openclimatefix-models/cloudcasting_uk

1---2language: en3library_name: pytorch4license: mit5---6 7 8# Cloudcasting9 10## Model Description11 12<!-- Provide a longer summary of what this model is/does. -->13This model is trained to predict future frames of satellite data from past frames. It takes 3 hours14of recent satellkite imagery at 15 minute intervals and predicts 3 hours into the future also at1515 minute intervals. The satellite inputs and predictions are multispectral with 11 channels.16 17 18See [1] for the repo used to train the model.19 20- **Developed by:** Open Climate Fix and the Alan Turing Institute21- **License:** mit22 23 24# Training Details25 26## Data27 28<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->29This was trained on EUMETSAT satellite imagery derived from the data stored in [this google public 30dataset](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). 31 32The data was processed using the protocol in [2]33 34 35 36## Results37 38The training logs for the current model can be found here:39- https://wandb.ai/openclimatefix/sat_pred/runs/xlq6w7qj40 41 42### Software43 44- [1] https://github.com/openclimatefix/sat_pred45- [2] https://github.com/alan-turing-institute/cloudcasting