Science bit: AI looks for better batteries

IFL Science reports about a promising result from the marriage of massive computing power and AI (artificial intelligence) software to see if those two parents could produce something better than what exists today. The marriage produced a baby!:
AI Discovers New Material That Could Slash Lithium Use In Batteries

Great job, AI! Please don't kill us

A new material that could dramatically reduce the amount of lithium used in batteries has been identified by artificial intelligence (AI). Discoveries like this would have taken years in times gone by, but sky-rocketing computer power now means they can be found in days.

The new material was recently sniffed out during a joint venture by Microsoft and the Pacific Northwest National Laboratory (PNNL), which employed the help of advanced AI and high-performance computing (HPC), a type of cloud-based computing that uses large numbers of computers to solve complex scientific and mathematical tasks.

The system analyzed over 32 million potential inorganic materials and, within just 80 hours, it managed to weedle this down to 18 promising candidates that could be used in battery development. Humans then [made and] tested these candidates and discovered one electrolyte that looked particularly promising.



The material is a solid-state electrolyte. It was thought that sodium ions and lithium ions couldn’t be used together in a single solid-state electrolyte system due to their chemical qualities, but the AI system indicated that such a material was possible. When the researchers tested the idea, it turned out to be true.

Since the electrolyte uses both lithium and sodium, as well as some other elements, it reduces the amount of required lithium by as much as 70 percent.
The research paper, Accelerating computational materials discovery with artificial intelligence and cloud high-performance computing: from large-scale screening to experimental validation, describing these results has not yet been peer-reviewed. It is posted here at arXiv, in the computational physics category of materials science. 

The material found to be potentially useful is one in the group having the generic formula 

NaxLi3xYCl6
0

where Na is sodium, Li is lithium, Y is yttrium, Cl is chlorine and x is 1 or 2. In other words, the solid state electrolyte is one of four compounds (NaLiYCl6, Na2LiYCl6, NaLi2YCl6, or Na2Li2YCl6). No, I don't know why they described the material like that. Even patent concerns don’t explain this weird nomenclature.

Q: Does it sound plausible that, as the researchers put it, this research method constitutes an “unprecedented approach of synergistically integrating AI models and cloud high performance computing”?

Common sense (an essentially contested concept) says that someone must have married AI with cloud computing before now for something or another, if not materials science.


By Germaine: Not fully convinced this approach is really unprecedented, but is considering sleuthing the question . . . . consider, consider . . . . nah, not worth it

Sleuthing

Comments

Popular posts from this blog

That Uplifting Tweet You Just Shared? A Russian Troll Sent It

The Nightmare Scenario That Keeps Election Lawyers Up At Night -- And Could Hand Trump A Second Term

Philosophical Question #14 – Lifestyle Choices