Effects of multi-temporal environmental variables on SOC spatial prediction models in coastal wetlands of a Chinese delta

Mapping the SOC distributions in coastal wetlands plays an important role in assessing ecosystem services, predicting the greenhouse effects and investigating global carbon cycle. Few research has explored the relationships of SOC and environmental variables with seasonal changes, and the effects of multi-temporal environmental variables on Digital Soil Mapping (DSM). The results showed that the relationships between SOC and environmental variables in different months varied significantly in coastal wetlands of the Yellow River Delta (YRD). In general, the environmental variables in wet season showed stronger correlations and higher importance scores with SOC compared with those in dry season. In addition, SOC prediction models based on multi-temporal data in wet season and mono-temporal data in April had stronger prediction performance compared with those based on multi-temporal data in dry season. As a result, data fusion of multi-temporal data did not necessarily contribute to the model performance enhancement. Relative homogenous soil-landscape attributes and spectral characteristics in coastal wetlands of the YRD in dry season could not accurately explain the strong spatial variation of SOC in this area, and it might be the major reason that caused the stronger model performance of soil prediction models based on wet season than those based on dry season. Therefore, the accurate spatial prediction of soil properties requires the characterization of the seasonal dynamics of soil-landscape relationships. In general, the findings of this research demonstrated that the selection of the environmental variables in the establishment of DSM model should consider the seasonal effects of environmental variables.

Evolutionary pathways in soil-landscape evolution models

Soils and landscapes can show complex, non-linear evolution, especially under changing climate or land use. Soil-landscape evolution models (SLEMs) are increasingly equipped to simulate the development of soils and landscapes over long timescales under these changing drivers, but provide large data output that can be difficult to interpret and communicate. New tools are required to analyse and communicate large model output. In this work, I show how spatial and temporal trends in previously published model results can be summarized and conceptualized with evolutionary pathways, which are possible trajectories of the development of soil patterns. Simulated differences in rainfall and land use control progressive or regressive soil development and convergence or divergence of the soil pattern. These changes are illustrated with real-world examples of soil development and soil complexity. The use of evolutionary pathways for analysing the results of SLEMs is not limited to the examples in this paper, but they can be used on a wide variety of soil properties, soil pattern statistics and models. With that, evolutionary pathways provide a promising tool to analyse and communicate soil model output, not only for studying past changes in soils, but also for evaluating future spatial and temporal effects of soil management practices in the context of sustainability.

A Parsimonious Approach to Estimate Soil Organic Carbon Applying Unmanned Aerial System (UAS) Multispectral Imagery and the Topographic Position Index in a Heterogeneous Soil Landscape

Remote sensing plays an increasingly key role in the determination of soil organic carbon (SOC) stored in agriculturally managed topsoils at the regional and field scales. Contemporary Unmanned Aerial Systems (UAS) carrying low-cost and lightweight multispectral sensors provide high spatial resolution imagery (<10 cm). These capabilities allow integrate of UAS-derived soil data and maps into digitalized workflows for sustainable agriculture. However, the common situation of scarce soil data at field scale might be an obstacle for accurate digital soil mapping. In our case study we tested a fixed-wing UAS equipped with visible and near infrared (VIS-NIR) sensors to estimate topsoil SOC distribution at two fields under the constraint of limited sampling points, which were selected by pedological knowledge. They represent all releva nt soil types along an erosion-deposition gradient; hence, the full feature space in terms of topsoils’ SOC status. We included the Topographic Position Index (TPI) as a co-variate for SOC prediction. Our study was performed in a soil landscape of hummocky ground moraines, which represent a significant of global arable land. Herein, small scale soil variability is mainly driven by tillage erosion which, in turn, is strongly dependent on topography. Relationships between SOC, TPI and spectral information were tested by Multiple Linear Regression (MLR) using: (i) single field data (local approach) and (ii) data from both fields (pooled approach). The highest prediction performance determined by a leave-one-out-cross-validation (LOOCV) was obtained for the models using the reflectance at 570 nm in conjunction with the TPI as explanatory variables for the local approach (coefficient of determination (R²) = 0.91; root mean square error (RMSE) = 0.11% and R² = 0.48; RMSE = 0.33, respectively). The local MLR models developed with both reflectance and TPI using values from all points showed high correlations and low prediction errors for SOC content (R² = 0.88, RMSE = 0.07%; R² = 0.79, RMSE = 0.06%, respectively). The comparison with an enlarged dataset consisting of all points from both fields (pooled approach) showed no improvement of the prediction accuracy but yielded decreased prediction errors. Lastly, the local MLR models were applied to the data of the respective other field to evaluate the cross-field prediction ability. The spatial SOC pattern generally remains unaffected on both fields; differences, however, occur concerning the predicted SOC level. Our results indicate a high potential of the combination of UAS-based remote sensing and environmental covariates, such as terrain attributes, for the prediction of topsoil SOC content at the field scale. The temporal flexibility of UAS offer the opportunity to optimize flight conditions including weather and soil surface status (plant cover or residuals, moisture and roughness) which, otherwise, might obscure the relationship between spectral data and SOC content. Pedologically targeted selection of soil samples for model development appears to be the key for an efficient and effective prediction even with a small dataset.

