Identification of state-wide soil functional process units for Baden-Württemberg

• Applicant: Professorin Dr. Mareike Ließ
• Subject Area: Soil Sciences ; Methods in Artificial Intelligence and Machine Learning
• Term: since 2025
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 549153178

In cooperation with the application partner Regierungspräsidium Freiburg - Landesamt für Geologie, Rohstoffe und Bergbau (LGRB), spatially localized soil functional process units (SFPs) are to be identified for Baden-Württemberg. Each SFP is characterized by a multivariate soil parameter distribution along its depth profile concerning those soil properties that control important soil functions. The methodological approach is based on an optimization procedure with a complex objective function that identifies SFPs with the lowest internal variability and the greatest possible differences between them. The similarity between the soils on the one hand and the similarity of the site factors on the other are taken into account. The project is based on findings from previous work on the designation of SFPs. Based on the data science approaches developed for this purpose, an extended approach is to be developed for the state-wide soil parameter space of Baden-Württemberg. The resulting data product contains location-specific uncertainty estimates and thus enables the real estimation of all soil functional target values that are derived on the basis of this soil information.

• DFG Programme: Research Grants (Transfer Project)
• Application Partner: Regierungspräsidium Freiburg ; Abteilung 9 - Landesamt für Geologie, Rohstoffe und Bergbau