graph_weather

graph_weather copied to clipboard

# Pull Request ## Description _Please delete the italicised instruction text! Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context....

branberry

## Detailed Description https://github.com/pyg-team/pytorch_geometric/releases/tag/2.2.0 ## Context New version has improvements for working on larger-than-memory graphs, etc. which might be helpful here, and also the speed ups that should be included....

jacobbieker

Add support for training on Google's ARCO ERA5

4

## Detailed Description The Google ERA5 archive is available: https://github.com/google-research/ARCO-ERA5 and goes back quite far. Its currently being expanded, but already covers years of data at the native model resolution....

jacobbieker

[Paper] Generating physically-consistent high-resolution climate data with hard-constrained neural networks

4

https://www.climatechange.ai/papers/aaaifss2022/5 Interesting work on making sure the outputs of high-resolution models are physically consistent. Might be good to include some of their work in this

jacobbieker

Perform Data Assimilation with model

4

## Detailed Description One of the most compute intensive steps in NWPs is doing the data assimilation to create the starting conditions for running the simulation. This type of model...

jacobbieker

More efficent way of encoding input graph/output graph?

2

Currently, one of the issues with this implementation is that when there are a large amounts of input lat/lon coordinates (such as a 1 deg grid or smaller), the graphs...

jacobbieker

**Describe the bug** The Encoder's scatter_sum results in the input graph not matching the new graph, and being off by a little bite in the first dimension. This results in...

jacobbieker

[Paper] FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators

2

Another interesting-looking paper! https://arxiv.org/abs/2202.11214 To quote the abstract: > FourCastNet, short for Fourier Forecasting Neural Network, is a global data-driven weather forecasting model that provides accurate short to medium-range global...

JackKelly

Add TPU support

6

## Detailed Description Currently, the graph neural network library dependencies don't support TPUs with pytorch geometric, or don't seem to at least because of custom kernels. We could add a...

jacobbieker

latent graph structure - Encoder.forward()

4

@jacobbieker - Hi, I've been looking at the GNN encoder / decoder code to try to understand the overall logic and structure (I'm new to pytorch-geometric). I'm not quite able...

mishooax