@unibiblio

Datasets: 100 Heat Pumps + Synthetic Permeability Fields, Simulation - Raw, 3 + 1 Data Points : Randomized heterogeneous permeability field k (Perlin noise)

. Dataset, (2024)Related to: Pelzer, Julia and Verburg, Corné and Heinlein, Alexander and Schulte, Miriam. "Few-Shot Learning by Explicit Physics Integration: An Application to Groundwater Heat Transport". 2025. Submitted.
DOI: 10.18419/darus-4156

Zusammenfassung

This data set serves as training data for modeling the temperature field emanating from several open loop groundwater heat pumps (one hundred heat pumps, randomly placed). It is simulated with Pflotran and saved in h5 format. The data set contains 3 data points, each consisting of one simulation run until a near steady state is reached. Each data point measures 12.8 x 12.8 km with 2560 x 2560 cells. Additionally, there is one data point of 25.6 x 25.6 km of the same resolution for scaling tests. The varying parameter of the data set is the heterogeneous permeability with a fixed minimum and maximum. Other parameters that define the data set, such as porosity, 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. Generated with scripts from Dataset generation with Pflotran (commit 8549bbd9e22d2) with arguments given in inputs/args.yaml.

Links und Ressourcen

Tags