[Estimation of Cropland Nitrogen Runoff Loss Loads in the Yangtze River Basin Based on the Machine Learning Approaches].

A quantitative understanding of cropland nitrogen (N) runoff loss is critical for developing efficient N pollution control strategies. Using correlation analysis, a structural equation model, variance decomposition, and machine learning methods, this study identified the primary influencing factors of total N (TN) runoff loss from uplands (n=570) and paddy (n=434) fields in the Yangtze River Basin (YRB) and then developed a machine learning-based prediction model to quantify cropland N runoff loss load. The results indicated that runoff depth, soil N content, and fertilizer addition rate were the major influencing factors of TN runoff loss from uplands, whereas TN runoff loss rate from paddy fields was mainly regulated by runoff depth and fertilizer addition rate. Among the four used machine learning methods, the prediction models based on the random forest algorithm presented the highest accuracy (R2=0.65-0.94) for predicting upland and paddy field TN runoff loss rates. The random forest algorithm based model estimated a total cropland TN loss load in the YRB of 0.47 Tg·a-1 (upland:0.25 Tg·a-1; paddy field:0.22 Tg·a-1) in 2013, with 58% of TN runoff loss load derived from the midstream and downstream regions. The models predicted that TN runoff loss loads from croplands in YRB would decrease by 2.4%-9.3% for five scenarios, with higher TN load reductions occurring from scenarios with decreased runoff amounts. To mitigate cropland N nonpoint source pollution in YRB, it is essential to integrate efficient water, fertilizer, and soil nutrient managements as well as to consider the midstream and downstream regions as the high priority area. The machine learning-based modeling method developed in this study overcame the difficulty of identifying the functional relationships between cropland TN loss rate and multiple influencing factors in developing relevant prediction models, providing a reliable method for estimating regional and watershed cropland TN loss load.

Quantifying groundwater phosphorus flux to rivers in a typical agricultural watershed in eastern China.

Increasing evidence indicates that groundwater can contain high dissolved phosphorus (P) concentrations, thereby contributing as a potential pollution source for surface waters. However, limited quantitative knowledge is available concerning groundwater P fluxes to rivers. Based on monthly hydrochemical monitoring data for rivers and groundwater in 2017-2020, this study combined baseflow separation methods and a load apportionment model (LAM) to quantify contributions from point sources, surface runoff, and groundwater/subsurface runoff to riverine P pollution in a typical agricultural watershed of eastern China. In the studied Shuanggang River, most total P (TP) and dissolved P (DP) concentrations exceeded targeted water quality standards (i.e., TP ≤ 0.2 mg P L-1, DP ≤ 0.05 mg P L-1), with DP (76 ± 20%) being the major riverine P form. Observed DP concentrations in groundwater were generally higher than those of river waters. There was a strong correlation between river and groundwater P concentrations, implying that groundwater might be a considerable P pollution source to rivers. The nonlinear reservoir algorithm estimated that baseflow/groundwater contributed 66-68% of monthly riverine water discharge on average, which was consistent with results estimated by an isotope-based sine-wave fitting method. The LAM incorporating point sources, surface runoff, and groundwater effectively predicted daily riverine TP [calibration: coefficient of determination (R2) = 0.76-0.82, Nash-Sutcliffe Efficiency (NSE) = 0.61-0.77; validation: R2 = 0.88-0.98, NSE = 0.54-0.64] and DP loads (calibration: R2 = 0.73-0.84, NSE = 0.67-0.72; validation: R2 = 0.88-0.97, NSE = 0.56-0.83). The LAM estimated point source, surface runoff, and groundwater contributions to riverine loads were 15-18%, 14-35%, and 46-70% for TP loads and 7-9%, 10-32%, and 59-82% for DP loads, respectively. Groundwater was the dominant riverine P source due to long-term accumulation of P from excess fertilizer and farmyard manure applications. The developed methodology provides an alternative method for quantifying P pollution loads from point sources, surface runoff, and groundwater to rivers. This study highlights the importance of controlling groundwater P pollution from agricultural lands to address riverine water quality objectives and further implies that decreasing fertilizer P application rates and utilizing legacy soil P for crop uptake are required to reduce groundwater P loads to rivers.