Post by account_disabled on Feb 1, 2024 4:29:32 GMT -5
Modern rechargeable lithium-ion batteries rely on lithium and other rare earth metals. Although they offer an efficient energy source with a long cycle life, they can also raise environmental concerns and make recycling difficult. Microsoft has partnered with the Department of Energy's Pacific Northwest National Laboratory (PNNL) to discover a new material that could reduce global reliance on lithium in the production of rechargeable batteries. Using AI and the Azure Quantum Elements cloud platform, the Microsoft team has significantly accelerated time-consuming research on naturally occurring materials.
With Fax Lists Redmond's high-performance computing (HPC) systems, AI algorithms were able to predict new material properties such as energy, strength, stress, electronic band gap and mechanical properties. Microsoft and PNNL trained AI models using millions of data points from simulations, resulting in predictions of material properties 1,500 times faster than traditional density functional theory calculations. The selection process began with 32.6 million candidate materials and AI algorithms identified 500,000 expected sustainable materials.
After testing the functional properties, the pool was further narrowed down to 800 potential candidates. Using "AI-speed" simulations to study dynamic properties such as ion diffusion, the Microsoft Quantum team narrowed the selection down to 150 materials. With the synergy of AI, the Azure Quantum Elements platform and established scientific expertise, Microsoft claims that modern technology can combine the next 250 years of innovation in chemistry and materials science "into the next 25 years". Practical considerations, including innovation, mechanics and availability of elements, were then taken into account to determine a group of 18 top candidates.
With Fax Lists Redmond's high-performance computing (HPC) systems, AI algorithms were able to predict new material properties such as energy, strength, stress, electronic band gap and mechanical properties. Microsoft and PNNL trained AI models using millions of data points from simulations, resulting in predictions of material properties 1,500 times faster than traditional density functional theory calculations. The selection process began with 32.6 million candidate materials and AI algorithms identified 500,000 expected sustainable materials.
After testing the functional properties, the pool was further narrowed down to 800 potential candidates. Using "AI-speed" simulations to study dynamic properties such as ion diffusion, the Microsoft Quantum team narrowed the selection down to 150 materials. With the synergy of AI, the Azure Quantum Elements platform and established scientific expertise, Microsoft claims that modern technology can combine the next 250 years of innovation in chemistry and materials science "into the next 25 years". Practical considerations, including innovation, mechanics and availability of elements, were then taken into account to determine a group of 18 top candidates.