Various research topics from the field of soil science or agriculture require digital maps of soil properties as input data. Such maps can be achieved by digital soil mapping (DSM) techniques which have developed consistently during the last decades. Our research focuses on the application of geostatistical methods (including ordinary kriging, regression-kriging and geographically weighted regression) and machine learning algorithms to produce high resolution digital maps of topsoil properties in Romania. Six continuous predictors were considered in our study (digital elevation model, topographic wetness index, normalized difference vegetation index, slope, latitude and longitude). A tolerance test was performed to ensure that all predictors can be used for the purpose of digital soil mapping. The input soil data was extracted from the LUCAS database and includes 7 chemical properties (pH, electrical conductivity, calcium carbonate, organic carbon, N, P, K) and the particle-size fractions (sand, silt, clay). The spatial autocorrelation is higher for pH, organic carbon and calcium carbonate, as indicated by the partial sill / nugget ratio of semivariograms, meaning that these properties are more predictable than the others by kriging interpolation. The optimal DSM method was selected by independent sample validation, using resampled statistics from 100 samples randomly extracted from the validation dataset. Also, an additional independent sample of soil profiles, comprising legacy soil data, and the 200k Romania soil map were used for a supplementary validation. The results show that machine learning and regression-kriging are the optimal methods in most cases. Among the machine learning tested algorithms, the best performance is associated with Support Vector Machines and Random Forests methods. The geographically weighted regression is also among the optimum methods for pH and calcium carbonates spatial prediction. Good predictions were achieved for pH (R²of 0.417–0.469, depending on the method), organic carbon (R²of 0.302–0.443), calcium carbonates (R²of 0.300–0.330) and moderate predictions for electric conductivity, total nitrogen, silt and sand (R²of 0.155–0.331), while the lowest prediction characterizes the phosphorous content (R²of 0.015–0.044). LUCAS proved to be a reliable and useful soil database and the achieved spatial distributions of soil properties can be further used for national and regional soil studies.

Soil erosion is triggered by rainfall through the detachment of soil particles and their transport downslope, playing a key role in soil erosion models. Together with the vegetation cover, rainfall is a temporal dynamic factor, inducing corresponding time variations of erosion rates. Under current climate change, rainfall is also changing its characteristics and our study aimed to reveal whether these changes will significantly affect rainfall erosivity in Romania, and implicitly the soil erosion. To achieve this purpose, we developed a statistical non-parametric model for predicting rainfall erosivity on the basis on the modified Fournier index and applied it to future precipitation evolution scenarios. The precipitation data were extracted from the CHESLA database for the Romanian territory for two climate change contrasting scenarios (RCP 4.5 and 8.5). Average predictions from five selected climate models were used in order to minimize prediction uncertainty. The results show that rainfall erosivity is likely to increase, at least during the 2041–2060 period, especially in the south-western, western and eastern part of the country, which may cause a corresponding increase in soil erosion rates, with an average of 1–2 t ha⁻¹ yr⁻¹. During the 2061–2080 period, rainfall erosivity is likely to decrease in central and eastern Romania.