Google DeepMind AI reveals thousands of new material possibilities. Google DeepMind utilised artificial intelligence (AI) to forecast the structure of over 2 million new materials, a discovery that might soon be applied to improve real-world technology, according to the company.
Google DeepMind AI reveals thousands of new material possibilities
The Alphabet-owned AI business stated in a research report published in the science magazine Nature on Wednesday that nearly 400,000 of its hypothetical material designs may soon be created in lab conditions.
The discovery could lead to the development of better-performing batteries, solar panels, and computer chips.
The development and production of novel materials can be a time-consuming and expensive process. For example, it took nearly two decades of research to commercialise lithium-ion batteries, which are now used to power everything from phones and laptops to electric vehicles.
“We’re hoping that big improvements in experimentation, autonomous synthesis, and machine learning models will significantly shorten that 10 to 20-year timeline to something that’s much more manageable,” said Ekin Dogus Cubuk, a DeepMind research scientist.
DeepMind’s AI was taught using data from the Materials Project, an international research collaboration created in 2011 at the Lawrence Berkeley National Laboratory that consists of existing research on about 50,000 known materials.
The company announced that it would now share its data with the research community to hasten further advances in material discovery.
“Industry tends to be a little risk-averse when it comes to cost increases, and new materials typically take a bit of time before they become cost-effective,” said Kristin Persson, head of the Materials Project.
“If we can shrink that even a bit more, it would be considered a real breakthrough.”
DeepMind said that after using AI to forecast the stability of these novel materials, it would now focus on predicting how readily they can be synthesised in the lab.