trainsn/GNN-Surrogate
GNN-Surrogate: A Hierarchical and Adaptive Graph Neural Network for Parameter Space Exploration of Unstructured-Mesh Ocean Simulations - Source Code
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.
Stars
26
Forks
3
Language
C++
License
MIT
Category
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.
Higher-rated alternatives
pyg-team/pytorch_geometric
Graph Neural Network Library for PyTorch
a-r-j/graphein
Protein Graph Library
raamana/graynet
Subject-wise networks from structural MRI, both vertex- and voxel-wise features (thickness, GM...
pykale/pykale
Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for...
dmlc/dgl
Python package built to ease deep learning on graph, on top of existing DL frameworks.