Retrieval of Total Phosphorus Concentration in the Surface Water of Miyun Reservoir Based on Remote Sensing Data and Machine Learning Algorithms

Some essential water conservation areas in China have continuously suffered from various serious problems such as water pollution and water quality deterioration in recent decades and thus called for real-time water pollution monitoring system underwater resources management. On the basis of the remote sensing data and ground monitoring data, this study firstly constructed a more accurate retrieval model for total phosphorus (TP) concentration by comparing 12 machine learning algorithms, including support vector machine (SVM), artificial neural network (ANN), Bayesian ridge regression (BRR), lasso regression (Lasso), elastic net (EN), linear regression (LR), decision tree regressor (DTR), K neighbor regressor (KNR), random forest regressor (RFR), extra trees regressor (ETR), AdaBoost regressor (ABR) and gradient boosting regressor (GBR). Then, this study applied the constructed retrieval model to explore the spatial-temporal evolution of the Miyun Reservoir and finally assessed the water quality. The results showed that the model of TP concentration built by the ETR algorithm had the best accuracy, with the coefficient R2 reaching over 85% and the mean absolute error lower than 0.000433. The TP concentration in Miyun Reservoir was between 0.0380 and 0.1298 mg/L, and there was relatively significant spatial and temporal heterogeneity. It changed remarkably during the periods of the flood season, winter tillage, planting, and regreening, and it was lower in summer than in other seasons. Moreover, the TP in the southwest part of the reservoir was generally lower than in the northeast, as there was less human activities interference. According to the Environmental Quality Standard for the surface water environment, the water quality of Miyun Reservoir was overall safe, except only for an over-standard case occurrence in the spring and September. These conclusions can provide a significant scientific reference for water quality monitoring and management in Miyun Reservoir.

Machine Learning-Based Prediction of Chlorophyll-a Variations in Receiving Reservoir of World’s Largest Water Transfer Project—A Case Study in the Miyun Reservoir, North China

Although water transfer projects can alleviate the water crisis, they may cause potential risks to water quality safety in receiving areas. The Miyun Reservoir in northern China, one of the receiving reservoirs of the world’s largest water transfer project (South-to-North Water Transfer Project, SNWTP), was selected as a case study. Considering its potential eutrophication trend, two machine learning models, i.e., the support vector machine (SVM) model and the random forest (RF) model, were built to investigate the trophic state by predicting the variations of chlorophyll-a (Chl-a) concentrations, the typical reflection of eutrophication, in the reservoir after the implementation of SNWTP. The results showed that compared with the SVM model, the RF model had higher prediction accuracy and more robust prediction ability with abnormal data, and was thus more suitable for predicting Chl-a concentration variations in the receiving reservoir. Additionally, short-term water transfer would not cause significant variations of Chl-a concentrations. After the project implementation, the impact of transferred water on the water quality of the receiving reservoir would have gradually increased. After a 10-year implementation, transferred water would cause a significant decline in the receiving reservoir’s water quality, and Chl-a concentrations would increase, especially from July to August. This led to a potential risk of trophic state change in the Miyun Reservoir and required further attention from managers. This study can provide prediction techniques and advice on water quality security management associated with eutrophication risks resulting from water transfer projects.

Explicating Sediment Sources of the Catchment Upstream of the Miyun Reservoir in Beijing, China

As the only water drinking resource in Beijing, the Miyun Reservoir is still suffered over ten thousand tons of sediment input from its upper catchment. Explicating sediment sources of the catchment upstream of the reservoir is urgently required to further implement soil conservation measures. In this paper, the Revised Universal Soil Loss Equation (RUSLE) and Sediment Delivery (SEDD) models were combined to explicate the major sediment source of the catchment through exploring the spatial distributions of soil erosion and sediment delivery as well as their relations with land use and topography, and sediment source areas were then identified. The catchment average soil erosion intensity (SEI) of 4.08 t ha− 1 yr− 1 was two times the soil loss tolerance (T = 2.00 t ha− 1 yr− 1) of the study region. The values of cell sediment delivery ratio (SDR) showed a network distribution pattern, ranging from zero to unit, with an average of 1.65%. Cell specific sediment yield (SSY) presented a similar spatial pattern to SDR, ranging from 0 to 902 t ha− 1 yr− 1, with an average of 0.04 t ha− 1 yr− 1. Bare land suffered the highest SEI of 39.01 t ha− 1 yr− 1, followed by shrub land and orchard field. Nearly 70% of the sediment came from grass land. Farmland was the second sediment contributor. Grass land and farmland are the two major sediment source areas. Soil conservation practices should be further implemented on these lands, especially on the 3–5°slopes with elevations less than 500 m a.s.l.

Assessment of the Impacts of Land Use Change on Non-Point Source Loading under Future Climate Scenarios Using the SWAT Model

The Miyun Reservoir is an important source of surface drinking water in Beijing. Due to climate change and human activities, the inflow of Miyun Reservoir watershed (MRW) has been continuously reduced in the past 30 years, which has seriously affected the safety of Beijing’s water supply. Therefore, this study aimed to assess the mitigation measures based on the quantification of the integrated impacts of climate and land use change in MRW. The non-point source (NPS) model (soil and water assessment tool, SWAT) was used for the development of future climate scenarios which were derived from two regional climate models (RCMs) under two representative concentration pathways (RCPs). Three land use scenarios were generated by the land use model (conversion of land-use and its effects (CLUE-S)): (1) historical trend scenario, (2) ecological protection without consideration of spatial configuration scenario and (3) ecological protection scenario. Moreover, the reduction of sediment and nutrients under three future land use patterns in future climate scenarios was evaluated. The results showed that an appropriate land use change project led to the desired reduction effect on sediment and nutrients output under future climate scenarios. The average reduction rates of sediment, total nitrogen and total phosphorus were 11.4%, 6.3% and 7.4%, respectively. The ecological protection scenario considering spatial configuration showed the best reduction effect on sediment, total nitrogen and total phosphorus. Therefore, the addition of region-specific preference variables as part of land use change provides better pollutant control effects. Overall, this research provides technical support to protect the safety of Beijing’s drinking water and future management of non-point source pollution in MRW.