Identification of pollution source and prediction of water quality based on deep learning techniques.

Semi-arid rivers are particularly vulnerable and responsive to the impacts of industrial contamination. Prompt identification and projection of pollutant dynamics are crucial in the accidental pollution incidents, therefore required the timely informed and effective management strategies. In this study, we collected water quality monitoring data from a typical semi-arid river. By water quality inter-correlation mapping, we identified the regularity and abnormal fluctuations of pollutant discharges. Combining the association rule method (Apriori) and characterized pollutants of different industries, we tracked major industrial pollution sources in the Dahei River Basin. Meanwhile, we deployed the integrated multivariate long and short-term memory network (LSTM) to forecast principal contaminants. Our findings revealed that (1) biological oxygen demand (BOD), chemical oxygen demand (COD), total nitrogen, total phosphorus, and ammonia nitrogen exhibited high inter-correlations in water quality mapping, with lead and cadmium also demonstrating a strong association; (2) The main point sources of contaminant were coking, metal mining, and smelting industries. The government should strengthen the regulation and control of these industries and prevent further pollution of the river; (3) We confirmed 4 key pollutants: COD, ammonia nitrogen, total nitrogen, and total phosphorus. Our study accurately predicted the future changes in this water quality index. The best results were obtained when the prediction period was 1 day. The prediction accuracies reached 85.85%, 47.15%, 85.66%, and 89.07%, respectively. In essence, this research developed effective water quality traceability and predictive analysis methods in semi-arid river basins. It provided an effective tool for water quality surveillance in semi-arid river basins and imparts a scientific scaffold for the environmental stewardship endeavors of pertinent authorities.

Contribution of nonpoint source pollution from baseflow of a typical agriculture-intensive basin in northern China.

Baseflow is an essential component of total surface runoff that is widely considered one of the most influential factors regarding water quality via nonpoint source (NPS) pollution. Previously, many researchers and policy makers have directed their efforts toward surface runoff pollution, largely ignoring nutrient delivery via baseflow. Taking a typical agriculture-intensive basin of northern China as an example, this study explored the spatiotemporal characteristics of baseflow and pollution load in relation to NPS pollution. Baseflow was quantified using digital filtering techniques, and the results together with observed pollution data were used to validate a physically based hydrological model, i.e., the Soil and Water Assessment Tool. Then, the spatial and temporal distribution characteristics of NPS and baseflow pollution were investigated using the modeling results. Results indicated that baseflow contribution to total runoff accounted for more than 70% during the studied years (2016-2018), and 84.15% of the basin area showed non-point source pollution dominated by baseflow pollution; both baseflow and its pollution load were greater in the nonflood seasons (spring, autumn, and winter) than in the flood season (summer); the spatial distribution of baseflow total nitrogen and total phosphorus pollution intensity showed higher values in the east and lower values in the west; the scaling effects of baseflow and its pollution load was found with increasing basin area. The results of our study highlighted the necessity for management of pollution load via baseflow in the river basin and provided reference information for improvement of NPS pollution management in other similar basins.

Assessing alterations of water level due to environmental water allocation at multiple temporal scales and its impact on water quality in Baiyangdian Lake, China.

Lakes in arid/semiarid regions face problems of insufficient inflow and degradation of water quality, which threaten the health of the lake ecosystem. Baiyangdian Lake (BYDL), the largest lake in the North China Plain, is confronted with such challenges. The objective of this study was to improve understanding of how changes in water level influence water quality in the BYDL at different temporal scales, especially related to implementations of intermittent environmental water allocation activities in the past two decades, by using data on monthly lake water level, climate factors of precipitation and temperature, and lake water quality. The Mann-Kendall method and continuous wavelet analysis revealed that the lake water level shows a significant decreasing trend after 1967, and the period of 16-year was identified as the principal period for 1950-2018. Based on cross-wavelet transform and wavelet coherence analysis, the periodic agreement and coherence between water level and climatic factors decreased after 1997, when environmental water allocations started, indicating that the influences of climatic factors, i.e., precipitation and temperature, became weak. By utilizing the cross-wavelet transform and wavelet coherence analysis methods, the relationships between lake water level and water quality parameters of chemical oxygen demand, ammonia nitrogen, total nitrogen, and total phosphorus were investigated. We found that the change in source and amount of environmental water allocation is one possible reason for the temporal evolution in joint variability between lake water level and water quality. Meanwhile, a dilution effect of freshwater allocated to BYDL was detected in the time-frequency domain. However, the result also indicates that the driving mechanism of water quality is complex due to the combined impacts of water allocation, nonpoint source pollution in the rainy season, and nutrient release from lake sediment. Our findings improve the general understanding of changes in water level in lakes located in arid and semiarid regions under climate change and intensive human activities, and also provide valuable knowledge for decision making in aquatic ecosystem restoration of BYDL and other similar lakes.

Assessment of lake eutrophication using a novel multidimensional similarity cloud model.

Lake eutrophication is characterized by a variety of indicators, including nitrogen and phosphorus concentrations, chemical oxygen demand, chlorophyll levels, and water transparency. In this study, a multidimensional similarity cloud model (MSCM) is combined with a random weighting method to reduce the impacts of random errors in eutrophication monitoring data and the fuzziness of lake eutrophication definitions on the consistency and reliability of lake eutrophication evaluations. Measured samples are assigned to lake eutrophication levels based on the cosine of the angle between the cloud digital characteristics vectors of each sample and those of each eutrophication grade. To field test this method, the eutrophication level of Nansi Lake in Shandong Province was evaluated based on monitoring data collected in 2009-2016. Results demonstrate that, in 2009 and in 2011-2015, the upper lake of Nansi Lake exhibited moderate eutrophication while the lower lake exhibited mild eutrophication. In 2010, 2016, elevated concentrations of total nitrogen and total phosphorus led to an increase in the eutrophication level of the lower lake, matching that of the upper lake. Based on the results of these field tests, we conclude that the MSCM presented in this study provides a more flexible and effective method for evaluating lake eutrophication data than the existing multidimensional normal cloud model.

Non-point source pollution risks in a drinking water protection zone based on remote sensing data embedded within a nutrient budget model.

A simple, transparent and reliable method for evaluating non-point source pollution (NPSP) risks to drinking water source areas lacking observational data is proposed herein. The NPSP risks are assessed by using nutrient budget models for total nitrogen and total phosphorus, making the best use of remote sensing and field survey data. We demonstrate its potential using a case study of the Chaihe Reservoir in northeastern China. Fertilizer inputs and crop-uptake outputs were estimated based on normalized difference vegetation index, which is derived from remote sensing as indicators of crop growth and production. The nutrient balances for this area showed surpluses of both N and P within the soil system. Estimated imbalances per unit area were consistent with statistical relationships derived from all Chinese counties, demonstrating that the proposed method is reliable. The surplus P amounts were higher than the standard threshold for NPSP risks, indicating the existence of a potential contamination risk of P to this drinking water source.