Identification of agricultural surface source pollution in plain river network areas based on 3D-EEMs and convolutional neural networks.

Agricultural non-point sources, as major sources of organic pollution, continue to flow into the river network area of the Jiangnan Plain, posing a serious threat to the quality of water bodies, the ecological environment, and human health. Therefore, there is an urgent need for a method that can accurately identify various types of agricultural organic pollution to prevent the water ecosystems in the region from significant organic pollution. In this study, a network model called RA-GoogLeNet is proposed for accurately identifying agricultural organic pollution in the river network area of the Jiangnan Plain. RA-GoogLeNet uses fluorescence spectral data of agricultural non-point source water quality in Changzhou Changdang Lake Basin, based on GoogLeNet architecture, and adds an efficient channel attention (ECA) mechanism to its A-Inception module, which enables the model to automatically learn the importance of independent channel features. ResNet are used to connect each A-Reception module. The experimental results show that RA-GoogLeNet performs well in fluorescence spectral classification of water quality, with an accuracy of 96.3%, which is 1.2% higher than the baseline model, and has good recall and F1 score. This study provides powerful technical support for the traceability of agricultural organic pollution.

Model evaluation of total phosphorus prediction based on model accuracy and interpretability for the surface water in the river network of the Jiangnan Plain, China.

Due to climatic and hydrological changes and human activities, eutrophication and frequent outbreaks of cyanobacteria are prominent in the Jiangnan Plain basin of China. Therefore, building a suitable model to accurately predict the phosphorus concentration in surface water is of practical significance to prevent the above problems. This study built 10 models to predict the phosphorus element in the surface water of the river network in the Jiangnan Plain. The main water types in the basin include the Yangtze River, the Beijing-Hangzhou Canal, and the Gehu Lake. The 10 models in different datasets have been comprehensively evaluated by the prediction accuracy and interpretability of the model, and the calculation of the partial dependence diagram (PDP) and SHAP has proved that there is a transparent response relationship between phosphorus and different factors. The results show that the Yangtze River, Beijing-Hangzhou Canal, and Gehu Lake are suitable for random forest, linear regression, and random forest models, respectively, under the comprehensive evaluation of the prediction accuracy and interpretability of the model. Models with low prediction accuracy often show strong interpretability. In different water body types, turbidity, water temperature, and chlorophyll-a are the three factors that affect the model in predicting phosphorus.

Co-Occurrence of Microcystins and Taste-and-Odor Compounds in Drinking Water Source and Their Removal in a Full-Scale Drinking Water Treatment Plant.

The co-occurrence of cyanotoxins and taste-and-odor compounds are a growing concern for drinking water treatment plants (DWTPs) suffering cyanobacteria in water resources. The dissolved and cell-bound forms of three microcystin (MC) congeners (MC-LR, MC-RR and MC-YR) and four taste-and-odor compounds (geosmin, 2-methyl isoborneol, ß-cyclocitral and ß-ionone) were investigated monthly from August 2011 to July 2012 in the eastern drinking water source of Lake Chaohu. The total concentrations of microcystins and taste-and-odor compounds reached 8.86 µg/L and 250.7 ng/L, respectively. The seasonal trends of microcystins were not consistent with those of the taste-and-odor compounds, which were accompanied by dominant species Microcystis and Dolichospermum. The fate of the cyanobacteria and metabolites were determined simultaneously after the processes of coagulation/flocculation, sedimentation, filtration and chlorination in the associated full-scale DWTP. The dissolved fractions with elevated concentrations were detected after some steps and the breakthrough of cyanobacteria and metabolites were even observed in finished water. Chlorophyll-a limits at intake were established for the drinking water source based on our investigation of multiple metabolites, seasonal variations and their elimination rates in the DWTP. Not only microcystins but also taste-and-odor compounds should be taken into account to guide the management in source water and in DWTPs.

The establishment of preliminary safety threshold values for cyanobacteria based on periodic variations in different microcystin congeners in Lake Chaohu, China.

As harmful cyanobacterial proliferation threatens the safety of drinking water supplies worldwide, it is essential to establish a safety threshold (ST) for cyanobacteria to control cyanobacterial density effectively in water sources. For this purpose, cyanobacterial abundance, microcystin (MC) production, and environmental parameters were monitored monthly from September 2011 to August 2012 in one drinking water source of Lake Chaohu. The cyanobacterial density ranged from 1400 to 220 000 cells per mL with the succession of two dominant species Microcystis and Dolichospermum, which was determined by water temperature and nutrient loading. The MC concentrations were correlated significantly with the cyanobacterial density and they varied between 0.28 and 8.86 µg L(-1). Therefore, the characteristics of MC cell quotas were classified according to four stages of the development of cyanobacteria, namely: recruitment, multiplication, decline and dormancy. The ST for cyanobacteria was established for different periods based on the MC cell quota and its guideline wherein three commonly monitored MC congeners (MC-LR, -RR and -YR) were considered in the present study. Its reliability was verified in the water source using the data collected between June 2013 and May 2014. The results highlighted the necessity to classify the ST-values in different periods referring to the main MC congeners rather than MC-LR, which will facilitate the management and control of toxic cyanobacterial proliferation in drinking water sources.