Cover

This work by Yanlong Zhao et al. presents an AI-enabled physical-digital discovery loop for carbon nanotube research. Physical experiments generate CNTs with diverse structures, while AI-assisted characterization converts complex microscopy and spectroscopy outputs into quantitative descriptors such as diameter, alignment, and defects. These descriptors feed structure-property models that predict conductivity, strength, and optical response. The digital workflow then recommends the next synthesis conditions, closing the loop between experiment, data, and decision-making. This integrated framework highlights how AI can accelerate CNT optimization from growth to applications under data-scarce conditions.