Scientific machine learning for closure models in multiscale problems: A review

B Sanderse, P Stinis, R Maulik, SE Ahmed - arXiv preprint arXiv …, 2024 - arxiv.org
Closure problems are omnipresent when simulating multiscale systems, where some
quantities and processes cannot be fully prescribed despite their effects on the simulation's …

[HTML][HTML] ModelFLOWs-app: data-driven post-processing and reduced order modelling tools

A Hetherington, A Corrochano… - Computer Physics …, 2024 - Elsevier
This article presents an innovative open-source software named ModelFLOWs-app, 1
written in Python, which has been created and tested to generate precise and robust hybrid …

Study on rapid prediction of flow field in a knudsen compressor based on multi-fidelity reduced-order models

Q Xiao, D Zeng, Z Yu, S Zou, Z Liu - International Journal of Hydrogen …, 2024 - Elsevier
The safe and stable operation of a hydrogen Knudsen compressor is essential for
transporting hydrogen in microfluidic systems. This study uses proper orthogonal …

[HTML][HTML] Multi-fidelity surrogate modeling of nonlinear dynamic responses in wave energy farms

C Stavropoulou, E Katsidoniotaki, N Faedo… - Applied Energy, 2025 - Elsevier
In wave energy farms, accurately determining the motion of each wave energy converter is
essential for performance evaluation, estimating energy production, and implementing …

[HTML][HTML] Multi-fidelity physics constrained neural networks for dynamical systems

H Zhou, S Cheng, R Arcucci - Computer Methods in Applied Mechanics …, 2024 - Elsevier
Physics-constrained neural networks are commonly employed to enhance prediction
robustness compared to purely data-driven models, achieved through the inclusion of …

Multi-hierarchical surrogate learning for explicit structural dynamical systems using graph convolutional neural networks

J Kneifl, J Fehr, SL Brunton, JN Kutz - Computational Mechanics, 2024 - Springer
Highly nonlinear dynamic finite element simulations using explicit time integration are
particularly valuable tools for structural analysis in fields like automotive, aerospace, and …

Gaussian process fusion method for multi-fidelity data with heterogeneity distribution in aerospace vehicle flight dynamics

B Yang, B Chen, Y Liu, J Chen - Engineering Applications of Artificial …, 2024 - Elsevier
In the engineering design of aerospace vehicles, design data at different stages exhibit
hierarchical and heterogeneous distribution characteristics. Specifically, high-fidelity design …

Recurrent Deep Kernel Learning of Dynamical Systems

N Botteghi, P Motta, A Manzoni, P Zunino… - arXiv preprint arXiv …, 2024 - arxiv.org
Digital twins require computationally-efficient reduced-order models (ROMs) that can
accurately describe complex dynamics of physical assets. However, constructing ROMs from …

Accelerated construction of projection-based reduced-order models via incremental approaches

E Agouzal, T Taddei - Advanced Modeling and Simulation in Engineering …, 2024 - Springer
We present an accelerated greedy strategy for training of projection-based reduced-order
models for parametric steady and unsteady partial differential equations. Our approach …

Fourier-enhanced reduced-order surrogate modeling for uncertainty quantification in electric machine design

A Partovizadeh, S Schöps, D Loukrezis - arXiv preprint arXiv:2412.06485, 2024 - arxiv.org
This work proposes a data-driven surrogate modeling framework for cost-effectively inferring
the torque of a permanent magnet synchronous machine under geometric design variations …