Ján Drgoňa

Drgona_Headshot.jpg

3400 N Charles St,

Baltimore, MD 21218

I am an associate professor in the Department of Civil and Systems Engineering at Johns Hopkins University (JHU). I hold a secondary appointment at the Department of Electrical and Computer Engineering, and I am the core faculty member of the Ralph S. O’Connor Sustainable Energy Institute (ROSEI), and an affiliate of the Data Science and AI Institute (DSAI).

Previously, I was a research data scientist at the Pacific Northwest National Laboratory (PNNL), and a postdoc at KU Leuven in Belgium. I did my PhD in process control from Slovak University of Technology.

My project portfolio is focused on differentiable programming and scientific machine learning (SciML) for dynamical systems, constrained optimization, and control with applications to sustainable energy systems.

I am a lead software developer of Neuromancer SciML library in PyTorch for solving constrained optimization, physics-informed machine learning, and optimal control problems.

news

Oct 6, 2025 I gave a talk at the roundtable event on Construction and Environmental Aspects of Data Centers hosted by the University of Maryland’s Department of Civil and Environmental Engineering.
Oct 4, 2025 I gave a talk on Scientific Machine Learning at JHU’s Connect to Campus 2025 event.
Sep 29, 2025 I gave a talk at the Computing and Sustainability Seminar, hosted by MIT’s Laboratory for Information and Decision Systems (LIDS).
Jul 7, 2025 I had a packed program at the ACC 2025 in Denver, CO. I co-organized workshop on Physics-Informed Machine Learning in Control. I co-organized a tutorial session on Safe Physics-Informed Machine Learning for Dynamics and Control. I also presented my work on differentiable predictive control (DPC) in a tutorial session on Learning Interpretable Control Policies: Unifying Reinforcement Learning, Differentiable Programming and Bayesian Optimization. All my ACC slides are available at GitHub.
Jun 22, 2025 I gave a talk at the EU-JHU Energy Technology & Science Bridge.

selected publications

  1. DPC_original.PNG
    Learning Constrained Parametric Differentiable Predictive Control Policies With Guarantees
    Ján Drgoňa, Aaron Tuor, and Draguna Vrabie
    IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2024
  2. ACMCS2023.PNG
    Constructing Neural Network Based Models for Simulating Dynamical Systems
    Christian Legaard, Thomas Schranz, Gerald Schweiger, and 6 more authors
    ACM Computing Surveys, Feb 2023
  3. DPC.PNG
    Differentiable predictive control: Deep learning alternative to explicit model predictive control for unknown nonlinear systems
    Ján Drgoňa, Karol Kiš, Aaron Tuor, and 2 more authors
    Journal of Process Control, Aug 2022
  4. NeurIPS_DMM.PNG
    On the Stochastic Stability of Deep Markov Models
    Ján Drgoňa, Sayak Mukherjee, Jiaxin Zhang, and 2 more authors
    In Advances in Neural Information Processing Systems, Aug 2021
  5. ARC.PNG
    All you need to know about model predictive control for buildings
    Ján Drgoňa, Javier Arroyo, Iago Cupeiro Figueroa, and 8 more authors
    Annual Reviews in Control, Sep 2020