EGU22-2543, updated on 27 Mar 2022
https://doi.org/10.5194/egusphere-egu22-2543
EGU General Assembly 2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Multiorder Hydrologic Position for Europe (EU-MOHP) as a Set of Environmental Predictor Variables for Hydrologic Modelling and Groundwater Mapping with Focus on the Application of Machine Learning

Maximilian Nölscher1, Michael Mutz2, and Stefan Broda1
Maximilian Nölscher et al.
  • 1Federal Institute for Geosciences and Natural Resources, Basic information Groundwater and Soil, Berlin, Germany (max-n@posteo.de)
  • 2no affiliation

The application of machine learning in geosciences began several decades ago and is, especially in the advent of increasing and affordable computational power, continuously gaining popularity. However, in some specific areas such as hydrogeology, where processes are partly or fully subsurface, the application of machine learning is still limited due to either missing or noisy data, such as in mapping hydrogeochemical parameters of aquifer properties. The presented dataset EU-MOHP v013.1.0 partly closes this gap. It provides cross-scale information on the multiorder hydrologic position (MOHP) of a geographic point within its respective river network and catchment as gridded maps. More precisely, it comprises the three measures “lateral position” (LP) as a relative measure of the position between the stream and the catchment divide, “divide stream distance” (DSD) as sum of the distances to the nearest stream and divide and “stream distance” (SD) as an absolute measure of the distance to the nearest stream. These three measures are calculated for several hydrologic orders to reflect different spatial scales. Its spatial extent covers major parts of the European Economic Area (EEA39), which also largely coincides with physiographical Europe. Although there might be many potential use cases, this dataset serves predominantly as valuable static environmental predictor variable for hydrogeological and hydrological modelling such as mapping or regionalization tasks using machine learning. The concept is strongly inspired by Belitz et al. (2019), who generated this dataset for conterminous USA.

How to cite: Nölscher, M., Mutz, M., and Broda, S.: Multiorder Hydrologic Position for Europe (EU-MOHP) as a Set of Environmental Predictor Variables for Hydrologic Modelling and Groundwater Mapping with Focus on the Application of Machine Learning, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-2543, https://doi.org/10.5194/egusphere-egu22-2543, 2022.

Comments on the display material

to access the discussion