What is it about?
New sustainable materials are vital for a greener future, this paper demonstrates the Materials Informatic methodology, using Natural Language Processing (NPL), Machine Learning (ML) and high-throughput experiments to discover new magnetic materials. It demonstrates how NLP can be used to build bespoke databases, which can then be used to train ML algorithms that can predict new magnetic material compositions, which are verified using high throughput experiments.
Featured Image
Photo by Pietro Jeng on Unsplash
Why is it important?
With the aim to achieve net zero by 2030, discovering new materials that are cheaper, greener and more sustainable has become more important within materials research. Unfortunately, traditional material discovery methodologies can take up to 10 years to reach commercialisation, which is too long. Materials informatics offers an opportunity to discover new materials, in a shorter time frame, by using artificial intelligence to make unbiased predictions, that can then be verified quickly using high throughput experiments.
Perspectives
Discovering new magnetic materials, for applications such as electric motor, wind turbines and power electronics is really important for the drive towards net zero. Materials Informatics provides us with the opportunities to discover new compositions, using unbiased digital methods, that could change the world.
Nicola Morley
University of Sheffield
Read the Original
This page is a summary of: Material informatics for functional magnetic material discovery, AIP Advances, January 2024, American Institute of Physics,
DOI: 10.1063/9.0000657.
You can read the full text:
Contributors
The following have contributed to this page
