---
language: en
license: mit
library_name: pytorch
---


# Cloudcasting

## Model Description

These models are trained to predict future frames of satellite data from past frames. The model uses 3 hours
of recent satellite imagery at 15 minute intervals and predicts 3 hours into the future also at
15 minute intervals. The satellite inputs and predictions are multispectral with 11 channels.


See [1] for the repo used to train the model.

- **Developed by:** Open Climate Fix and the Alan Turing Institute
- **License:** mit


# Training Details

## Data

This was trained on EUMETSAT satellite imagery derived from the data stored in [this google public 
dataset](https://console.cloud.google.com/marketplace/product/bigquery-public-data/eumetsat-seviri-rss?hl=en-GB&inv=1&invt=AbniZA&project=solar-pv-nowcasting&pli=1). 

The data was processed using the protocol in [2]


## Results

See the READMEs in each model dir for links to the wandb training runs


## Usage

These models rely on [1] being installed. Example usage to load the model is shown below

```{python}
import hydra
import yaml
from huggingface_hub import snapshot_download
from safetensors.torch import load_model


REPO_ID = "openclimatefix/cloudcasting_example_models"
REVISION = <commit-id>
MODEL = "simvp_model"

# Download the model checkpoints
hf_download_dir = snapshot_download(
    repo_id=REPO_ID,
    revision=REVISION,
)

# Create the model object
with open(f"{hf_download_dir}/model_config.yaml", "r", encoding="utf-8") as f:
    model = hydra.utils.instantiate(yaml.safe_load(f))

# Load the model weights
load_model(
    model,
    filename=f"{hf_download_dir}/model.safetensors", 
    strict=True,
)
```

### Software

- [1] https://github.com/openclimatefix/sat_pred
- [2] https://github.com/alan-turing-institute/cloudcasting