Researchers from AIMR developed an AI-driven approach to model carbon growth on metal surfaces with high accuracy. By integrating molecular dynamics, time-stamped force-biased Monte Carlo simulations, and machine learning, their method replicates key processes like carbon diffusion and graphene nucleation, enabling scalable, efficient carbon nanomaterial production for electronics and energy storage.

Conventional thinking holds that the metal site in single atom catalysts (SACs) has been a limiting factor to the continued improvement of the design and, therefore, the continued improvement of the capability of these SACs. More specifically, the lack of outside-the-box thinking when it comes to the crucial hydrogen evolution reaction (HER), a half-reaction resulting in the splitting of water, has contributed to a lack of advancement in this field. New

research emphasizes the importance of pushing the limits of the metal site design in SACs to optimize the HER and addressing the poisoning effects of HO* and O* that might affect the reaction. All of these improvements could lead to an improved performance of the reaction, which can make sustainable energy storage or hydrogen production more available.