trainsn/GNN-Surrogate

GNN-Surrogate: A Hierarchical and Adaptive Graph Neural Network for Parameter Space Exploration of Unstructured-Mesh Ocean Simulations - Source Code

33
/ 100
Emerging

This project helps oceanographers and climate scientists rapidly explore how different ocean simulation parameters affect their models. It takes raw MPAS-Ocean mesh data and simulation outputs, then uses a specialized neural network to quickly predict how changes in parameters would alter simulation results, without needing to run full, time-consuming simulations. The output is predicted ocean temperature fields and other data within an MPAS NetCDF file.

No commits in the last 6 months.

Use this if you need to quickly understand the impact of various physical parameters on unstructured-mesh ocean simulations, reducing the need for extensive, costly computational runs.

Not ideal if you need to simulate aspects of ocean behavior beyond temperature fields or if you are not working with MPAS-Ocean simulations.

oceanography climate modeling ocean simulation parameter exploration scientific computing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

26

Forks

3

Language

C++

License

MIT

Last pushed

Jun 04, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/trainsn/GNN-Surrogate"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.