The dataset contains trained ConvLSTM models for heat plume extension and the prepared dataset for training and testing.

In this repo the code for model training and dataset preparation is published. The last relevant git commit is 0a148e6131b98260.

The prepared dataset for training is called ep_medium_1000dp_only_vary_dist inputs_ks. It consists of 1000 simulation runs from darus-3652 that are prepared for the ConvLSTM network. Each data point measures 320 m x 6400 m with 64 x 1280 cells. All parameters are constant except for the permeability, which varies across the domain and from data point to data point.