Graduate Fellows

Dinara Ermakova – UC Berkeley PhD Student (NSSC Fellow)

During the summer 2022, Dinara interned in the ORNL Nuclear Energy and Fuel Cycle Division working under Drs. Andrew Worrall and Jin Whan Bae. Dinara’s research was focused on the electricity generation sector which is responsible for 25% of the world’s greenhouse gas (GHG) emissions and thus has been the focus of efforts to transition to clean energy and sustainable development in many nations. According to Dinara’s research, the rapid development of renewable energy sources and technologies will require an enormous amount of raw materials to replace coal and gas plants and increase in the capacity to handle growing electricity demand because renewable energy sources have a low-power density and intermittent behavior. During her internship, she was explored the opportunity for remining abandoned mines waste as a way to satisfy demand, facilitate cleanup activities, and engage local communities. The results of her work will be published in a technical report.  In addition, Dinara was able to work on her dissertation project, assessing the material demand for the projected transition and its transportation carbon footprint.  Apart from work, Dinara says, she that her internship provided the opportunity to meet “many brilliant people and make friends at the Lab.

Jordan Stomps – University of Wisconsin-Madison (ETI Fellow)

Jordan is a doctoral student at the University of Wisconsin-Madison studying nuclear engineering under Paul Wilson. He began his internship at ORNL in May 2022 to develop and expand his doctoral research. His research is supported by the NNSA Consortium for Enabling Technology and Innovation (ETI) under the Research Thrust Area for Computer and Engineering Sciences for Nonproliferation. His doctoral research utilizes data collected under the NNSA NA-22 MINOS project in collaborations with ORNL research scientists (Jared Johnson venture lead; Ken Dayman team lead).

Jordan’s research focuses on leveraging large volumes of radiation-detection data (i.e. gamma-rays) that have limited attribution. In real-world scenarios, the high cost of limited contextual and ground truth information can make labeling sufficient data prohibitive. Using semi-supervised machine learning techniques, Jordan is designing methods that can increase the amount of high value, interpretable, and actionable information relevant to a range of nonproliferation missions. This ultimately leads to more informed decisions and resource efficiency based on nuclear monitoring.

By working with ORNL researchers, Jordan has been able to align his research with impactful applications to help further NNSA’s nonproliferation objectives. In addition to having a network of expertise on nuclear nonproliferation, Jordan’s research is also being supported by ORNL’s scientific and computing resources which are critical tools for research in machine learning and artificial intelligence applications. Jordan hopes to complete his PhD while at ORNL; and hopes to use this experience to build a career in nuclear nonproliferation research.