Spatiotemporal variations of cropland phosphorus runoff loss in China

• Published in: Journal of hydrology (Amsterdam) 2025-02, Vol.648, p.132419, Article 132419
• Main Authors: Pan, Zheqi, Zhang, Yufu, Ma, Longdan, Zhou, Jia, Wang, Yucang, Wu, Kaibin, Zhang, Qian, Chen, Dingjiang
• Format: Article
• Language: English
• Subjects: Cropland; Machine learning; Mitigation strategy; Non-point source pollution; Phosphorus loss; Runoff
• ISSN: 0022-1694
• DOI: 10.1016/j.jhydrol.2024.132419

•Upland P runoff loss predicted by runoff depth, SOM, and soil available P content.•Paddy field P runoff loss predicted by runoff depth, SOM, and P fertilizer rate.•Random forest-based model had the highest accuracy for predicting P loss rates.•Model-estimated upland TP runoff loss rates increased significantly in 1990–2020.•Reducing P runoff loss requires integrated water, soil and fertilizer managements. Quantitative assessment of cropland phosphorus (P) loss via surface runoff is essential for developing effective pollution mitigation strategies. In this study, we compiled 812 datasets from 114 peer-reviewed papers for cropland P loss across China. We then developed machine learning (ML) approaches to estimate temporal and spatial variations in P runoff loss across China from 1990 to 2020. Four prevalent ML models were considered, namely, multiple linear regression (MLR), random forest (RF), classification and regression trees (CART), and boosted regression trees (BRT). Among these four models, RF exhibited the highest predictive accuracy for both uplands (calibration: R2 = 0.86, n = 293; validation: R2 = 0.61, n = 96) and paddy fields (calibration: R2 = 0.88, n = 137; validation: R2 = 0.60, n = 44). According to RF, China’s croplands are estimated to have lost an average of 148 ± 27 Gg P yr−1 from 1990 to 2020, with uplands and paddy fields contributing 114 ± 26 Gg P yr−1 and 34 ± 4 Gg P yr−1, respectively. There was a significant increase in upland TP runoff loss over the study period (p