Using local ensemble models and Landsat bare soil composites for large-scale soil organic carbon maps in cropland

• Published in: Geoderma Vol. 444; p. 116850
• Main Authors: Broeg, Tom, Don, Axel, Gocht, Alexander, Scholten, Thomas, Taghizadeh-Mehrjardi, Ruhollah, Erasmi, Stefan
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.04.2024; Elsevier
• Subjects: agricultural soils; autocorrelation; climate-smart agriculture; Cropland; Digital Soil Mapping; Ensemble Modeling; Germany; greenhouse gases; inventories; Landsat; Pedometrics; prediction; reflectance; Soil Organic Carbon; Soil Reflectance Composite; spatial data; Germany; Digital Soil Mapping; Cropland; Soil Organic Carbon; Ensemble Modeling; Pedometrics; Soil Reflectance Composite

•National soil organic carbon maps for cropland based on soil reflectance composite.•Local ensemble model that accounts for spatial dependencies in predictions.•Local variable importance of the spectral bands is attributed to soil properties.•New approach to reduce spatial autocorrelation and increa...