Microsoft uses AI to complete 20-year-old material screening task in 80 hours

IT House News on January 10th, Microsoft and Pacific Northwest National Laboratory (PNNL) collaborated to use the power of AI to identify new materials and apply them in batteries, can reduce the use of lithium metal by up to 70% .

Source: Microsoft

Existing lithium batteries are prone to overheating and catching fire, and the extraction process requires large amounts of water and energy, thus having a negative impact on the environment.

Using artificial intelligence, Microsoft and PNNL sifted through 32 million potential materials and narrowed the list down to 23, five of which were known materials, within 80 hours. The team stated that if they had used traditional methods to obtain these materials, the process would have taken more than twenty years.

Krysta Svore, head of the Microsoft Quantum Redmond (QuArC) group at Microsoft Research, said:

We need to compress the next 250 years of chemical materials science into the next 20 years, right? This is because we want to save our planet. As can be seen from these results, the combination of artificial intelligence and high-performance computing can accelerate scientific discovery.

Physical chemist Karl Mueller, director of the PNNL Project Development Office, said:

We have to pay attention to the speed at which we acquire new ideas and new materials, and if we can feel this acceleration, then this will be the key to finding such materials in the future.

IT Home learned from reports that this candidate material is simply called N2116. It is a solid electrolyte with a low risk factor and is not prone to bursting and causing fires.

Pacific Northwest National Laboratory (PNNL) materials scientist Dan Thien Nguyen is assembling a coin cell battery using synthetic solid electrolytes. Image source: Microsoft

Scientists are still studying the remaining 17 potential materials to find the best alternative to lithium metal.

The team also leverages generative artificial intelligence and high-performance computing to make the process easier and faster.

The above is the detailed content of Microsoft uses AI to complete 20-year-old material screening task in 80 hours. For more information, please follow other related articles on the PHP Chinese website!