Abstract Soil total phosphorus (STP) is defined as the entirety of phosphorus present in the soil, constituted by both organic and inorganic fractions. STP is an essential element for maintaining ecosystem productivity and nutrient balance. However, due to the multiple impacts of climate change and intensified anthropogenic disturbances, the spatial distribution, drivers, and future trends of STP in the drylands of China are still unclear. This limits the precise management of soil P resources and sustainable regional development. In this study, based on the STP concentration data of 1108 sample sites, we compared the predictive performance of five machine learning models, selected the eXtreme Gradient Boosting model with superior predictive performance, estimated the STP stocks, mapped their spatial distribution, clarified the main drivers, and predicted future trends at the 0‐ to 100‐cm soil depths. The results were as follows: (1) STP stocks at 0‐ to 30‐cm and 30‐ to 100‐cm depths were estimated to be 1.59 ± 0.50 and 3.58 ± 1.24 Pg, respectively. Among them, grassland STP stocks are the highest and shrub STP stocks are the lowest. (2) The spatial distribution of STP at 0–30 cm was primarily driven by climate, specifically mean annual temperature, whereas at 30–100 cm, it was primarily driven by microbial factors, specifically microbial biomass P. (3) Under future IPCC's Shared Socioeconomic Pathways, STP stocks all showed an increasing trend. The results help to understand how drylands respond to global changes, which is of great significance to the stability of terrestrial ecosystems and the sustainable use of P, and provide data support for regional soil fertility regulation.
Zhang et al. (Sun,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: