Applications of machine learning to high temperature and high pressure environments: A literature review
In recent years, machine learning as a new style of calculation has been developed quickly, and because it can obtain results that experiments cannot achieve, it has become a useful calculation tool in the field of high temperature and high pressure (HTHP). It can simulate and calculate the experime...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2024-12-01
|
| Series: | APL Machine Learning |
| Online Access: | http://dx.doi.org/10.1063/5.0233409 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In recent years, machine learning as a new style of calculation has been developed quickly, and because it can obtain results that experiments cannot achieve, it has become a useful calculation tool in the field of high temperature and high pressure (HTHP). It can simulate and calculate the experimental results according to some calculation principles, such as first-principles, and execute prediction based on models created, such as Gaussian approximation potential, to obtain high-precision results. In addition, its simulation process is very fast, and the cost is not as expensive as that of density functional theory, so machine learning in the field of HTHP computing has aroused great research interest. The rapid development of machine learning makes it a powerful tool to predict some parameter or mechanism of materials and brings a new chance to simulate more complex experimental environments. In this paper, we review some of the most recent applications and insights into machine learning techniques in the fields of mechanics, thermology, electricity, and structural search under the demanding conditions of HTHP. |
|---|---|
| ISSN: | 2770-9019 |