{"id":7868,"date":"2023-11-29T18:16:05","date_gmt":"2023-11-29T18:16:05","guid":{"rendered":"https:\/\/dailyai.com\/?p=7868"},"modified":"2023-11-29T21:24:34","modified_gmt":"2023-11-29T21:24:34","slug":"deepminds-gnome-system-discovered-millions-of-new-materials","status":"publish","type":"post","link":"https:\/\/dailyai.com\/de\/2023\/11\/deepminds-gnome-system-discovered-millions-of-new-materials\/","title":{"rendered":"Das GNoME-System von DeepMind entdeckte Millionen von neuen Materialien"},"content":{"rendered":"

Google DeepMind’s AI platform, Graphical Networks for Material Exploration (GNoME), has predicted the existence of over 2 million new materials, of which 700 have been sent for lab synthesis and further testing.\u00a0<\/b><\/p>\n

Dogus Cubuk, the materials discovery lead at Google DeepMind, explained the purpose of the study, <\/span>which is published in Nature<\/span><\/a>; \u201cWhile materials play a very critical role in almost any technology, we as humanity know only a few tens of thousands of stable materials.\u201d<\/span><\/p>\n

GNoME operates similarly to DeepMind’s AlphaFold system<\/a> for protein folding, which has revolutionized biological research and drug discovery. <\/span><\/p>\n

The AI tool employs two deep-learning models to generate and evaluate billions of potential material structures, including 421,000 stable materials.<\/span><\/p>\n

\"DeepMind
GNoME discovered many times more materials than collective research has identified to date. Source: DeepMind<\/a>.<\/figcaption><\/figure>\n

As part of the study, DeepMind, in partnership with Lawrence Berkeley National Laboratory, has developed an <\/span>autonomous laboratory<\/span><\/a> known as A-Lab. It leverages GNoME\u2019s discoveries, integrating robotics with machine learning to develop the new materials identified by GNoME.\u00a0<\/span><\/p>\n

Kristin Persson at Berkeley Lab explained how GNoME accelerates the research process: \u201cIf you\u2019re unlucky, it can take months or even years [to make materials]. But the A-Lab doesn\u2019t mind failing. It keeps trying and trying.\u201d<\/span><\/p>\n

In terms of practical uses, A-Lab might discover materials usable in clean energy, computing, and other high-tech industries.<\/span><\/p>\n

More about the studies\u00a0<\/span><\/h2>\n

Traditional approaches to material discovery involve scientists manually combining elements from the periodic table, often modifying existing structures to discover new ones.\u00a0<\/span><\/p>\n

This is extremely time-consuming and inefficient due to the vast number of possible combinations and limited ability to predict success rates at scale.\u00a0<\/span><\/p>\n

DeepMind applies machine learning to this process, enabling the iterative discovery and testing of millions of compounds.\u00a0<\/span><\/p>\n