Bio
Jordan is a nonproliferation data scientist in the Data Science and Engineering for Nonproliferation group. Prior to joining ORNL in January 2024, Jordan completed a PhD in nuclear engineering and engineering physics (2023) at the University of Wisconsin-Madison. Jordan also holds a master’s degree in nuclear engineering and engineering physics (2021) from the University of Wisconsin-Madison and a bachelor’s degree in physics (2019) from Michigan State University. Jordan collaborated with ORNL for his dissertation research, starting as an intern at ORNL in May 2022 until his graduation in December 2023. As an intern, Jordan developed data analytical techniques for simulated environmental samples generated from reactor models. Jordan’s dissertation focused on leveraging large volumes of unlabeled gamma-ray spectra to improve the efficacy of machine learning models otherwise trained on limited labeled datasets. Using a set of data augmentations tailored for gamma spectroscopy, Jordan employed contrastive self-supervision to train a model that produced meaningful representations of spectra with embedded information learned from unlabeled data. Much of Jordan’s current research projects focus on improving the value of learned information in machine learning for rare-event or limited labeled data scenarios on a variety of modalities for national security. Active areas of research interest include semi-supervised machine learning, few-shot machine learning, time series forecasting, fuel cycle modeling, and scientific computing.
Education
- PhD Nuclear Engineering and Engineering Physics, University of Wisconsin-Madison (2023)
- MS Nuclear Engineering and Engineering Physics, University of Wisconsin-Madison (2021)
- BS Physics, Michigan State University (2019)