Estimation of soil pH with geochemical indices in forest soils

Soil pH is a critical soil quality index and controls soil microbial activities, soil nutrient availability, and plant roots growth and development. The current study aims to evaluate various pedotransfer functions for predicting soil pH using different geochemical indices (CaO, ratios of Al(2)O(3), Fe(2)O(3), TiO(2), SiO(2), MgO, and K(2)O to CaO) in forest soils. Various models including empirical functions (quadratic, cubic, sigmoid, logarithmic) and artificial neural network with these geochemical indices were assessed by independent testing set. Mean bias error (MBE), root mean square error (RMSE), mean absolute percentage error (MAPE), mean absolute error (MAE), coefficient of determination (R(2)), t-statistics (t-stat), and Akaike’s Information Criterion (AIC) were applied to evaluate the model performances. Additionally, a new indicator (global performance indictor, GPI) was originally introduced in this study and was used to rank these models. According to GPI, the sigmoid functions and ANNs performed better than others. On average, they could explain above 70% of the variability in soil pH. Both model structure and dataset shape impact on model performance. The best input was CaO for ANNs, sigmoid, and logarithmic functions. The ratios of K(2)O to CaO and Al(2)O(3) to CaO were the best inputs for quadratic and cubic equations, respectively.