The spatial distribution characteristics of soil attributes are of great significance for quantitative monitoring of land quality, precision agricultural production, and sustainable use of land resources. Therefore, to meet the needs of quantitative monitoring of the quantity and quality of China's black soil and the development of modern precision agriculture for different scales of high-precision key soil attributes, the core demonstration area of Youyi Farm was selected as the study area. A total of 152 soil samples of the surface layer (0-20 cm) were collected and 29 variables, such as soil texture, topography, and the derived factors and bio-factors, were chosen as the environmental variables. Four representative digital soil mapping models, ordinary kriging (OK), geographically weighted regression (GWR), random forest (RF) and random forest-ordinary kriging (RF-OK), were selected to predict the contents and spatial distributions of soil pH, soil organic matter (SOM), and total nitrogen (TN) contents. The root mean of square error (RMSE), consistency correlation coefficient (CCC), coefficient of determination (R2), and bias (Bias) were used to comprehensively evaluate the prediction performance of the models. The results showed that the pH value of soil samples in the study area ranged from 5.26 to 8.42 with an average value of 6.63. The SOM content ranged from 19.41 to 109.17 g·kg-1 with an average value of 42.26 g·kg-1. The TN content ranged from 0.94 to 5.20 g·kg-1 with an average value of 1.94 g·kg-1. The coefficients of variation were 13.67%, 29.50% and 31.98%, respectively, all of which belonged to moderate spatial variation. In terms of the prediction accuracy of the four models, the RF-OK model showed the best performance for predicting soil pH (R2 = 0.83 and RMSE = 0.41) and SOM (R2 = 0.72 and RMSE = 7.36 g·kg-1). The RF model achieved the best performance in predicting soil TN (R2 = 0.59 and RMSE = 0.36 g·kg-1). Based on the optimal models, the overall spatial distribution trends of soil pH, SOM and TN were similar. Soil pH in the northeast was dominated by neutral soils, whereas that in the southwest was mainly acidic soils. The SOM and TN contents in the northeast were obviously higher than those in the southwest. This study not only provides data support for precision agriculture management in the demonstration area, but also provides valuable reference for selecting prediction methods of digital soil mapping.