High-resolution agriculture soil property maps from digital soil mapping methods, Czech Republic

Detailed maps of soil properties are essential for soil protection planning and management; however, creating very high-resolution maps at the national level with sufficient accuracy is a challenging task and remains unavailable for most countries. For the Czech Republic, very high resolution (20 m center dot pixel(-1)) soil property maps (soil organic carbon-SOC, texture, pH, bulk density, soil depth) were created using digital soil mapping methods, combined with a wide database of soil legacy and current samples. The latest approaches were employed for predictive mapping: a quantile random forest model with the determination of prediction intervals, a mosaic of bare soils from Sentinel-2 satellite data, a Gaussian pyramid of terrain attributes, and a buffer distance map. These variables were found to be among the most important in the resulting models. The properties were mapped with an RMSE accuracy of 0.43% SOC, 5.56-11.14% for texture fractions, 0.70 pH, 0.13 g center dot cm(-3) bulk density, and 20.03 cm for soil depth, thus providing detailed data on soil cover. Greater levels of inaccuracy were found in areas with extreme values, for which further investigation is necessary either through more detailed sampling based on active learning, or adapted methods for enhanced predictive ability.

Automated summary

Creating detailed maps of soil properties is vital for soil protection planning and management. This study demonstrates the creation of high-resolution soil property maps for the Czech Republic using digital soil mapping methods and a comprehensive soil sample database. The study employed advanced techniques for predictive mapping and achieved high accuracy in mapping various soil properties. However, further investigation is needed to improve accuracy in areas with extreme values.