Schematic of the cloud environment used for the materials discovery workloads in this study. Credit: arXiv (2024). DOI: 10.48550/arxiv.2401.04070
A team of Microsoft AI researchers working with colleagues at the Pacific Northwest National Laboratory used AI to develop a battery that uses less lithium. Together they published an article describing their work on the arXiv preprint server.
Lithium-ion batteries have become the industry standard for electronic devices and electric vehicles and are expected to play a major role in the conversion to a green electricity grid. But lithium is expensive, which has led several teams around the world to look for alternatives. In this new effort, the research team looked for ways to reduce the amount of lithium used in batteries.
This would normally take a long time – probably several years – due to the comprehensive approach required. To reduce the workload and time needed to process millions of candidates, researchers have turned to AI.
Noting that AI applications are good at using huge amounts of data to learn how to do things, the researchers designed one that could study millions of materials that could be added to a lithium battery to replace a certain amount of lithium and test the results to determine the factors. such as the stability and behavior of a battery using a given material.
Using this approach, the research team was able to narrow the list of possible candidates down to just a few hundred possibilities. They then turned to materials scientists at the Pacific Northwest National Laboratory for advice on how to narrow the possibilities even further. The scientists suggested adding more specific selection criteria and more elimination cycles. After heeding this advice, the team arrived at a promising candidate and an approach that involves replacing about half of a battery’s lithium atoms with sodium atoms.
After building a working battery using the new approach, the researchers found that its conductivity was lower than needed, but they also think there is room for improvement. They plan to continue working on the approach and process they used to find their solution, which they believe could eventually solve other types of materials processing problems.
More information:
Chi Chen et al, Accelerating computational materials discovery through artificial intelligence and high-performance computing in the cloud: from large-scale screening to experimental validation, arXiv (2024). DOI: 10.48550/arxiv.2401.04070
arXiv
© 2024 Science X Network
Quote: Using AI to develop a battery that uses less lithium (January 17, 2024) retrieved January 17, 2024 from
This document is subject to copyright. Except for fair use for private study or research purposes, no part may be reproduced without written permission. The content is provided for information only.
