google deepmind Artificial Intelligence (AI) has predicted the structures of over two million novel chemical materials, marking a breakthrough in scaling up real-world technologies.
in a scientific paper Issued The AI company reported in Nature on Wednesday, November 29 that nearly 400,000 of its theoretical material designs could soon undergo laboratory testing. Potential uses of the research include the development of batteries, solar panels and computer chips with enhanced performance.
According to the paper, identifying and creating new materials is often expensive and time-consuming. It took nearly two decades of research before lithium-ion batteries – now widely used in devices like phones, laptops and electric vehicles – became commercially accessible.
Akin Dogus Kubek, a research scientist at DeepMind, expressed optimism that advances in experimentation, autonomous synthesis, and machine learning models could significantly shorten the 10 to 20-year-long timeline for materials discovery and synthesis.
The paper shows that the AI developed by DeepMind was trained using data from the Materials Project, an international research consortium founded at Lawrence Berkeley National Laboratory in 2011. The data set included information on approximately 50,000 pre-existing materials.
Connected: After 12 days of unemployment, Sam Altman is officially back at OpenAI
The organization expressed its intention to distribute its data to the research community for the purpose of accelerating additional progress in the field of materials discovery. However, Materials Project director Kristin Persson said in the paper that the industry is cautious about cost increases, and new materials often take time to become cost-effective. According to Persson, shortening this timeline would be the ultimate success.
After employing AI to predict the stability of these novel materials, DeepMind has turned its attention to predicting their synthesizability in laboratory conditions.
magazine: Real AI Use Cases in Crypto, No. 3: Smart Contract Audits and Cybersecurity
