News

Google’s artificial intelligence predicted the structure of 2 million new substances

DeepMind, a Google-owned startup, has used artificial intelligence to predict the structure of more than two million new substances. It is said that the achievement could soon be used to improve many technologies.

According to the report ReutersDeepMind says it has simulated nearly 400,000 new combinations of materials that can be produced in the lab. The possible applications of these materials include the production of batteries and solar panels and processors with much higher efficiency.

Discovery and synthesis of new materials can be a costly and time-consuming process. For example, it took nearly two decades of research to develop lithium-ion batteries to the point where they are now used to power everything from phones and laptops to car be used electrically.

A DeepMind researcher says: “We hope that major advances in automated testing and simulation of compounds and machine learning models can significantly shorten the 10 to 20-year time frame so that products can reach the commercialization stage more quickly.”

DeepMind’s AI is trained using data from the Materials Project Institute. This international research group was established in 2011 at Lawrence Berkeley National Laboratory. The said data includes information on about 50,000 known substances.

The Materials Project research group has said it will share its data with the research community to help further advances in materials discovery. After using artificial intelligence to predict the stability of new materials, DeepMind said it will now focus on determining how to produce them in the lab.

Source link

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button

Adblock Detected

Please consider supporting us by disabling your ad blocker