This data set serves as training and testing data for modelling the temperature field emanating from open loop groundwater heat pumps (100, randomly placed). It is simulated with Pflotran and saved in h5 format. It contains 4 + 1 data points, each consisting of one simulation run until a quasi-steady state is reached. Each data point measures 12.8 km x 12.8 km x 5 m with 2560 x 2560 x 1 cells. The 5th data point is intended for scalability test with the same parameters except for the size of 25.6 km x 12.8 km x 5 m with 5120 x 2560 x 1 cells. The varying parameters of the data sets are the positions of the heat pumps and a heterogeneous permeability field (cut from real permeability fields of the region of Munich). Other parameters that define the data sets, such as porosity and hydraulic pressure gradient are chosen to be as close as possible to reality. Source: "Die hydraulischen Grundwasserverhältnisse des quartären und des oberflächennahen tertiären Grundwasserleiters im Großraum München", Geologica Bavarica Volume 122.

Please follow the instructions in README.md to prepare the data for training a neural network.