Prediction dataset of Parametrised PINNs for Water Infiltration in Unsaturated Soils

This dataset contains simulation and training results generated with the PINNFlow framework, a research software project developed at the Chair of Methods for Model-based Development in Computational Engineering (MBD), RWTH Aachen University. The repository provides datasets stored in the Hierarchical Data Format (HDF5) for reproducible experiments involving physics-informed neural networks (PINNs) for water infiltration.