Large-Scale Modeling of Solum Thickness Based on the Local Topographic Attributes of Ground and Bedrock Surfaces

This study was aimed to address the importance of neighborhood scale and using bedrock topography in the soil-landscape modeling in a low-relief large region. For this study, local topographic attributes (slopes and curvatures) of the ground surface (DTM) and bedrock surface (DBM) were derived at five different neighborhood sizes (3×3, 9×9, 15×15, 21×21, and 27×27). Afterward, the topographic attributes were used for multivariate adaptive regression splines (MARS) modeling of solum thickness. The results demonstrate that there are statistical differences among DTM and DBM morphometric variables and their correlation to solum thickness. The MARS analyses revealed that the neighborhood scale could remarkably affect the soil–landscape modeling. We developed a powerful MARS model for predicting soil thickness relying on the multi-scale geomorphometric analysis (R2= 83%; RMSE= 12.70 cm). The MARS fitted model based on DBM topographic attributes calculated at a neighborhood scale of 9×9 has the highest accuracy in the prediction of solum thickness compared to other DBM models (R2 = 61%; RMSE = 19cm). This study suggests that bedrock topography can be potentially utilized in soil-related research, but this idea still needs further investigations.

Machine Learning With GA Optimization to Model the Agricultural Soil-Landscape of Germany: An Approach Involving Soil Functional Types With Their Multivariate Parameter Distributions Along the Depth Profile

Societal demands on soil functionality in agricultural soil-landscapes are confronted with yield losses and environmental impact. Soil functional information at national scale is required to address these challenges. On behalf of the well-known theory that soils and their site-specific characteristics are the product of the interaction of the soil-forming factors, pedometricians seek to model the soil-landscape relationship using machine learning. Following the rationale that similarity in soils is reflected by similarity in landscape characteristics, we defined soil functional types (SFTs) which were projected into space by machine learning. Each SFT is described by a multivariate soil parameter distribution along its depth profile. SFTs were derived by employing multivariate similarity analysis on the dataset of the Agricultural Soil Inventory. Soil profiles were compared on behalf of differing sets of soil properties considering the top 100 and 200 cm, respectively. Various depth weighting coefficients were tested to attribute topsoil properties higher importance. Support vector machine (SVM) models were then trained employing optimization with a distributed multiple-population hybrid Genetic algorithm for parameter tuning. Model training, tuning, and evaluation were implemented in a nested k-fold cross-validation approach to avoid overfitting. With regards to the SFTs, organic soils were differentiated from mineral soils of various particle size distributions being partly influenced by waterlogging and groundwater. Further SFTs reflect soils with a depth limitation within the top 100 cm and high stone content. Altogether, with SVM predictive model accuracies between 0.7 and 0.9, the agricultural soil-landscape of Germany was represented with eight SFTs. Soil functionality with regards to the soil’s capacity to store plant-available water and soil organic carbon is well characterized. Four additional soil functions are described to a certain extent. An extension of the approach to fully cover soil functions such as nutrient cycling, agricultural biomass production, filtering of contaminants, and soil as a habitat for soil biota is possible with the inclusion of additional soil properties. Altogether, the developed data product represents the 3D multivariate soil parameter space. Its agglomerated simplicity into a limited number of spatially allocated process units provides the basis to run agricultural process models at national scale (Germany).