Development of Artificial Intelligence Techniques for Automated Nanoparticle Characterization
Advanced synthesis methods have made it possible to create millions of nanoparticles on a single chip. These megalibraries provide a wealth of information, but their formidable size renders manual characterization infeasible. This talk will describe the development of novel artificial intelligence techniques to automate nanoparticle characterization. First, we show that neural architecture search can create machine learning models that generalize well to previously-unseen nanoparticle datasets. Next, we demonstrate a rapid, unsupervised segmentation technique for our data that is expected to perform at least 25 times faster, on average, than the benchmark method. We then describe how image processing can be applied to nanoparticle images before machine learning model training such that accuracy is improved by >10% relative to baseline. These artificial intelligence techniques are expected to significantly accelerate nanoparticle analysis relative to manual processes and represent a step towards “self-driving” laboratories.
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
- 833 Dyer Road
- Monterey, California
- United States 93940
- Building: 232
Speakers
Prof. Alexandra Day of US Naval Academy
Development of Artificial Intelligence Techniques for Automated Nanoparticle Characterization
Alexandra Day is an Assistant Professor of Electrical and Computer Engineering at the United States Naval Academy in Annapolis. She holds a PhD in computer engineering from Northwestern University, where her dissertation focused on developing AI tools for automated nanoparticle characterization. Her current research uses supercomputers to train machine learning models for scientific applications. Prior to graduate school, she spent five years as an Assistant Technical Staff member at MIT Lincoln Laboratory and she has completed technical internships at the University of Maryland, NIST, CERN, MIT Lincoln Laboratory, and Lawrence Livermore National Laboratory. She is a recipient of the National Science Foundation Graduate Research Fellowship and was named a 2024 Rising Star in Computational and Data Sciences.