Research Interests

My research lies at the intersection of computational engineering, scientific machine learning, and scientific software development.

I develop physics-informed surrogate models for simulations and digital twins and investigate learning-based optimization methods. My current work includes hybrid digital twins for critical infrastructure within the RISK.twin project and machine-learning predictors for accelerating nonlinear finite-element simulations. Earlier research focused on physics-informed neural networks for industrial fluid-flow applications and reinforcement learning for shape optimization.

Keywords

• Scientific Machine Learning
• Surrogate Modeling
• Scientific Software Development
• Physics-Informed Neural Networks
• Reinforcement Learning for Optimization
• Numerical Optimization
• Finite Element Method
• Computational Mechanics
• Hybrid Digital Twins

Academic Career

Since February 2024, I have been a Scientific Project Coordinator and Postdoctoral Researcher at the University of the Bundeswehr Munich (UniBw M), where I coordinate the interdisciplinary RISK.twin project, supervise doctoral researchers and conduct research. Before joining the UniBw M, I worked as a Research Associate at RWTH Aachen University, where I completed my PhD in Computational Engineering within the Helmholtz School of Data Science in Life, Earth and Energy in 2023.

Teaching

Publications

Peer-reviewed publications

Mattuschka, M., An der Lan, N., von Danwitz, M., Wolff, D., & Popp, A. (2026). Goal-oriented optimal sensor placement for PDE-constrained inverse problems in crisis management. Computer Assisted Methods in Engineering and Science, 33(2), 147–170. : 10.24423/cames.2026.1887

Trávníková, V., Wolff, D., Dirkes, N., Elgeti, S., von Lieres, E., & Behr, M. (2024). A model hierarchy for predicting the flow in stirred tanks with physics-informed neural networks. Advances in Computational Science and Engineering, 2(2), 91–129. : 10.3934/acse.2024007

Fricke, C., Wolff, D., Kemmerling, M., & Elgeti, S. (2023). Investigation of reinforcement learning for shape optimization of 2D profile extrusion die geometries. Advances in Computational Science and Engineering, 1(1), 1–35. : 10.3934/acse.2023001

Peer-Reviewed Proceedings and Book Contributions

Sahin, T., Wolff, D., & Popp, A. (2025). Physics-Informed Neural Networks for Solving Contact Problems in Three Dimensions. In Advances and Challenges in Computational Mechanics (pp. 419–431). Springer Nature Switzerland. : 10.1007/978-3-031-93213-7_33

Sahin, T., Wolff, D., von Danwitz, M., & Popp, A. (2024). Towards a Hybrid Digital Twin: Fusing Sensor Information and Physics in Surrogate Modeling of a Reinforced Concrete Beam. In 2024 Sensor Data Fusion: Trends, Solutions, Applications (SDF) (pp. 1–8). 2024 Sensor Data Fusion: Trends, Solutions, Applications (SDF). IEEE. : 10.1109/sdf63218.2024.10773885

Idzik, C., Hilger, D., Hosters, N., Kemmerling, M., Niemietz, P., Ortjohann, L., Sasse, J., Serafeim, A., Wang, J., Wolff, D., & Hirt, G. (2023). Decision Support for the Optimization of Continuous Processesusing Digital Shadows. In Interdisciplinary Excellence Accelerator Series (pp. 281–301). Springer International Publishing. : 10.1007/978-3-031-44497-5_12

Wolff, D., Fricke, C., Kemmerling, M., & Elgeti, S. (2023). Towards shape optimization of flow channels in profile extrusion dies using reinforcement learning. In PAMM (Vol. 22, Issue 1). Wiley. : 10.1002/pamm.202200009

Monographs

Wolff, D. (2023). Learning-based approaches for the analysis and optimization of profile extrusion dies and bioreactors. Dissertation. RWTH Aachen University. : 10.18154/RWTH-2023-10706

Wolff, D. (2020). Modern Design of a C++17 Finite Element Continuum Mechanics Simulation Code: Automatized Differentiation and Flexible Coupling Strategies. Master's Thesis. RWTH Aachen University. : 10.18154/RWTH-2020-09061