There are 3 repositories under reduced-order-modeling topic.
One-dimensional unsteady compressible reacting flow simulation framework, designed for simple prototyping and testing of novel reduced-order model methods.
Source code for POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decomposition. Available on doi.org/10.1016/j.cma.2021.114181.
Non-intrusive reduced order models using proper orthogonal decomposition (POD) and radial basis function (RBF) interpolation for shallow water equations
OpenFOAM examples for data-driven ML and ROM
Reduced Order Models in a scikit-learn approach.
Framework to learn effective dynamics and couple a macro scale simulator with a fast neural network latent propagator.
Non-intrusive reduced-order modeling with geometry-informed snapshots. Current based registration is applied to compute the diffeomorphism between snapshots.
A Surrogate Modeling Framework for the Phase-Field Simulation.
Code TMA4900 Industrial Mathematics, Master’s Thesis
Supplemental Material for "BUQEYE Guide to Projection-Based Emulators in Nuclear Physics"
Code for building a reduced-order model for the linear elasticity equation on a square in 2D for my specialization Project at NTNU.
Neural network pruning to reduce the size of Neural Implicit Flow network.