Machine learning-driven material discovery, from algorithm to novel material.
Title: Machine learning-driven material discovery, from algorithm to novel material.
SNIC Project: Berzelius-2022-141
Project Type: LiU Berzelius
Principal Investigator: QiChen Xu <qichenx@kth.se>
Affiliation: Kungliga Tekniska högskolan
Duration: 2022-06-27 – 2023-01-01
Classification: 10304
Homepage: https://www.kth.se/
Keywords:

Abstract

The main task of this project is to use state-of-the-art data-driven approaches, including machine learning to perform research that will result in the discovery and development of novel materials primarily focusing on magnetic systems. This planned project is also a sub-project of another two projects and will help explore and design data-mining algorithms to search for novel functional materials with the help of GPUs. Algorithms and approaches that we plan to develop or apply are all based on GPU. This project is a combination of AI and material research.