Google’s DeepMind has commissioned an AI to research materials. The result dwarfs anything that humans have achieved in this area in the last few centuries. This could particularly advance the battery sector and the computer chip sector.
• Google’s DeepMind discovers 2.2 million new substances
• Some of the materials can be manufactured
• Used in many industries
According to an article in Nature magazine, the research team from Google’s AI subsidiary DeepMind has achieved a breakthrough in the field of materials research. Accordingly, the team developed an AI algorithm that was able to predict the structure of more than two million possible new crystalline materials. “Today, in an article published in Nature, we announce the discovery of 2.2 million new crystals – equivalent to nearly 800 years of knowledge,” the company confirmed in a blog post.
Graph Networks for Materials Exploration reports success
Accordingly, the artificial intelligence, which the researchers gave the name “Graph Networks for Materials Exploration”, discovered around two million potential structures of previously unknown materials within a year, for which there could be numerous possible applications in the future.
The AI tool rated some of the crystals discovered, 380,000 in number, as stable. These are considered “promising candidates for experimental synthesis” and can therefore be produced under laboratory conditions and do not decompose.
Advances in important industries
According to the researchers, among the crystalline materials considered promising by AI are those that bring important advances and “have the potential to develop future transformative technologies, from superconductors to powering supercomputers to batteries “The next generation is enough to increase the efficiency of electric vehicles”.
AI uses data from large database
In order to enable artificial intelligence to solve the task, DeepMind’s AI was fed data from the Materials Project. This data collection contains information on numerous currently known substances and their associated structures. The most promising materials discovered by the AI Graph Networks for Materials Exploration should also be included in the data collection.
AI results faster than human scientists
When it comes to materials research, Google DeepMind’s artificial intelligence has clearly outstripped scientists. “In the past, scientists searched for novel crystal structures by optimizing known crystals or experimenting with new combinations of elements – an expensive trial-and-error process that could take months to produce even limited results,” according to the abstract DeepMind researchers. “GNoME’s discovery of 2.2 million materials would represent approximately 800 years of knowledge and demonstrates an unprecedented scale and level of accuracy in predictions,” DeepMind continued.
Editorial team finanzen.net
Selected leverage products on Alphabet A (ex Google)
With knock-outs, speculative investors can participate disproportionately in price movements. Simply select the lever you want and we will show you suitable open-end products on Alphabet A (ex Google)
The leverage must be between 2 and 20
Advertising