News

Abstract: The goal of inverse molecular design is the discovery of novel molecular structures that fulfill a set of target properties. In this project we explore the application of generative models and molecular graph representations for the development of solutions to the inverse molecular design…

We offer multiple opportunities for a M.Sc. thesis on several topics at the interface of Machine Learning and Physical Modeling. The projects would be contacted in close collaboration with Carl Zeiss AG. More details can be found here. If you are interested please send an Email to Prof.…

A framework that generalizes several existing schemes for parametric PDEs and achieves generalization in out-of-distribution, multiscale problems. More details: https://arxiv.org/abs/2405.19019

We are currently looking for M.Sc. students to work on the topic of "Inverse Materials Design". This is an interdisciplinary topic that combines computational modeling of physical systems with adavnaced machine learning techniques. More details can be found here

Highlights • We propose a probabilistic, data-driven closure model for Reynolds-Averaged Navier-Stokes simulations. • It is trained with high-fidelity data of mean velocity/pressure and quantifies aleatoric uncertainties in the model form. • It can automatically identify regions where closure is…

Abstract: Random media and the process-structure-property chain generally define complex, high-dimensional and stochastic materials systems, posing a challenging setting for any prediction or optimization task. In this thesis, we pursue a Bayesian approach for learning and predicting the behavior…

Abstract: Solving high-dimensional, nonlinear systems is a key challenge in engineering and computational physics. We propose novel physics-aware machine learning models that rely both on physical knowledge as well as a small amount of data and are, after an initial training phase, able to solve…

Application deadline: March 8th 2023. Details about the position as well as the application process can be found here

While the forward and backward modeling of the process-structure-property chain has received a lot of attention from the materials’ community, fewer efforts have taken into consideration uncertainties. Those arise from a multitude of sources and their quantification and integration in the inversion…

Abstract: In recent years, data-driven approaches have significantly reduced the computational effort required to capture the structure-property linkages in high-contrast microstruc- tures. Convolutional neural networks (CNNs), a special form of artificial neural networks (ANNs), have been shown to…

Sven Lüpke presents his Interdisciplinary Project on "Generative Modeling for Molecules"

3 M.Sc thesis topics in collaboration with Carl Zeiss AG at the interface of Machine Learning and Physical Modeling

New work on "Physics-Aware Neural Implicit Solvers" (PANIS)

M.Sc. thesis on the topic of "Inverse Materials Design"

New paper on "A probabilistic, data-driven closure model for RANS simulations with aleatoric, model uncertainty" in the Journal of Computaional Physics

Maximilian Rixner defends his Ph.D. thesis on "Physics-Informed and Data-Driven Probabilistic Modeling of Materials Systems"

Sebastian Kaltenbach defends his Ph.D. thesis on "Physics-aware, probabilistic machine learning in the Small Data regime"

A Postdoc position is available on Data-driven Modeling of Materials and Engineering Physics

New paper on "Self-supervised optimization of random material microstructures in the small-data regime" in npj Computational Materials

Carlos Vonessen presents his B.Sc. thesis on "Development and comparison of several deep learning models to capture structure-property linkages in high-contrast two-phase 2D elastic composites"