Notebooks & Codes

Explore Interactive Tutorials and Python Implementations

Welcome to our collection of Jupyter notebooks, research codes, and reference implementations. These resources provide practical examples of ModelFLOWs methodologies, including modal decomposition, reduced-order modeling, deep learning, forecasting, data assimilation, and CFD applications. Select a resource below to explore the code, methodology, and results.

Modal Decomposition

Topic: Modal Decomposition

Modal decomposition of complex dynamical systems.

View Notebook

Reduced-Order Deep Learning

Topic: Deep Learning

Hybrid POD-DL and latent-space learning approaches for complex dynamical systems.

View Notebook

Data Assimilation

Topic: Data Assimilation

Tools to combine experimental data with numerical models to refine predictions.

View Notebook

AI-Accelerated CFD

Topic: Hybrid AI-CFD

Accelerate computational fluid dynamics simulations using hybrid POD–Deep Learning reduced-order models.

View Notebook