A team of scientists has developed a method to shed light on the dynamic behavior of nanoparticles—tiny structures that play a key role in pharmaceuticals, electronics, and materials used in industry and energy conversion. The breakthrough, published in Science, combines artificial intelligence with electron microscopy to visualize how these minuscule particles respond to various stimuli.
On the left is a platinum nanoparticle, which has been imaged via electron microscopy. The data have sufficient spatial resolution to display individual atoms. However, these images are heavily corrupted by noise due to the high temporal resolution, which is nonetheless necessary to visualize fundamental dynamic behavior on the nanoparticle surface associated with its functionality. At right is the output of an AI system, which is able to effectively remove the noise and reveal the atomic structure of the nanoparticle. Image Credit: Courtesy of Arizona State's Peter Crozier and Joshua Vincent and NYU's Carlos Fernandez-Granda and Sreyas Mohan.
Nanoparticle-based catalytic systems have a tremendous impact on society. It is estimated that 90 % of all manufactured products involve catalytic processes somewhere in their production chain. We have developed an artificial-intelligence method that opens a new window for the exploration of atomic-level structural dynamics in materials.
Carlos Fernandez-Granda, Director, Study Author and Professor, Center for Data Science, New York University
The research, which involved scientists from Arizona State University, Cornell University, and the University of Iowa, leverages AI-enhanced electron microscopy to capture molecular structures and movements at an unprecedented time resolution—down to one-billionth of a meter.
Electron microscopy can capture images at a high spatial resolution, but because of the velocity at which the atomic structure of nanoparticles changes during chemical reactions, we need to gather data at a very high speed to understand their functionality. This results in extremely noisy measurements. We have developed an artificial-intelligence method that learns how to remove this noise—automatically—enabling the visualization of key atomic-level dynamics.
Peter A. Crozier, Professor and Study Author, Materials Science and Engineering, Arizona State University
Tracking the movement of atoms in a nanoparticle is crucial for understanding their behavior in industrial applications. However, these atoms are so small and faint that their actions are often unclear—similar to trying to follow objects in a grainy, low-light video. To address this, the researchers trained a deep neural network, the computational engine behind AI, to enhance electron-microscope images, revealing the atoms and their motion more clearly.
The nature of changes in the particle is exceptionally diverse, including fluxional periods, manifesting as rapid changes in atomic structure, particle shape, and orientation; understanding these dynamics requires new statistical tools. This study introduces a new statistic that utilizes topological data analysis to both quantify fluxionality and to track the stability of particles as they transition between ordered and disordered states.
David S. Matteson, Professor and Associate Chair, Department of Statistics and Data Science, Cornell University
Journal Reference:
Crozier, A. P., et al. (2025) Visualizing nanoparticle surface dynamics and instabilities enabled by deep denoising. doi/10.1126/science.ads2688