(465a) Learning the Diffusion of Nanoparticles in Liquid Phase TEM Using Physics-Informed Generative AI

Diffusion of small nanoparticles in complex environments can inform us of the underlying rheological properties of their surrounding environment. The advent of Liquid Phase Transmission Electron Microscopy (LPTEM) has introduced a novel avenue for high spatial and temporal resolution single-particle tracking of nanoparticles in complex liquid environments from emulsion dispersions to polymeric solutions. Interpreting the underlying physics of single particle trajectories has traditionally been approached with canonical statistical methods such as time-averaged mean squared displacement; however, these methods fail on single short trajectories, especially the ones with non-gaussian and nonergodic characteristics – a common feature of LPTEM trajectories. These challenges have led to a body of computational research on classifying short single-particle trajectories into ideal classes of anomalous diffusion and determining their anomalous exponents using supervised and unsupervised machine learning methods. However, experimental data from single particle tracking experiments remains a largely unknown mixture of different anomalous diffusion classes with unknown anomalous exponents, making it difficult to classify them into ideal stochastic models. Here, we have developed a physics-informed generative neural network model trained on a large data set of experimental trajectories mixed with simulated trajectories of gold nanorods from LPTEM experiments. We show that this model learns the time-dependent dynamics of the experimental trajectories in its continuous latent space representation based on statistical/physical properties. We demonstrate that our model can distinguish various levels of anomaly regardless of the underlying class of diffusion, a key feature for analysis of LPTEM single particle trajectories in the nanorheology of complex environments.