Assessment of SoilGrids data for soil erosion estimation at watershed scale: A case study in Northern Thailand

Soil erosion has been identified as one of the most destructive forms of land degradation, posing a threat to the sustainability of global economic, social and environmental systems. This underscores the need for sustainable land management that takes erosion control and prevention into consideration. This requires the use of state-of-the-art erosion prediction models. The models often require extensive input of detailed spatial and temporal data, some of which are not readily available in many developing countries, particularly detailed soil data. SoilGrids could potentially fill the data gap. Nevertheless, its value and accuracy for soil erosion modeling in the humid tropics is still unknown, necessitating the need to assess its value vis-à-vis field-based data. The major objective of this study was to conduct a comparative assessment the value of SoilGrids vis-à-vis field-based soil data for estimation of soil loss. Soil samples were collected from five physiographic positions (summit, shoulder, back slope, foot slope and toe slope) using the soil catena approach. Samples were collected using a 5 cm steel sample ring (undisturbed) and a spade (disturbed). Data on the landform, predominant vegetation types, canopy cover, average plant height (m), land use, soil depth (m), shear strength (kPa) and soil color were recorded for each site. The soil samples were subjected to laboratory analysis (saturated hydraulic conductivity, bulk density, particle size distribution and soil organic matter content). Pedotransfer functions were applied on the SoilGrids and field-based data to generate soil hydrological properties. The resultant field-based data was compared with the SoilGrids data for corresponding points/areas to determine the potential similarities of the two datasets. Both datasets were then used as inputs for soil erosion assessment using the Revised Morgan-Morgan-Finney (RMMF) model. The results from both datasets were again compared to determine the degree of similarity. The results show that with respect to point-based comparison, both datasets were significantly different. At the hillslope delineation level, the field-based data still consistently had a greater degree of variability, but the hillslope averages were not significantly different for both datasets. Similar results were recorded with the soil loss parameters generated from both datasets; point-based comparison showed that both datasets were significantly different, whereas, the reverse was the case for parcel/area-based comparison. SoilGrids data is certainly useful especially where soil data is lacking. Its utility is, however, dependent on the scale of operation or the extent of detail required. When detailed, site-specific data are required, SoilGrids may not be a good alternative to soil survey data in the humid tropics. On the other hand, if the average soil properties of a region, area or land parcel are required for the implementation of a particular project, plan or program, then SoilGrids data can be a very valuable alternative to soil survey data.