Soil information is valuable for many disciplines (e.g. agriculture, geomorphology, geology, archaeology) and can be used to produce maps or statistics on soil productivity. As part of the project CRC1070 ResourceCulture, we collected information on the soil quality in the Dohuk province of the Kurdistan region of Iraq. In total, 561 samples were collected at 136 locations in 2017, 2018, 2022, and 2023. These samples were collected at different depth increments (0 - 10, 10 - 30, 30 - 50, 50 - 70 and 70 - 100 cm) with an auger before being prepared and measured with mid-infrared (MIR) spectroscopy. Part of these samples (109) were selected to be analyzed in a laboratory, measuring texture, pH, organic and total carbon, nitrogen, sulfur, electrical conductivity, bulk density and calcium carbonate. A Cubist model was used to predict the remaining samples based on the MIR spectra. We then modelled digital soil mapping with machine learning methods (ensemble learning, linear regression, decision trees) for these soil components. Additionally, we mapped the soil depth using the information collected in the field.

The prediction map for soil depth in cm (0 - 100 cm) is based on a quantile random forest (QRF) model. The uncertainty was computed based on the lower and higher quantile from the QRF model (Uncertainty = (Qp0.95 - Qp0.05) / (Qp0.5)) and is expressed in cm. The pixel size is 25 x 25 m, and the projected coordinate system is WGS84 (epsg:4326).Additionally, five maps for each depth increment (0 - 10 - 30 - 50 - 70 - 100 cm) of the ten predicted properties are provided. The pH is expressed in absolute value, MWD in mm, Nt, Ct, Corg, Sand, Silt and Clay in %, and EC in µS/cm. For 0 - 10 cm depth: pH with QRF model, CaCO3 with QRF model, Nt with QRF model, Ct with QRF, Corg with Cubist, EC with SVMr, MWD with Knn Sand with QRF, Silt with Ensemble and Clay with QRF/Ensemble. For 10 - 30 cm depth: pH with QRF model, CaCO3 with Ensemble model, Nt with QRF model, Ct with QRF, Corg with QRF, EC with Cubist, MWD with Cubist, Sand with QRF, Silt with Ensemble, and Clay with QRF/Ensemble. For 30 - 50 cm depth: pH with QRF model, CaCO3 with QRF model, Nt with Knn model, Ct with Ensemble, Corg with QRF, EC with QRF, MWD with QRF, Sand with QRF, Silt with QRF, and Clay with QRF. For 50 - 70 cm depth: pH with QRF model, CaCO3 with SVMr model, Nt with QRF model, Ct with QRF, Corg with Cubist, EC with Ensemble, MWD with CART, Sand with CART, Silt with QRF, and Clay with CART/QRF. For 70 - 100 cm depth: pH with Knn model, CaCO3 with Ensemble model, Nt with Ensemble model, Ct with CART, Corg with Ensemble, EC with CART, MWD with QRF, Sand with Cubist, Silt with QRF, and Clay with Cubist/QRF. The pixel size is 25 x 25 m, and the projected coordinate system is WGS84 (epsg:4326).