahedral Oxyhalides via High-Throughput Ab Initio Calculations and Machine Learning

TL;DR

This paper presents a combined high-throughput ab initio and machine learning approach to rapidly identify promising two-dimensional octahedral oxyhalides with enhanced optoelectronic properties, overcoming traditional trial-and-error limitations.

Contribution

It introduces a novel machine-learning model trained on density functional data to efficiently screen thousands of 2D oxyhalides for optoelectronic applications.

Findings

Identified several 2D oxyhalides with suitable band gaps and high electron mobility.

Developed a machine-learning model that accelerates materials screening.

Proposed distorted stacked octahedral factors as key features for prediction.

Abstract

Traditional trial-and-error methods are obstacles for large-scale searching of new optoelectronic materials. Here, we introduce a method combining high-throughput ab initio calculations and machine-learning approaches to predict two-dimensional octahedral oxyhalides with improved optoelectronic properties. We develop an effective machine-learning model based on an expansive dataset generated from density functional calculations including the geometric and electronic properties of 300 two-dimensional octahedral oxyhalides. Our model accelerates the screening of potential optoelectronic materials of 5,000 two-dimensional octahedral oxyhalides. The distorted stacked octahedral factors proposed in our model play essential roles in the machine-learning prediction. Several potential two-dimensional optoelectronic octahedral oxyhalides with moderate band gaps, high electron mobilities, and ultrahigh absorbance coefficients are successfully hypothesized.