metnet

PyTorch Implementation of Google Research's MetNet and MetNet-2

https://github.com/openclimatefix/metnet

Science Score: 36.0%

This score indicates how likely this project is to be science-related based on various indicators:

○
CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
✓
Academic publication links
Links to: arxiv.org
○
Committers with academic emails
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (12.3%) to scientific vocabulary

Keywords

pytorch

Keywords from Contributors

pytorch-lightning pytorch-implementation nowcasting-precipitation nowcasting-models nowcasting gan eumetsat particles battery climate-model

Last synced: 9 months ago · JSON representation

Repository

PyTorch Implementation of Google Research's MetNet and MetNet-2

Basic Info

Host: GitHub
Owner: openclimatefix
License: mit
Language: Python
Default Branch: main
Homepage:
Size: 185 KB

Statistics

Stars: 271
Watchers: 5
Forks: 53
Open Issues: 34
Releases: 43

Topics

pytorch

Created almost 5 years ago · Last pushed 9 months ago

Metadata Files

Readme License

MetNet and MetNet-2

PyTorch Implementation of Google Research's MetNet for short term weather forecasting (https://arxiv.org/abs/2003.12140), inspired from https://github.com/tcapelle/metnetpytorch/tree/master/metnetpytorch

MetNet-2 (https://arxiv.org/pdf/2111.07470.pdf) is a further extension of MetNet that takes in a larger context image to predict up to 12 hours ahead, and is also implemented in PyTorch here.

Installation

Clone the repository, then run shell pip install -r requirements.txt pip install -e .`

Alternatively, you can also install a usually older version through pip install metnet

Please ensure that you're using Python version 3.9 or above.

Data

While the exact training data used for both MetNet and MetNet-2 haven't been released, the papers do go into some detail as to the inputs, which were GOES-16 and MRMS precipitation data, as well as the time period covered. We will be making those splits available, as well as a larger dataset that covers a longer time period, with HuggingFace Datasets! Note: The dataset is not available yet, we are still processing data!

```python from datasets import load_dataset

dataset = load_dataset("openclimatefix/goes-mrms") ```

This uses the publicly avaiilable GOES-16 data and the MRMS archive to create a similar set of data to train and test on, with various other splits available as well.

Pretrained Weights

Pretrained model weights for MetNet and MetNet-2 have not been publicly released, and there is some difficulty in reproducing their training. We release weights for both MetNet and MetNet-2 trained on cloud mask and satellite imagery data with the same parameters as detailed in the papers on HuggingFace Hub for MetNet and MetNet-2. These weights can be downloaded and used using:

python from metnet import MetNet, MetNet2 model = MetNet().from_pretrained("openclimatefix/metnet") model = MetNet2().from_pretrained("openclimatefix/metnet-2")

Example Usage

MetNet can be used with:

```python from metnet import MetNet import torch import torch.nn.functional as F

model = MetNet( hiddendim=32, forecaststeps=24, inputchannels=16, outputchannels=12, satchannels=12, inputsize=32, )

MetNet expects original HxW to be 4x the input size

x = torch.randn((2, 12, 16, 128, 128)) out = [] for leadtime in range(24): out.append(model(x, leadtime)) out = torch.stack(out, dim=1)

