Scientific machine learning for closure models in multiscale problems: A review
Closure problems are omnipresent when simulating multiscale systems, where some
quantities and processes cannot be fully prescribed despite their effects on the simulation's …
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 …
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 …
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 …
essential for performance evaluation, estimating energy production, and implementing …
[HTML][HTML] Multi-fidelity physics constrained neural networks for dynamical systems
Physics-constrained neural networks are commonly employed to enhance prediction
robustness compared to purely data-driven models, achieved through the inclusion of …
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
Highly nonlinear dynamic finite element simulations using explicit time integration are
particularly valuable tools for structural analysis in fields like automotive, aerospace, and …
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 …
hierarchical and heterogeneous distribution characteristics. Specifically, high-fidelity design …
Recurrent Deep Kernel Learning of Dynamical Systems
Digital twins require computationally-efficient reduced-order models (ROMs) that can
accurately describe complex dynamics of physical assets. However, constructing ROMs from …
accurately describe complex dynamics of physical assets. However, constructing ROMs from …
Accelerated construction of projection-based reduced-order models via incremental approaches
We present an accelerated greedy strategy for training of projection-based reduced-order
models for parametric steady and unsteady partial differential equations. Our approach …
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 …
the torque of a permanent magnet synchronous machine under geometric design variations …