Home | Research | Groups | Rüdiger Westermann

Research Group Rüdiger Westermann

Link to Rüdiger Westermann

Rüdiger Westermann

Prof. Dr.

Principal Investigator

Computer Graphics & Visualization

Rüdiger Westermann

holds the Chair of Computer Graphics and Visualization at TU Munich.

He conducts research in the field of applied informatics in the areas of computer graphics, scientific visualization and real-time numerical simulation. The focus is on developing efficient algorithms for interactive data exploration and physical simulation in virtual environments and implementing them in multicore architectures. Key research contributions in recent years relate to volume visualization, multiscale simulation with finite elements, and hierarchical data representation.

Team members @MCML

Link to Kevin Höhlein

Kevin Höhlein

Computer Graphics & Visualization

Publications @MCML

[1]
F. Koehler, S. Niedermayr, R. Westermann and N. Thuerey.
APEBench: A Benchmark for Autoregressive Neural Emulators of PDEs.
NeurIPS 2024 - 38th Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 10-15, 2024. To be published. Preprint available. arXiv.
Abstract

We introduce the Autoregressive PDE Emulator Benchmark (APEBench), a comprehensive benchmark suite to evaluate autoregressive neural emulators for solving partial differential equations. APEBench is based on JAX and provides a seamlessly integrated differentiable simulation framework employing efficient pseudo-spectral methods, enabling 46 distinct PDEs across 1D, 2D, and 3D. Facilitating systematic analysis and comparison of learned emulators, we propose a novel taxonomy for unrolled training and introduce a unique identifier for PDE dynamics that directly relates to the stability criteria of classical numerical methods. APEBench enables the evaluation of diverse neural architectures, and unlike existing benchmarks, its tight integration of the solver enables support for differentiable physics training and neural-hybrid emulators. Moreover, APEBench emphasizes rollout metrics to understand temporal generalization, providing insights into the long-term behavior of emulating PDE dynamics. In several experiments, we highlight the similarities between neural emulators and numerical simulators.

MCML Authors
Link to Rüdiger Westermann

Rüdiger Westermann

Prof. Dr.

Computer Graphics & Visualization

Link to Nils Thuerey

Nils Thuerey

Prof. Dr.

Physics-based Simulation