Spatial prediction of soil calcium carbonate content based on Bayesian maximum entropy using environmental variables
2021
Shan, Mei | Liang, Shuang | Fu, Hongchen | Li, Xiaoli | Teng, Yu | Zhao, Jingwen | Liu, Yaxin | Cui, Chen | Chen, Li | Yu, Hai | Yu, Shunbang | Sun, Yanling | Mao, Jian | Zhang, Hui | Gao, Shuang | Ma, Zhenxing
Soil calcium carbonate (CaCO₃) content is an important soil property. The prediction of soil CaCO₃ content is necessary for the sustainable management of soil fertility. In this work, we attempted to incorporate environmental variables directly and through regression models into the framework of Bayesian maximum entropy (BME) to predict CaCO₃ content. Firstly, multiple linear regression (MLR) and geographically weighted regression (GWR) were used to establish a relationship between sampling data and environmental variables, including Digital Elevation Model, pH, temperature, rainfall, and fluvo-aquic soils. Prediction results of MLR and GWR served as soft data and were incorporated into the framework of BME to estimate the CaCO₃ content. Secondly, soil samples and environmental variables were combined to generate probability distributions of CaCO₃ at unsampled points. These probability distributions were used as soft data for the BME to predict the CaCO₃ content. The results showed that the GWR method (r = 0.84, RMSE = 24.0 g kg⁻¹) performed better than the MLR method (r = 0.73, RMSE = 30.1 g kg⁻¹). The BME-GWR method outperformed the BME-EV and BME-MLR methods. The r values of BME-GWR, BME-EV, and BME-MLR methods were 0.87, 0.86, and 0.82, respectively, and the RMSEs of the three methods were 22.2, 23.9, and 25.2 g kg⁻¹, respectively. The spatial distribution of CaCO₃ content predicted by the above methods was similar and significantly higher in the southwest than in the northeast.
显示更多 [+] 显示较少 [-]