The Center for Education and Research in Information Assurance and Security (CERIAS)
The Center for Education and Research inInformation Assurance and Security (CERIAS)
Principal Investigator: Lefteri Tsoukalas
GEMINA aims to develop digital twin technology for advanced nuclear reactors and transform operations and maintenance (O&M) systems in the next generation of nuclear power plants. There is a need for tools that introduce greater flexibility in reactor systems, increased autonomy in operations, faster design iteration, and improved economic competitiveness. To
accomplish this, we explore the application of data-driven and physics-informed models for monitoring sensor measurements and reactor transients. We also develop transfer learning methods which allow for monitoring with limited historical data, using models trained on different operating conditions.
Other PIs: Alexander Heifetz
Students: Styliani Pantopoulou Konstantinos Prantikos Maria Pantopoulou
Pantopoulou, S.; Ankel, V.; Weathered, M.T.; Lisowski, D.D.; Cilliers, A.; Tsoukalas, L.H.; Heifetz, A. Monitoring of Temperature Measurements for Different Flow Regimes in Water and Galinstan with Long Short-Term Memory Networks and Transfer Learning of Sensors. Computation 2022, 10, 108.
S. Pantopoulou, M. Weathered, D. Lisowski, L. H. Tsoukalas and A. Heifetz, "Temporal Forecasting of Distributed Temperature Sensing in a Thermal Hydraulic System With Machine Learning and Statistical Models," in IEEE Access, vol. 13, pp. 10252-10264, 2025.
Prantikos, K., Tsoukalas, L. H., & Heifetz, A. (2022). Physics-informed neural network solution of point kinetics equations for a nuclear reactor digital twin. Energies, 15(20), 7697.
Prantikos, K., Chatzidakis, S., Tsoukalas, L. H., & Heifetz, A. (2023). Physics-informed neural network with transfer learning (TL-PINN) based on domain similarity measure for prediction of nuclear reactor transients. Scientific reports, 13(1), 16840.