papers

Publications (9)

physics.flu-dyn2025

Physics-Informed Neural Networks for Transonic Flows around an Airfoil

Simon Wassing, Stefan Langer, Philipp Bekemeyer

Physics-informed neural networks have gained popularity as a deep-learning based parametric partial differential equation solver. Especially for engineering applications, this appr…

physics.flu-dyn2024

Physics-Informed Neural Networks for Parametric Compressible Euler Equations

Simon Wassing, Stefan Langer, Philipp Bekemeyer

The numerical approximation of solutions to the compressible Euler and Navier-Stokes equations is a crucial but challenging task with relevance in various fields of science and eng…

cs.LG2025

Fusing CFD and measurement data using transfer learning

Alexander Barklage, Philipp Bekemeyer

Aerodynamic analysis during aircraft design usually involves methods of varying accuracy and spatial resolution, which all have their advantages and disadvantages. It is therefore…

cs.LG2025

Predicting Onflow Parameters Using Transfer Learning for Domain and Task Adaptation

Emre Yilmaz, Philipp Bekemeyer

Determining onflow parameters is crucial from the perspectives of wind tunnel testing and regular flight and wind turbine operations. These parameters have traditionally been predi…

cs.LG2026

Goal-Driven Adaptive Sampling Strategies for Machine Learning Models Predicting Fields

Jigar Parekh, Philipp Bekemeyer

Machine learning models are widely regarded as a way forward to tackle multi-query challenges that arise once expensive black-box simulations such as computational fluid dynamics a…

cs.CE2024

Partitioned Surrogates and Thompson Sampling for Multidisciplinary Bayesian Optimization

Susanna Baars, Jigar Parekh, Ihar Antonau +2

The long runtime associated with simulating multidisciplinary systems challenges the use of Bayesian optimization for multidisciplinary design optimization (MDO). This is particula…