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...
Saved in:
| Main Authors: | , , , |
|---|---|
| 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!
|
| 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 |