Unlock the Possibilities: Google DeepMind AI Discovers Thousands of New Materials!

Google DeepMind has achieved a significant milestone by utilizing artificial intelligence (AI) to forecast the composition of over 2 million novel materials. This groundbreaking development has the potential to enhance various practical applications in the near future, according to the company.

In a research paper published Wednesday in the science journal Nature, the Alphabet-owned artificial intelligence company said nearly 400,000 of its hypothetical material models could soon be produced under laboratory conditions.

Potential applications of the research include the manufacture of more efficient batteries, solar panels and computer chips.

Finding and synthesizing new materials can be an expensive and time-consuming process. For example, it took about two decades of research before lithium-ion batteries—used today in everything from phones and laptops to electric vehicles—were made commercially available.

“We hope that major improvements in experimentation, autonomous synthesis, and machine learning models will significantly shorten this 10-20 year timeline to something much more manageable,” said DeepMind researcher Ekin Dogus Cubuk.

DeepMind’s AI was trained by the Materials Project, an international research group founded in 2011 at Lawrence Berkeley National Laboratory that consists of existing research on about 50,000 already known materials.

The company said it is now sharing its data with the research community to accelerate new breakthroughs in materials discovery.

“The industry is usually a bit risky when it comes to cost increases, and new materials usually take a while to become cost-effective,” said materials project manager Kristin Persson.

“If we can make it even smaller, that would be considered a real breakthrough.”

Having used artificial intelligence to predict the stability of these new materials, DeepMind said it is now focusing on predicting how easily they can be synthesized in the lab.