Non-Intrusive Surrogate Modelling Using Sparse Random Features With Applications in Crashworthiness Analysis

MCML Authors

Felix Krahmer

Prof. Dr.

Principal Investigator

Optimization & Data Analysis

Anna Veselovska

Dr.

→ Group Massimo Fornasier
 Applied Numerical Analysis

Abstract

Efficient surrogate modelling is a key requirement for uncertainty quantification in data-driven scenarios. In this work, a novel approach of using Sparse Random Features for surrogate modelling in combination with self-supervised dimensionality reduction is described. The method is compared to other methods on synthetic and real data obtained from crashworthiness analyses. The results show a superiority of the here described approach over state of the art surrogate modelling techniques, Polynomial Chaos Expansions and Neural Networks.

article

---

International Journal for Uncertainty Quantification

15.4. Mar. 2025.

---

Authors

M. Herold • J. S. Jehle • F. Krahmer • A. Veselovska

---

Links

DOI

---

Research Area

 A2 | Mathematical Foundations