Spin-off repository of Trixi.jl with neural network-based shock indicators.
**Note: This repository is currently not under development and has been archived. If you are interested in using any of this, please get in touch with the developers of the Trixi.jl package.
To run any of the elixirs with the neurl network-based indicators, you first need to install all required auxiliary packages by running the following code in the Julia REPL:
julia> using Pkg
julia> Pkg.add(["BSON", "Flux", "OrdinaryDiffEq", "Trixi"])Then, clone this repository
git clone [email protected]:trixi-framework/TrixiSmartShockFinder.jl.gitenter the directory, and start Julia (tested with Julia v1.9) with the project set to the clone directory
cd TrixiSmartShockFinder.jl
julia --project=.
Now run one of the elixirs in the examples folder, e.g.,
using TrixiSmartShockFinder
trixi_include("examples/tree_2d_dgsem/elixir_euler_blast_wave_neuralnetwork_perssonperaire.jl")TrixiSmartShockFinder.jl was initiated by Michael Schlottke-Lakemper (University of Augsburg, Germany) and Julia Odenthal (University of Cologne, Germany).
TrixiSmartShockFinder.jl is licensed under the MIT license (see LICENSE.md).