Exploring New Nitrogen-Rich Compounds: Hybrid First-Principle Calculations and Machine-Learning Algorithms

The third-generation semiconductors have the characteristics of a large bandgap, a high breakdown electric field, a fast electron saturation rate, high-temperature resistance, corrosion resistance, and radiation resistance, making them the preferred core materials and devices for cutting-edge high-t...

Full description

Saved in:
Bibliographic Details
Main Authors: Hang Zhou, Jie Wu, Jiangtao Yang, Qingyang Fan
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Crystals
Subjects:
Online Access:https://www.mdpi.com/2073-4352/15/3/225
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The third-generation semiconductors have the characteristics of a large bandgap, a high breakdown electric field, a fast electron saturation rate, high-temperature resistance, corrosion resistance, and radiation resistance, making them the preferred core materials and devices for cutting-edge high-tech fields, such as mobile communication, new energy vehicles, and smart grids in the future. The III–V compound semiconductors are a typical representative of them. In order to discover and explore new III–V semiconductor materials more efficiently and accurately, this paper adopts a machine-learning method optimized by the beetle algorithm and combined with first-principle calculation verification to efficiently and accurately predict the performance of III–V nitride materials and study their physicochemical properties. This study improved the prediction efficiency of nitrogen-rich III–V semiconductor materials through the combination of machine learning and first principles, providing a new approach for the efficient and accurate prediction of semiconductor materials.
ISSN:2073-4352