Large-scale mapping of soil particle size distribution using legacy data and machine learning-based pedotransfer functions

Abstract

Large-scale maps of particle size fractions (i.e., sand, silt, and clay contents) were created for a case study based on the newly developed Profile-level Database of the Hungarian Large-Scale Soil Mapping (Hungarian acronym: NATASA). This database combines data from previous surveys, offering potential to improve soil mapping accuracy. The database includes information on soil taxonomy and basic soil chemical and physical properties. However, this database contains no direct information on sand, silt and clay content, only an indirect parameter, namely, the upper limit of soil plasticity. Particle size distribution is crucial for various applications, such as assessing soil degradation, hydrology and fertility. To overcome this limitation, we developed pedotransfer functions (PTFs) to compute the particle size distribution from the soil properties available in the NATASA dataset (1,372 soil profiles). The PTFs were trained and tested on the Hungarian Detailed Soil Hydrophysical Database (3,970 soil profiles) using the random forest method. For the prediction model, i) additive log-ratio transformed clay, silt and sand content were used as the dependent variables, and ii) the upper limit of soil plasticity, soil type, calcium carbonate content, organic matter content and pH were included as independent variables. The results indicate that the R2 values of the PTFs are 0.69 for clay, 0.58 for silt, and 0.74 for sand content. Since the NATASA database contains soil information from different depths, we splined the data into six standard depth layers (0–5, 5–15, 15–30, 30–60, 60–100 and 100–200 cm depths). The spatial modelling was performed by random forest kriging (RFK) using environmental auxiliary variables. The R2 values of the RFK models range from 0.19 to 0.67 for clay content, from 0.49 to 0.62 for silt content and from 0.69 to 0.74 for sand content. We compared the high-resolution (25 m) maps with the global SoilGrids (250 m resolution) and the national DOSoReMI.hu soil maps (100 m resolution). Our high-resolution maps offer more detailed information on clay, silt and sand content vertically and horizontally compared to global and national soil maps. This enhanced detail will facilitate future assessments of soil texture-related processes in the area.

Keywords

• Soil particle size distribution
• Upper limit of soil plasticity
• Pedotransfer function
• Random forest kriging
• Digital soil mapping