Article CC BY 4.0
refereed
published

Transferability of covariates to predict soil organic carbon in cropland soils

ORCID
0000-0002-2078-0441
Affiliation
Thünen Institute of Farm Economics, Bundesallee 63, Braunschweig, Germany
Broeg, Tom;
ORCID
0000-0003-3042-6195
Affiliation
State Authority for Geology, Resources and Mining, Albertstraße 5, Freiburg, Germany
Blaschek, Michael;
GND
1079185011
ORCID
0000-0003-4911-3906
Affiliation
Department of Geosciences, Soil Science and Geomorphology, University of Tübingen, Tübingen, Germany
Seitz, Steffen;
GND
1223125866
ORCID
0000-0002-4620-6624
VIAF
12160789530202680835
Affiliation
Department of Geosciences, Soil Science and Geomorphology, University of Tübingen, Tübingen, Germany
Taghizadeh-Mehrjardi, Ruhollah;
ORCID
0000-0002-7178-0476
Affiliation
German Remote Sensing Data Center (DFD), German Aerospace Center (DLR), Muenchener Str. 20, Wessling, Germany
Zepp, Simone;
GND
115443630
ORCID
0000-0002-4875-2602
Affiliation
Department of Geosciences, Soil Science and Geomorphology, University of Tübingen, Tübingen, Germany
Scholten, Thomas

Precise knowledge about the soil organic carbon (SOC) content in cropland soils is one requirement to design and execute effective climate and food policies. In digital soil mapping (DSM), machine learning algorithms are used to predict soil properties from covariates derived from traditional soil mapping, digital elevation models, land use, and Earth observation (EO). However, such DSM models are trained for a specific dataset and region and have so far only allowed limited general statements to be made that would enable the models to be transferred to different regions. In this study, we test the transferability of SOC models for cropland soils using five different covariate groups: multispectral soil reflectance composites (satellite), soil legacy data (soil), digital elevation model derivatives (terrain), climate parameters (climate), and combined models (combined). The transferability was analyzed using data from two federal states in southern Germany: Bavaria and Baden-Wuerttemberg. First, baseline models were trained for each state with combined models performing best in both cases (R2 = 0.68/0.48). Next, the models were transferred and tested with soil samples from the other state whose data were not used during model calibration. Only satellite and combined models were transferable, but accuracy declined in both cases. In the final step, models were trained with samples from both states (mixed-data models) and applied to each state separately. This process significantly improved the accuracies of satellite, terrain, and combined models, while it showed no effect on climate models and decreased the models based on soil covariates. The experiment underlines the importance of EO for the transfer and extrapolation of DSM models.

Preview

Cite

Citation style:
Could not load citation form.

Access Statistic

Total:
Downloads:
Abtractviews:
Last 12 Month:
Downloads:
Abtractviews:

Rights

Use and reproduction: