As the largest terrestrial carbon pool, soil organic carbon (SOC) has the potential to influence and mitigate climate change; thus, SOC monitoring is of high importance in the frameworks of various international treaties. Therefore, high-resolution SOC maps are required. Machine learning (ML) offers new opportunities to develop these maps due to its ability to data mine large datasets. The aim of this study was to apply three algorithms commonly used in digital soil mapping – random forest (RF), boosted regression trees (BRT), and support vector machine for regression (SVR) – on the first German agricultural soil inventory to model the agricultural topsoil (0–30 cm) SOC content and develop a two-model approach to address the high variability in SOC in German agricultural soils. Model performance is often limited by the size and quality of the soil dataset available for calibration and validation. Therefore, the impact of enlarging the training dataset was tested by including data from the European Land Use/Cover Area frame Survey for agricultural sites in Germany. Nested cross-validation was implemented for model evaluation and parameter tuning. Grid search and the differential evolution algorithm were also applied to ensure that each algorithm was appropriately tuned . The SOC content of the German agricultural soil inventory was highly variable, ranging from 4 to 480 g kg−1. However, only 4 % of all soils contained more than 87 g kg−1 SOC and were considered organic or degraded organic soils. The results showed that SVR produced the best performance, with a root-mean-square error (RMSE) of 32 g kg−1 when the algorithms were trained on the full dataset. However, the average RMSE of all algorithms decreased by 34 % when mineral and organic soils were modelled separately, with the best result from SVR presenting an RMSE of 21 g kg−1. The model performance was enhanced by up to 1 % for mineral soils and by up to 2 % for organic soils. Despite the ability of machine learning algorithms, in general, and SVR, in particular, to model SOC on a national scale, the study showed that the most important aspect for improving the model performance was to separate the modelling of mineral and organic soils.
Many soil functions and processes are controlled by the soil particle size distribution. Accordingly, nationwide geoinformation on this soil property is required to enable climate-smart and resilient land management. This study presents a new deep learning approach to simultaneously model the contents of the three particle sizes of sand, silt, and clay and their variations with depth throughout the landscape. The approach allows for the consideration of the natural soil horizon boundaries and the inclusion of the surrounding landscape context of each soil profile to investigate the soil–landscape relation. Applied to the agricultural soil landscape of Germany, the approach generated a three-dimensional continuous data product with a resolution of 100 m in geographic space and a depth resolution of 1 cm. The approach relies on a patch-wise multi-target convolutional neural network (CNN) model. Genetic algorithm optimization was applied for CNN parameter tuning. Overall, the effectiveness of the CNN algorithm in generating multidimensional, multivariate, national-scale soil data products was demonstrated. The predictive performance resulted in a median root mean square error of 17.8 mass-% for the sand, 14.4 mass-% for the silt, and 9.3 mass-% for the clay content in the top ten centimeters. This increased to 20.9, 16.5, and 11.8 mass-% at a 40 cm depth. The generated data product is the first of its kind. However, even though the potential of this deep learning approach to understand and model the complex soil–landscape relation is virtually limitless, its limitations are data driven concerning the approximation of the soil-forming factors and the available soil profile data.
Soil organic matter (SOM) and the ratio of soil organic carbon to total nitrogen (C/N ratio) are fundamental to the ecosystem services provided by soils. Therefore, understanding the spatial distribution and relationships between the SOM components mineral-associated organic matter (MAOM), particulate organic matter (POM), and C/N ratio is crucial. Three ensemble machine learning models were trained to obtain spatial predictions of the C/N ratio, MAOM, and POM in German agricultural topsoil (0–10 cm). Parameter optimization and model evaluation were performed using nested cross-validation. Additionally, a modification to the regressor chain was applied to capture and interpret the interactions among the C/N ratio, MAOM, and POM. The ensemble models yielded mean absolute percent errors (MAPEs) of 8.2% for the C/N ratio, 14.8% for MAOM, and 28.6% for POM. Soil type, pedo-climatic region, hydrological unit, and soilscapes were found to explain 75% of the variance in MAOM and POM, and 50% in the C/N ratio. The modified regressor chain indicated a nonlinear relationship between the C/N ratio and SOM due to the different decomposition rates of SOM as a result of variety in its nutrient quality. These spatial predictions enhance the understanding of soil properties’ distribution in Germany.