MetNet creates predictions for the center 1/4th

y = torch.randn((2, 24, 12, 8, 8)) F.mse_loss(out, y).backward() ```

And MetNet-2 with:

```python from metnet import MetNet2 import torch import torch.nn.functional as F

model = MetNet2( forecaststeps=8, inputsize=64, numinputtimesteps=6, upsamplerchannels=128, lstmchannels=32, encoderchannels=64, centercrop_size=16, )

MetNet expects original HxW to be 4x the input size

x = torch.randn((2, 6, 12, 256, 256)) out = [] for leadtime in range(8): out.append(model(x, leadtime)) out = torch.stack(out, dim=1) y = torch.rand((2,8,12,64,64)) F.mse_loss(out, y).backward() ```

Contributors ✨

Thanks goes to these wonderful people (emoji key):

_{Jacob Bieker}
💻

_{Jack Kelly}
💻

_{Valter Fallenius}
📓

_terigenbuaa
💬

_Kan.Dai
💬

_{Sailesh Bechar}
💬

_{Rahul Maurya}
⚠️

This project follows the all-contributors specification. Contributions of any kind welcome!

Owner

Name: Open Climate Fix
Login: openclimatefix
Kind: organization
Email: info@openclimatefix.org
Location: London

Website: openclimatefix.org
Twitter: openclimatefix
Repositories: 88
Profile: https://github.com/openclimatefix

Using open science to mitigate climate change

GitHub Events

Total

Create event: 1
Release event: 1
Issues event: 2
Watch event: 34
Issue comment event: 18
Push event: 47
Pull request event: 1
Pull request review event: 3
Pull request review comment event: 11
Fork event: 5

Last Year

Create event: 1
Release event: 1
Issues event: 2
Watch event: 34
Issue comment event: 18
Push event: 47
Pull request event: 1
Pull request review event: 3
Pull request review comment event: 11
Fork event: 5

Committers

Last synced: 10 months ago

All Time

Total Commits: 166
Total Committers: 9
Avg Commits per committer: 18.444
Development Distribution Score (DDS): 0.53

Past Year

Commits: 2
Committers: 2
Avg Commits per committer: 1.0
Development Distribution Score (DDS): 0.5

Top Committers

Name	Email	Commits
Jacob Bieker	j**b@b**h	78
BumpVersion Action	b**n@g**s	37
Raahul Singh	r**2@g**m	19
allcontributors[bot]	4****]	14
pre-commit-ci[bot]	6****]	13
peterdudfield	p**d@h**m	2
Rahul Maurya	9****b	1
Jack Kelly	j**k@O**g	1
Database Missing no1	9****e	1

Committer Domains (Top 20 + Academic)

openclimatefix.org: 1 bieker.tech: 1

Issues and Pull Requests

Last synced: 9 months ago

All Time

Total issues: 34
Total pull requests: 31
Average time to close issues: 2 months
Average time to close pull requests: 25 days
Total issue authors: 20
Total pull request authors: 9
Average comments per issue: 2.97
Average comments per pull request: 1.48
Merged pull requests: 26
Bot issues: 0
Bot pull requests: 12

Past Year

Issues: 4
Pull requests: 2
Average time to close issues: N/A
Average time to close pull requests: 3 days
Issue authors: 4
Pull request authors: 1
Average comments per issue: 0.75
Average comments per pull request: 11.5
Merged pull requests: 2
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

jacobbieker (10)
ValterFallenius (4)
peterdudfield (2)
JackKelly (2)
ShileiCao (1)
CUITCHENSIYU (1)
codeastra2 (1)
NMC-DAVE (1)
terigenbuaa (1)
Nagessen (1)
lucasbs97 (1)
Raahul-Singh (1)
jramosss (1)
SaileshBechar (1)
dsuhoi (1)

Pull Request Authors

jacobbieker (11)
allcontributors[bot] (7)
pre-commit-ci[bot] (4)
Averagenormaljoe (2)
rahul-maurya11b (2)
ValterFallenius (1)
peterdudfield (1)
JackKelly (1)
Raahul-Singh (1)

Top Labels

Issue Labels

enhancement (16) bug (10) good first issue (4) documentation (2)

Pull Request Labels

enhancement (7)

Packages

Total packages: 2
Total downloads:
- pypi 338 last-month

Total dependent packages: 0
(may contain duplicates)
Total dependent repositories: 2
(may contain duplicates)
Total versions: 86
Total maintainers: 2

proxy.golang.org: github.com/openclimatefix/metnet

Documentation: https://pkg.go.dev/github.com/openclimatefix/metnet#section-documentation
License: mit
Latest release: v4.1.18+incompatible
published about 1 year ago

Versions: 44
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Dependent packages count: 5.4%

Average: 5.6%

Dependent repos count: 5.8%

Last synced: 9 months ago

pypi.org: metnet

PyTorch MetNet Implementation

Homepage: https://github.com/openclimatefix/metnet
Documentation: https://metnet.readthedocs.io/
License: MIT License
Latest release: 4.1.18
published about 1 year ago

Versions: 42
Dependent Packages: 0
Dependent Repositories: 2
Downloads: 338 Last month

Rankings

Stargazers count: 5.7%

Forks count: 6.4%

Dependent packages count: 7.3%

Average: 8.3%

Downloads: 10.5%

Dependent repos count: 11.8%

Maintainers (2)

jacobbieker openclimatefix

Last synced: 9 months ago

Dependencies

requirements.txt pypi

antialiased_cnns *
axial_attention *
einops >=0.3.0
huggingface_hub *
numpy >=1.19.5
pytorch_msssim *
torchvision >=0.10.0

.github/workflows/release.yaml actions

.github/workflows/workflows.yaml actions

setup.py pypi

metnet

Science Score: 36.0%

Keywords

Keywords from Contributors

Repository

Basic Info

Statistics

Topics

Metadata Files

README.md

MetNet and MetNet-2

Installation

Data

Pretrained Weights

Example Usage

MetNet expects original HxW to be 4x the input size

MetNet creates predictions for the center 1/4th

MetNet expects original HxW to be 4x the input size

Contributors ✨

Owner

GitHub Events

Total

Last Year

Committers

All Time

Past Year

Top Committers

Committer Domains (Top 20 + Academic)

Issues and Pull Requests

All Time

Past Year

Top Authors

Issue Authors

Pull Request Authors

Top Labels

Issue Labels

Pull Request Labels

Packages

proxy.golang.org: github.com/openclimatefix/metnet

Rankings

pypi.org: metnet

Rankings

Maintainers (2)

Dependencies