Scientific Machine Learning
SciML

The SciML group researches and develops numerical approximation methods which merge physics-based and data-driven modeling and computing techniques.

Our research spans to:

  • Data-driven simulation methods, where raw data are incorporated into physics-based numerical simulations;
  • Physics-informed machine learning, where physical constraints are integrated into data-driven machine learning techniques;
  • Applications in challenging engineering design tasks, such as optimization, uncertainty quantification, and parameter identification.

Selected research projects

  • Data-driven, material-model-free electromagnetic field solvers
  • Numerical simulation with physics-informed neural networks
  • Bayesian inference methods for parameter identification in biological and electrical engineering systems
  • Tensor decompositions for solving high-dimensional multi-linear systems
  • Uncertainty quantification for models with high-dimensional inputs and outputs
  • Surrogate-based design optimization

Group leader

  Name Working area(s) Contact
Dr.-Ing. Dimitrios Loukrezis
Scientific Machine Learning
Uncertainty Quantification, Scientific Machine Learning, Surrogate Modeling
+49 6151 16-24033
S2|17 217

Group members

  Name Working area(s) Contact
Dr. Ion Gabriel Ion
Armin Galetzka M.Sc.
Moritz von Tresckow M.Sc.
Electromagnetic field simulation with physics-informed neural networks
+49 6151 16- 24033
S2|17 217