معرفی
Ján Drgona is an Associate Professor in the Department of Civil and Systems Engineering at Johns Hopkins University's Whiting School of Engineering and a member of the Ralph S. O'Connor Sustainable Energy Institute (ROSEI). Previously, he served as a Principal Investigator and Research Data Scientist at Pacific Northwest National Laboratory (PNNL) and held a postdoctoral position at KU Leuven in Belgium.
Dr. Drgona earned his BSc, MSc, and PhD in control engineering from the Slovak University of Technology. His research centers on differentiable programming and scientific machine learning (SciML) for dynamical systems, optimization, and control, with particular applications to building energy systems and industrial process control. He is the lead developer of the Neuromancer SciML library in PyTorch for solving constrained optimization, physics-informed machine learning, and optimal control problems, which became PNNL's most popular open-source repository within two years of its release.
Dr. Drgona's publication record demonstrates a strong focus on bridging machine learning with physical systems and control theory. His recent work spans differentiable predictive control, physics-informed neural networks, optimization algorithms, and applications to energy systems. A recurring theme across his publications is the integration of domain knowledge with data-driven approaches to create more efficient, reliable, and interpretable systems for real-world applications, particularly in sustainable energy and building systems.
As an active member of the scientific community, Dr. Drgona regularly serves as a reviewer for prestigious journals including Applied Energy, Automatica, IEEE Control Systems Letters, IEEE Transactions on Control Systems Technology, IEEE Transactions on Industrial Informatics, Control Engineering Practice, Journal of Process Control, Energy and Buildings, Journal of Control Automation and Electrical Systems, and Electric Power Systems Research.
Dr. Drgona has been involved in several high-impact projects, including developing AI models that slash HVAC energy costs while predicting them with precision. He has participated in Johns Hopkins' International Energy Summit to accelerate clean technology innovation and has presented at major conferences including ACC 2025 where he co-organized workshops on Physics-Informed Machine Learning in Control and Safe Physics-Informed Machine Learning for Dynamics and Control.
