Saved in:
Bibliographic Details
Main Authors: Setinek, Paul, Galletti, Gianluca, Gross, Thomas, Schnürer, Dominik, Brandstetter, Johannes, Zellinger, Werner
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.12007
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908823947575296
author Setinek, Paul
Galletti, Gianluca
Gross, Thomas
Schnürer, Dominik
Brandstetter, Johannes
Zellinger, Werner
author_facet Setinek, Paul
Galletti, Gianluca
Gross, Thomas
Schnürer, Dominik
Brandstetter, Johannes
Zellinger, Werner
contents Neural surrogates for Partial Differential Equations (PDEs) often suffer significant performance degradation when evaluated on problem configurations outside their training distribution, such as new initial conditions or structural dimensions. While Unsupervised Domain Adaptation (UDA) techniques have been widely used in vision and language to generalize across domains without additional labeled data, their application to complex engineering simulations remains largely unexplored. In this work, we address this gap through two focused contributions. First, we introduce SIMSHIFT, a novel benchmark dataset and evaluation suite composed of four industrial simulation tasks spanning diverse processes and physics: hot rolling, sheet metal forming, electric motor design and heatsink design. Second, we extend established UDA methods to state-of-the-art neural surrogates and systematically evaluate them. Extensive experiments on SIMSHIFT highlight the challenges of out-of-distribution neural surrogate modeling, demonstrate the potential of UDA in simulation, and reveal open problems in achieving robust neural surrogates under distribution shifts in industrially relevant scenarios. Our codebase is available at https://github.com/psetinek/simshift
format Preprint
id arxiv_https___arxiv_org_abs_2506_12007
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SIMSHIFT: A Benchmark for Adapting Neural Surrogates to Distribution Shifts
Setinek, Paul
Galletti, Gianluca
Gross, Thomas
Schnürer, Dominik
Brandstetter, Johannes
Zellinger, Werner
Machine Learning
Computer Vision and Pattern Recognition
Computational Physics
Neural surrogates for Partial Differential Equations (PDEs) often suffer significant performance degradation when evaluated on problem configurations outside their training distribution, such as new initial conditions or structural dimensions. While Unsupervised Domain Adaptation (UDA) techniques have been widely used in vision and language to generalize across domains without additional labeled data, their application to complex engineering simulations remains largely unexplored. In this work, we address this gap through two focused contributions. First, we introduce SIMSHIFT, a novel benchmark dataset and evaluation suite composed of four industrial simulation tasks spanning diverse processes and physics: hot rolling, sheet metal forming, electric motor design and heatsink design. Second, we extend established UDA methods to state-of-the-art neural surrogates and systematically evaluate them. Extensive experiments on SIMSHIFT highlight the challenges of out-of-distribution neural surrogate modeling, demonstrate the potential of UDA in simulation, and reveal open problems in achieving robust neural surrogates under distribution shifts in industrially relevant scenarios. Our codebase is available at https://github.com/psetinek/simshift
title SIMSHIFT: A Benchmark for Adapting Neural Surrogates to Distribution Shifts
topic Machine Learning
Computer Vision and Pattern Recognition
Computational Physics
url https://arxiv.org/abs/2506.12007