https://github.com/openclimatefix/graph_weather

PyTorch implementation of Ryan Keisler's 2022 "Forecasting Global Weather with Graph Neural Networks" paper (https://arxiv.org/abs/2202.07575)
https://github.com/openclimatefix/graph_weather

forecasting-models graph-neural-networks pytorch weather

Last synced: 9 days ago
JSON representation

PyTorch implementation of Ryan Keisler's 2022 "Forecasting Global Weather with Graph Neural Networks" paper (https://arxiv.org/abs/2202.07575)

• Host: GitHub
• URL: https://github.com/openclimatefix/graph_weather
• Owner: openclimatefix
• License: mit
• Created: 2022-02-21T10:52:02.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-10-28T17:55:20.000Z (11 days ago)
• Last Synced: 2024-10-29T21:01:43.969Z (10 days ago)
• Topics: forecasting-models, graph-neural-networks, pytorch, weather
• Language: Python
• Homepage:
• Size: 5.41 MB
• Stars: 192
• Watchers: 8
• Forks: 50
• Open Issues: 55
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• open-sustainable-technology - Graph Weather - Data-driven approach for forecasting global weather using graph neural network. (Atmosphere / Meteorological Observation and Forecast)

README

        
# Graph Weather

[![All Contributors](https://img.shields.io/badge/all_contributors-11-orange.svg?style=flat-square)](#contributors-)

Implementation of the Graph Weather paper (https://arxiv.org/pdf/2202.07575.pdf) in PyTorch. Additionally, an implementation

of a modified model that assimilates raw or processed observations into analysis files.

## Installation

This library can be installed through

```bash

pip install graph-weather

```

## Example Usage

The models generate the graphs internally, so the only thing that needs to be passed to the model is the node features

in the same order as the ```lat_lons```.

```python

import torch

from graph_weather import GraphWeatherForecaster

from graph_weather.models.losses import NormalizedMSELoss

lat_lons = []

for lat in range(-90, 90, 1):

    for lon in range(0, 360, 1):

        lat_lons.append((lat, lon))

model = GraphWeatherForecaster(lat_lons)

# Generate 78 random features + 24 non-NWP features (i.e. landsea mask)

features = torch.randn((2, len(lat_lons), 102))

target = torch.randn((2, len(lat_lons), 78))

out = model(features)

criterion = NormalizedMSELoss(lat_lons=lat_lons, feature_variance=torch.randn((78,)))

loss = criterion(out, target)

loss.backward()

```

And for the assimilation model, which assumes each lat/lon point also has a height above ground, and each observation

is a single value + the relative time. The assimlation model also assumes the desired output grid is given to it as

well.

```python

import torch

import numpy as np

from graph_weather import GraphWeatherAssimilator

from graph_weather.models.losses import NormalizedMSELoss

obs_lat_lons = []

for lat in range(-90, 90, 7):

    for lon in range(0, 180, 6):

        obs_lat_lons.append((lat, lon, np.random.random(1)))

    for lon in 360 * np.random.random(100):

        obs_lat_lons.append((lat, lon, np.random.random(1)))

output_lat_lons = []

for lat in range(-90, 90, 5):

    for lon in range(0, 360, 5):

        output_lat_lons.append((lat, lon))

model = GraphWeatherAssimilator(output_lat_lons=output_lat_lons, analysis_dim=24)

features = torch.randn((1, len(obs_lat_lons), 2))

lat_lon_heights = torch.tensor(obs_lat_lons)

out = model(features, lat_lon_heights)

assert not torch.isnan(out).all()

assert out.size() == (1, len(output_lat_lons), 24)

criterion = torch.nn.MSELoss()

loss = criterion(out, torch.randn((1, len(output_lat_lons), 24)))

loss.backward()

```

## Pretrained Weights

Coming soon! We plan to train a model on GFS 0.25 degree operational forecasts, as well as MetOffice NWP forecasts.

We also plan trying out adaptive meshes, and predicting future satellite imagery as well.

## Training Data

Training data will be available through HuggingFace Datasets for the GFS forecasts. The initial set of data is available for [GFSv16 forecasts, raw observations, and FNL Analysis files from 2016 to 2022](https://huggingface.co/datasets/openclimatefix/gfs-reforecast), and for [ERA5 Reanlaysis](https://huggingface.co/datasets/openclimatefix/era5-reanalysis). MetOffice NWP forecasts we cannot

redistribute, but can be accessed through [CEDA](https://data.ceda.ac.uk/).

## Contributors ✨

Thanks goes to these wonderful people ([emoji key](https://allcontributors.org/docs/en/emoji-key)):

  

    

      
Jacob Bieker
💻

      
Jack Kelly
🤔

      
byphilipp
🤔

      
Markus Kaukonen
💬

      
MoHawastaken
🐛

      
Mihai
💬

      
Vitus Benson
🐛

    

    

      
dongZheX
💬

      
sabbir2331
💬

      
Lorenzo Breschi
💻

      
gbruno16
💻

    

  

This project follows the [all-contributors](https://github.com/all-contributors/all-contributors) specification. Contributions of any kind welcome!