Profile

I am a passionate researcher with a focus on data-driven modeling and machine learning. My research interests include surrogate modeling, surrogate-based optimization, data-driven modeling, and generative models. With a background in mechanical engineering and a strong work ethic developed through my years as a competitive swimmer, I bring a unique perspective to my research. I completed my bachelor’s studies through a dual study system with BASF, Germany’s largest chemical company, and finished my master’s studies on the topic of reduced order modeling and optimal flow control. I have also published a student project on the generation of synthetic ground penetrating radargrams using generative adversarial networks (GANs). I am proficient in programming with Python and have a growing enthusiasm for the rising popularity of Julia in my current work on surrogate-based optimization. Thank you for visiting my profile and feel free to reach out for further collaboration or inquiries.

Talks

• Gradient-enhanced BNN Surrogate Models for Aerodynamic Shape Optimization, AG Turbo, 06.03.2025, Cologne, Germany.
• Sobolev Learning for Bayesian Neural Network Assisted Aerodynamic Shape Optimization, STAB Konferenz, 13.11.2024, Regensburg, Germany.
• Bayesian Neural Network Surrogate Models for Aerodynamic Shape Optimization, AG Turbo, 08.10.2024, Dresden, Germany.
• Bayesian Neural Network Surrogates for Efficient Global Optimization of an Airfoil Geometry, ECCOMAS 2024, 07.06.2024, Lisbon, Portugal.
• Neural Network Surrogates for Efficient Global Optimization, AG Turbo, 07.03.2024, Darmstadt, Germany.
• Gradient Enhanced Surrogate Modeling Framework for Aerodynamic Design Optimization, AIAA Scitech 2024, 12.01.2024, Orlando FL, USA.
• Multi-Fidelity Aerodynamic Design Optimization Framework using Gradient Asissted
  Surrogate Modeling, EUROGEN 2023, 02.06.2023, Crete, Greece.
• Trailing Edge Noise Reduction by Porous Treatment using Derivative-Free Optimization, Scientific Computing Seminar, 05.01.2023, Kaiserslautern, Germany.
• Flow Control via Reduced Order Models, Scientific Computing Seminar, 18.11.2021, Kaiserslautern, Germany.
• Reduced Order Modeling and Nonlinear System Identification Techniques for Fluid Dynamics, Scientific Computing Seminar, 22.04.2021, Kaiserslautern, Germany.

Publications

@misc{nokey,

title = {Adjoint-Based Aerodynamic Shape Optimization with a Manifold Constraint Learned by Diffusion Models},

author = {L. Chen, E. Özkaya, J. Rottmayer, N.R. Gauger, Z. Shen, Y. Ye},

url = {https://arxiv.org/abs/2507.23443},

year  = {2025},

date = {2025-08-01},

urldate = {2025-08-01},

howpublished = {arXiv:2507.23443},

keywords = {},

pubstate = {published},

tppubtype = {misc}

}

@article{nokeyr,

title = {Data-driven aerodynamic shape design with distributionally robust optimization approaches},

author = {L. Chen, J. Rottmayer, L. Kusch, N. R.Gauger, Y. Ye, },

url = {https://doi.org/10.1016/j.cma.2024.117131},

issn = {0045-7825},

year  = {2024},

date = {2024-06-15},

urldate = {2024-06-15},

journal = {Computer Methods in Applied Mechanics and Engineering},

volume = {429},

pages = {117131},

abstract = {We formulate and solve data-driven aerodynamic shape design problems with distributionally robust optimization (DRO) approaches. DRO aims to minimize the worst-case expected performance in a set of distributions that is informed by observed data with uncertainties. Building on the findings of the work Gotoh, et al. (2018), we study the connections between a class of DRO and robust design optimization, which is classically based on the mean–variance (standard deviation) optimization formulation pioneered by Taguchi. Our results provide a new perspective to the understanding and formulation of robust design optimization problems. It enables data-driven and statistically principled approaches to quantify the trade-offs between robustness and performance, in contrast to the classical robust design formulation that captures uncertainty only qualitatively. Our preliminary computational experiments on aerodynamic shape optimization in transonic turbulent flow show promising design results.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Gradient Enhanced Surrogate Modeling Framework for Aerodynamic Design Optimization},

author = {E. Özkaya , J. Rottmayer, N.R. Gauger},

doi = {10.2514/6.2024-2670},

year  = {2024},

date = {2024-01-04},

urldate = {2024-01-04},

journal = {AIAA 2024-2670},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@misc{CRKGY2023,

title = {Data-driven aerodynamic shape design with distributionally robust optimization approaches},

author = {L. Chen, J. Rottmayer, L. Kusch, N.R. Gauger, Y. Ye},

url = {https://arxiv.org/pdf/2310.08931.pdf},

year  = {2023},

date = {2023-10-13},

urldate = {2023-10-13},

howpublished = {arXiv:2310.08931},

keywords = {},

pubstate = {published},

tppubtype = {misc}

}

@misc{nokey,

title = {Trailing-Edge Noise Reduction using Porous Treatment and Surrogate-based Global Optimization},

author = {J. Rottmayer, E. Özkaya, S. Satcunanathan, B. Y. Zhou, M. Aehle, N. R. Gauger, M. Meinke, W. Schröder, S. Pullin

},

url = {https://arxiv.org/abs/2301.13047},

year  = {2023},

date = {2023-01-30},

urldate = {2023-01-30},

howpublished = {arXiv:2301.13047},

keywords = {},

pubstate = {published},

tppubtype = {misc}

}

@conference{nokey,

title = {GPR-GANs: Generation of Synthetic Ground Penetrating Radargrams Using Generative Adversarial Networks},

author = {A. Fazeel, J. Rottmayer, R.Mehta and N. Bajcinca},

url = {https://ieeexplore.ieee.org/document/9843171},

doi = {10.1109/IWAGPR50767.2021.9843171},

year  = {2021},

date = {2021-00-00},

booktitle = {2021 11th International Workshop on Advanced Ground Penetrating Radar (IWAGPR)},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}