Data for digital soil moisture mapping

This repository contains the full processed input data sets and the corresponding results which were produced with the python soil moisture module (SM-Module) 10.5281/zenodo.14871758

The folder structure is as follows:

├── figures # figures and maps produced by prediction, including combined_images.gif for seed 12000
├── hyperparameters_tuning_stats
├── model_input
├── models
├── performance_stats
├── residuals

Citation

If you use any materials of this repository cite the paper Houben et al. (2025)

If you use any of the input data cite as follows:

    Soil moisture data created by Martini et al. 2015, processed by Houben et al. (2025).

If you use the DEM information or any derivatives cite as follows:

    Digital Elevation Model: Schröter et al. 2015, processed by Houben et al. (2025).

References

Houben, T., Ebeling, P., Khurana, S., Schmid, J., Boog, J., (2025): Machine-learning based spatio-temporal prediction of soil moisture in a grassland hillslope. Vadose Zone Journal. doi:...

Martini, E., Wollschläger, U., Kögler, S., Behrens, T., Dietrich, P., Reinstorf, F., Schmidt, K., Weiler, M., Werban, U., & Zacharias, S. (2015). Spatial and Temporal Dynamics of Hillslope-Scale Soil Moisture Patterns: Characteristic States and Transition Mechanisms. Vadose Zone Journal, 14(4). https://doi.org/10.2136/vzj2014.10.0150

Schröter, I., Paasche, H., Dietrich, P., & Wollschläger, U. (2015). Estimation of Catchment-Scale Soil Moisture Patterns Based on Terrain Data and Sparse TDR Measurements Using a Fuzzy C-Means Clustering Approach. Vadose Zone Journal, 14 (11). https://doi.org/10.2136/vzj2015.01.0008