Регистрация / Вход
Прислать материал

Applications of Artificial Intellegence in Crystal Structure Prediction

Name
Pavel
Surname
Dolgirev
Scientific organization
MIPT
Academic degree
Bachelor
Position
Master Student
Scientific discipline
Physics & Astronomy
Topic
Applications of Artificial Intellegence in Crystal Structure Prediction
Abstract
We present s new method for a fast, unbiased and accurate representation of interatomic interactions. It is a combination of a neural network and our new approach for pair potential reconstruction. The potential reconstruction method is simple and computationally cheap and gives rich information about interactions in crystals.
In addition, we present a way on how to analyse features that are included for the description of crystal structures. It helpes to find the most important features and as a result it helps to build physically more relevant model.
Keywords
neural networks, global search, USPEX, crystallography
Summary

1. We present our method of potential reconstruction, and show how it can be applied to real system.

2. We combine the method with machine learning, and present results.

3. We explain our ideas how to validate features.