Nanosciences and Nanotechnology

AI, Machine Learning and Autonomous Laboratories for Nanoscience

Further sessions may explore multiscale simulation, density functional theory, molecular dynamics, and digital twins of processes and devices. Presentations will consider graph neural networks, foundation models for microscopy and spectroscopy, and automated image segmentation for particle analysis. Researchers will examine physics-informed machine learning that respects conservation laws and improves extrapolation to unseen conditions. Attention will be given to reproducibility, benchmark datasets, and disclosure of model limitations. Compute cost, energy use, and access for researchers in lower-resource institutions will be reviewed. Responsible use of AI in materials discovery and safety prediction will be discussed.