This model is trained to predict future frames of satellite data from past frames. It takes 3 hours of recent satellkite 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.

This was trained on EUMETSAT satellite imagery derived from the data stored in this google public dataset.

The data was processed using the protocol in [2]

The training logs for the current model can be found here: