[HTML][HTML] Towards optimal β-variational autoencoders combined with transformers for reduced-order modelling of turbulent flows

Y Wang, A Solera-Rico, CS Vila, R Vinuesa - International Journal of Heat …, 2024 - Elsevier
Variational autoencoders (VAEs) have shown promising potential as artificial neural
networks (NN) for developing reduced-order models (ROMs) in the context of turbulent …

Deep learning combined with singular value decomposition to reconstruct databases in fluid dynamics

P Díaz-Morales, A Corrochano, M López-Martín… - Expert Systems with …, 2024 - Elsevier
Fluid dynamics problems are characterized by being multidimensional and nonlinear.
Therefore, experiments and numerical simulations are complex and time-consuming …

[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 …

Exploring the efficacy of a hybrid approach with modal decomposition over fully deep learning models for flow dynamics forecasting

R Abadía-Heredia, A Corrochano… - arXiv preprint arXiv …, 2024 - arxiv.org
Fluid dynamics problems are characterized by being multidimensional and nonlinear,
causing the experiments and numerical simulations being complex, time-consuming and …

Stability analysis of chaotic systems in latent spaces

E Özalp, L Magri - arXiv preprint arXiv:2410.00480, 2024 - arxiv.org
Partial differential equations, and their chaotic solutions, are pervasive in the modelling of
complex systems in engineering, science, and beyond. Data-driven methods can find …

Mode selection in concentric jets: the steady–steady 1: 2 resonant mode interaction with O (2) symmetry

A Corrochano, J Sierra-Ausín, JA Martin… - Journal of Fluid …, 2023 - cambridge.org
The linear and nonlinear stability of two concentric jets separated by a duct wall is analysed
by means of global linear stability and weakly nonlinear analysis. Three governing …