activity
20242026
most citedAccelerating Full Waveform Inversion By Transfer Learning

2 citations · 2 across the 2 of their papers we have counts for

collaborators

5 papers

cond-mat.mtrl-sci2026

Machine Learning Inference Limits of Routine Cement Characterization for CEM I Performance: Evidence From a Multi-Producer Dataset

Marchellino Ghorayeb, Christiane Rößler, Horst-Michael Ludwig +2

Routine cement performance characterization provides continuous quality control data, but its information content for performance inference and transferability across independent p…

math.NA2026

Lightweight return-mapping surrogates for multiscale plasticity: a practical guide

Alireza Daneshyar, Leon Herrmann, Stefan Kollmannsberger

This paper presents a practical guide to building lightweight neural-network surrogates for the plastic return-mapping process in concurrent multiscale (FE2) simulations. Rather th…

cs.CE2025

A Memory Efficient Adjoint Method to Enable Billion Parameter Optimization on a Single GPU in Dynamic Problems

Leon Herrmann, Tim Bürchner, László Kudela +1

Dynamic optimization is currently limited by sensitivity computations that require information from full forward and adjoint wave fields. Since the forward and adjoint solutions ar…

cs.LG20242 cited

Accelerating Full Waveform Inversion By Transfer Learning

Divya Shyam Singh, Leon Herrmann, Qing Sun +3

Full waveform inversion (FWI) is a powerful tool for reconstructing material fields based on sparsely measured data obtained by wave propagation. For specific problems, discretizin…

cs.LG2024

Neural Networks for Generating Better Local Optima in Topology Optimization

Leon Herrmann, Ole Sigmund, Viola Muning Li +2

Neural networks have recently been employed as material discretizations within adjoint optimization frameworks for inverse problems and topology optimization. While advantageous re…