A method for estimating the bulk density and particle density of granite residual soil based on the construction of pedotransfer functions

Particle density (ρ_s) and bulk density (ρ_b) are key factors in the calculation of total soil porosity. However, direct measurements of ρ_s and ρ_b are labour-intensive, time-consuming, and sometimes impractical. Pedotransfer functions (PTFs) provide alternative methods for indirect estimation of ρ_s and ρ_b. In this paper, the accuracy of typical 12 ρ_s and 9 ρ_b PTFs was evaluated using easily measurable soil properties (sand, silt, clay, and soil organic matter (SOM) content) from granitic residual soils collected from six study areas in subtropical China, and the accuracy of PTFs constructed based on multiple linear stepwise regression (MSR) and machine-learned algorithms (backpropagation neural network, k-nearest neighbour algorithms, random forests, support vector machines, and gradient boosted decision trees) was compared to determine the accuracy of PTFs. The results show that typical PTFs have poor accuracy (R²_adjusted < 0.020) and are not applicable to the indirect estimation of ρ_s and ρ_b in granitic residual soils. The PTFs constructed by machine learning algorithms all performed better than MSR, with the highest estimation accuracy of the PTFs constructed by the random forest algorithm, with R²_adjusted values of 0.923 and 0.933 for the ρ_s and ρ_b PTFs, respectively, and root-mean-square error of 0.020 g·cm⁻³ and 0.023 g·cm⁻³, respectively. Compared with MSR, the random forest algorithm has greater accuracy and eliminates the restriction of PTFs on predictors, which provides support for understanding the changing rules of ρ_s and ρ_b in granite residual soils in subtropical regions, evaluating soil quality and improving soil structure.