Direct numerical simulation of turbulent boundary layers at ReTau180

A large-scale benchmark for machine learning methods in fluid dynamics

fork of neko for PR purposes

Experimental next version of our stability toolbox for Nek5000 based on LightKrylov library

Model-Order Reduction Framework for Nek5000

A course in turbulence simulation

The MegaFlow2D dataset package

MODULO (MODal mULtiscale pOd) is a software developed at the von Karman Institute to perform Multiscale Modal Analysis of numerical and experimental data using the mPOD.

UQpy (Uncertainty Quantification with python) is a general purpose Python toolbox for modeling uncertainty in physical and mathematical systems.

A model demo which uses ResNet18 as the backbone to do image recognition tasks.Using Pytorch.

Differentiable Fluid Dynamics Package

Integrate the DeepSeek API into popular softwares

Advanced modeling of turbulence in CFD via the integration of Deep Learning technologies (PINNs and SINDy) trained on DNS data allowing a reduction of the RMSE of 81.29% for Channel data and 90.3% …

This codes calculates the dimensionalized POD and uses SINDy from the PySINDy python package to build a data-driven model for it. The code is used for NIMROD simulations of the HIT-SI experiment an…

Code for paper Sparse identification of nonlinear dynamics with Shallow Recurrent Decoder Networks.

A package for the sparse identification of nonlinear dynamical systems from data

Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems

This repository hold some techniques associated with Artificial Intelligence to examine the aerodynamics of airfoils

Mini Project for using POD for dimensionality reduction and then forecasting using RNN in this reduced dimensional space.

Parallel Orthogonal Deep Neural Network

Proper Orthogonal Decomposition - Radial Basis Function (POD-RBF) Network

Python tools for non-intrusive reduced order modeling

Multi-fidelity reduced-order surrogate modeling

POD-RNN and CRAN

Python code to calculate proper orthogonal decomposition modes (aka principal components), which are then used to generate reduced order models of the system dynamics.

Reduced Order Model Predictive Control

GCA-ROM is a library which implements graph convolutional autoencoder architecture as a nonlinear model order reduction strategy.