works on

From the 1 of 7 linked papers with an AI index.

activity
20242026
collaborators

7 papers

cs.LG2026

Microstructure-Conditioned Surrogate Models for Graded Multiscale Optimization of Mycelium Composites

J. Storm, I. B. C. M. Rocha, S. Schyck +2

The paper introduces a hypernetwork‑conditioned surrogate model that predicts the mechanical behavior of mycelium‑woodchip composites across varying microstructures, enabling effic…

stat.CO2026

Piecewise Deterministic Markov Processes for Bayesian Inference of PDE Coefficients

Leon Riccius, Iuri B. C. M. Rocha, Joris Bierkens +2

We develop a general framework for piecewise deterministic Markov process (PDMP) samplers that enables efficient Bayesian inference in non-linear inverse problems with expensive li…

cond-mat.dis-nn2025

Uncertainty Quantification in Multiscale Modeling of Polymer Composite Materials Using Physically Recurrent Neural Networks

N. Kovács, I. B. C. M. Rocha, F. P. van der Meer +2

This study investigates whether Physically Recurrent Neural Networks (PRNNs), a recent surrogate model for heterogeneous materials, trained on a micromodel with fixed material para…

physics.comp-ph2025

Multiscale Analysis of Woven Composites Using Hierarchical Physically Recurrent Neural Networks

Ehsan Ghane, Marina A. Maia, Iuri B. C. M. Rocha +2

Multiscale homogenization of woven composites requires detailed micromechanical evaluations, leading to high computational costs. Data-driven surrogate models based on neural netwo…

math.NA2025

Surrogate-based multiscale analysis of experiments on thermoplastic composites under off-axis loading

M. A. Maia, I. B. C. M. Rocha, D. Kovačević +1

In this paper, we present a surrogate-based multiscale approach to model constant strain-rate and creep experiments on unidirectional thermoplastic composites under off-axis loadin…

physics.comp-ph2024

Integration of Active Learning and MCMC Sampling for Efficient Bayesian Calibration of Mechanical Properties

Leon Riccius, Iuri B. C. M. Rocha, Joris Bierkens +2

Recent advancements in Markov chain Monte Carlo (MCMC) sampling and surrogate modelling have significantly enhanced the feasibility of Bayesian analysis across engineering fields.…