July-August_2023_AMP_Digital

ADVANCED MATERIALS & PROCESSES | JULY/AUGUST 2023 10 MACHINE LEARNING | AI A new report titled “AI for Science, Energy, and Security” presents a comprehensive vision for the Department of Energy to expand its work in the scientific use of artificial intelligence (AI). The study describes scientific grand challenges where AI plays a major role, such as transportation, national security, and development of next-generation materials. tinyurl.com/5n6rsnc4. BRIEF MACHINE LEARNING SUPPORTS SOLID-STATE BATTERIES Researchers at Duke University, Durham, N.C., and their colleagues discovered the atomic mechanisms that make compounds known as argyrodites promising candidates for both solid-state battery electrolytes and thermoelectric energy converters. Their results, and the machine learning approach used to achieve them, could lead to new energy storage applications for electric vehicles and other applications. “Every electric vehicle manufacturer is trying to move to new solid- state battery designs, but none of them are disclosing which compositions they’re betting on,” says associate professor Olivier Delaire. He and his colleagues looked at one promising candidate made of silver, tin, and selenium (Ag8SnSe6). Using a combination of neutrons and x-rays, the team bounced these fast-moving particles off atoms within samples of Ag8SnSe6 to reveal its molecular behavior in real time. Researcher Mayanak Gupta then developed a machine learning approach to make sense of the data and created a computational model to match the observations using quantum mechanical simulations. The results show that while the tin and selenium atoms create a relatively stable scaffolding, it is far from static. The crystalline structure constantly flexes to create windows and channels for the charged silver ions to move freely through the material: The tin and selenium lattices remain solid while the silver is in a nearly liquid-like state, according to Delaire. These results along with the approach of combining advanced experimental spectroscopy with machine learning could help researchers make faster progress toward replacing lithium-ion batteries in crucial applications. duke.edu. SOFTWARE SPEEDS POLYMER DISCOVERY A software program called PySoftK that aims to advance the discovery of new polymers has been developed by a team of interdisciplinary researchers at King’s College London. PySoftK uses artificial intelligence (AI) to identify new polymer materials, which could be used across a wide range of applications in energy storage, medical technology, and more. The software facilitates the use of computer simulations at a complex molecular scale to design new polymer materials. The program could change the way scientists investigate the relationship between the chemical structure and function of new polymeric materials, by providing a robust dataset for researchers to train AI to identify desirable polymer properties. Over the past few decades, molecular scale simulations have improved scientific understanding of the relationship between chemical structure and function in increasingly complex polymers. However, more recent advances in computing power and computational algorithms have Illustration of hybrid crystalline-liquid atomic structure in superionic phase of Ag8SnSe6. Tube-like filaments show the liquid-like distribution of silver ions flowing through the crystalline scaffold of tin and selenium atoms. PySoftK uses AI to identify new polymer materials for use in applications from energy storage to medical technology. enabled scientists to investigate more complex systems and provide more accurate predictions using molecular- scale simulations at speed. This can lead to faster and more cost-effective materials design. “By offering a set of tools and programming modules to automate the process of curating, modeling, and creating libraries of polymers, PySoftK facilitates the generation of large databases on which to train future machine learning and deep learning models. This allows researchers to move their focus away from exhaustive library maintenance and onto discovering new materials,” says Professor Chris Lorenz. www.kcl.ac.uk.

RkJQdWJsaXNoZXIy MTYyMzk3NQ==