Review of multi-fidelity models

MG Fernández-Godino - arxiv preprint arxiv:1609.07196, 2016 - arxiv.org
This article provides an overview of multi-fidelity modeling trends. Fidelity in modeling refers
to the level of detail and accuracy provided by a predictive model or simulation. Generally …

Enhanced Kriging leave-one-out cross-validation in improving model estimation and optimization

Y Pang, Y Wang, X Lai, S Zhang, P Liang… - Computer Methods in …, 2023 - Elsevier
Leave-one-out cross-validation (LOOCV) is a widely used technique in model estimation
and selection of the Kriging surrogate model for engineering problems, such as structural …

Multi-fidelity surrogate modeling using long short-term memory networks

P Conti, M Guo, A Manzoni, JS Hesthaven - Computer methods in applied …, 2023 - Elsevier
When evaluating quantities of interest that depend on the solutions to differential equations,
we inevitably face the trade-off between accuracy and efficiency. Especially for …

Hyperparameter-optimized multi-fidelity deep neural network model associated with subset simulation for structural reliability analysis

JPS Lima, F Evangelista Jr, CG Soares - Reliability Engineering & System …, 2023 - Elsevier
The present study proposes a two-stage Bi-Fidelity Deep Neural Network surrogate model to
quantify the uncertainty of structural analysis using low-fidelity data samples added to the …

[PDF][PDF] Disentangled multi-fidelity deep bayesian active learning. In International Conference on Machine Learning

D Wu, R Niu, M Chinazzi, Y Ma, R Yu - 2023 - par.nsf.gov
To balance quality and cost, various domain areas of science and engineering run
simulations at multiple levels of sophistication. Multi-fidelity active learning aims to learn a …

On-line transfer learning for multi-fidelity data fusion with ensemble of deep neural networks

Z Li, S Zhang, H Li, K Tian, Z Cheng, Y Chen… - Advanced Engineering …, 2022 - Elsevier
Abstract Deep Neural Network (DNN) is widely used in engineering applications for its
ability to handle problems with almost any nonlinearities. However, it is generally difficult to …

Multi-fidelity reduced-order surrogate modelling

P Conti, M Guo, A Manzoni, A Frangi… - … of the Royal …, 2024 - royalsocietypublishing.org
High-fidelity numerical simulations of partial differential equations (PDEs) given a restricted
computational budget can significantly limit the number of parameter configurations …

Embedding prior knowledge into data-driven structural performance prediction to extrapolate from training domains

SZ Chen, SY Zhang, DC Feng… - Journal of Engineering …, 2023 - ascelibrary.org
Abstract Machine learning (ML)–based data-driven approaches have become increasingly
prevalent for predicting structural performance. Because a properly trained ML model can …

[HTML][HTML] A multi-fidelity surrogate model for structural health monitoring exploiting model order reduction and artificial neural networks

M Torzoni, A Manzoni, S Mariani - Mechanical Systems and Signal …, 2023 - Elsevier
Stochastic approaches to structural health monitoring (SHM) are often inevitably limited by
computational constraints. For instance, for Markov chain Monte Carlo algorithms relying …

An extended physics informed neural network for preliminary analysis of parametric optimal control problems

N Demo, M Strazzullo, G Rozza - Computers & Mathematics with …, 2023 - Elsevier
In this work we propose an application of physics informed supervised learning strategies to
parametric partial differential equations. Indeed, even if the latter are indisputably useful in …