In a research paper published in the scientific journal Nature on Wednesday, the AI company owned by Alphabet said that nearly 400,000 of its hypothetical material designs could soon be manufactured under laboratory conditions.
Potential applications of this research include the production of batteries, solar panels, and computer chips with improved performance.
Photo: Reuters
Discovering and synthesizing new materials can be a costly and time-consuming process. For example, it took about two decades of research before lithium-ion batteries – which are now used to power everything from phones and laptops to electric vehicles – were brought to market.
"We expect that major improvements in experimentation, automated synthesis, and machine learning modeling will significantly shorten that 10- to 20-year timeframe to a much more accessible level," said Ekin Dogus Cubuk, a research scientist at DeepMind.
DeepMind's AI is trained on data from the Materials Project, an international research group established at Lawrence Berkeley National Laboratory in 2011, which includes existing research on approximately 50,000 known materials.
The company said it will now share its data with the research community in the hope of driving further breakthroughs in materials discovery .
After using AI to predict the stability of these new materials, DeepMind says it will now shift its focus to assessing how difficult or easy it will be to synthesize them in the laboratory.
Mai Anh (according to Reuters)
Source
Comment (0)