Water Quality Monitoring Data Research Articles

Evaluating Current Water Quality Monitoring System on Hau River, Mekong Delta, Vietnam Using Multivariate Statistical Techniques

This study aims to assess the sampling sites and frequencies of sampling of the existing surface water quality monitoring on Hau River using multivariate analysis techniques. Principal Component Analysis (PCA) and Cluster Analysis (CA) were used to analyze the water quality monitoring data collected every month in 2018 from 8 sampling stations. Surface water quality parameters including pH, temperature, dissolved oxygen (DO), total suspended solids (TSS), nitrate (N-NO3-), phosphate (P-PO43-), chemical oxygen demand (COD) and coliforms were used in the PCA and CA analyses. The findings indicated that the Hau River water quality was polluted by TSS, COD and coliforms in which COD was high in dry season, TSS was high in wet season and coliforms were high all year round. The PCA revealed that pH, temperature, DO, TSS, N-NO3-, P-PO43-, COD and coliforms influenced on the water quality, therefore, relevant for examination in the water samples. These water quality variables were affected by various polluting sources, for examples, runoff, human activities, and hydrological influence. Cluster analysis suggested that the current monitoring program could be reduced from 8 to 3-4 points and 12 to 3-4 times per year. This monitoring program could save the total budget for up to 42%. The findings of the present study could be useful to the policy maker especially to those who are dealing with surface water monitoring systems. The multivariate statistical techniques could be used to assess the surface water quality monitoring network.

Design and Analysis of a Water Quality Monitoring Data Service Platform

Water is one of the basic resources for human survival. Water pollution monitoring and protection have been becoming a major problem for many countries all over the world. Most traditional water quality monitoring systems, however, generally focus only on water quality data collection, ignoring data analysis and data mining. In addition, some dirty data and data loss may occur due to power failures or transmission failures, further affecting data analysis and its application. In order to meet these needs, by using Internet of things, cloud computing, and big data technologies, we designed and implemented a water quality monitoring data intelligent service platform in C# and PHP language. The platform includes monitoring point addition, monitoring point map labeling, monitoring data uploading, monitoring data processing, early warning of exceeding the standard of monitoring indicators, and other functions modules. Using this platform, we can realize the automatic collection of water quality monitoring data, data cleaning, data analysis, intelligent early warning and early warning information push, and other functions. For better security and convenience, we deployed the system in the Tencent Cloud and tested it. The testing results showed that the data analysis platform could run well and will provide decision support for water resource protection.

Three-Dimensional Hydrodynamic and Water Quality Integrative Simulation System Based on GIS of Donghu in Wuhan

The three-dimensional hydrodynamic and water quality integrative simulation system is established based on the coupling of three-dimensional hydrodynamic model and WASP water quality model and GIS control technology in this paper. It integrates the functions of unstructured grid generation, three-dimensional hydrodynamic and water quality simulation and three-dimensional visual display. When the basic lake data is imported, the system can simulate and display the three-dimensional dynamic change process of lake hydrodynamic parameters and water quality parameters in a one-stop way. Numerical simulation was carried out on its hydrodynamic and water quality, taking Donghu in Wuhan as the study area. The system was tested with topographic data, water quality monitoring data, hydrological data and meteorological data of Donghu in 2018. Compared with the measured results, the error is small, which shows that the system could be used for hydrodynamic and water quality simulation of inland lakes.

Visualization Research and Application of Water Quality Monitoring Data Based on Echarts

Visualization Research and Application of Water Quality Monitoring Data Based on Echarts

Water quality affected by floating debris near the dam section of Three Gorges Reservoir

每年汛期与蓄水期三峡水库近坝段水域会有大量漂浮物聚集，为探索三峡水库近坝段水域（坝前及以上约12.7 km长的河段）水面漂浮物对水质的影响，2018年开展了漂浮物覆盖水体水质跟踪监测和漂浮物浸泡试验，并以2014-2018年的漂浮物产量和近坝段水域水质监测数据为基础进行了相关分析与回归分析.结果表明：漂浮物会提高坝前覆盖水体的氮类营养盐水平和有机污染物浓度，引起河湾漂浮物覆盖水域氨氮（NH₃-N）浓度升高，致使氮类营养盐组成的变化和由于高锰酸盐指数/总有机碳比值（COD_Mn/TOC）的差异变化对水体产生有机污染.除NH₃-N外，坝前水域受漂浮物影响程度大于河湾区域，漂浮物对河湾水质的影响在蓄水期更为明显，漂浮物覆盖水体垂直方向上2 m内水质因子无明显分层现象；相比综合类漂浮物，植物类漂浮物对水质的影响更迅速和明显；漂浮物仅在其覆盖的水体小范围内对氮类营养盐指标造成影响，漂浮物产量的增加会增大近坝段水域水体悬浮物、有机污染物和还原性无机物质（COD_Mn）浓度，形成一定的影响规律.因此，合理布置清漂作业点，高效及时地开展漂浮物清理工作，短期内优先打捞植物类漂浮物，合理实施水库调度以减少漂浮物聚集量与缩短滞留时长，加强漂浮物影响水体的水质监测对近坝区河段水环境保护意义重大.;During the flood season and impoundment period, there will be a large amount of floating debris gathering in the water area near the dam of the Three Gorges Reservoir. In order to explore the influence of water surface floating debris on the water quality near the dam section of the Three Gorges Reservoir (about 12.7 km long before and after the dam), floating immersion test and water quality monitoring of floating body covered water were carried out in 2018. Correlation analysis and regression analysis were used to analyze both the drift production of 2014-2018 and the water quality monitoring data of the near dam section. The results showed that the floating debris increased the concentration of nitrogen nutrient salts and organic pollutants in front of the dam, and led to the increase of NH₃-N concentration in the bay area resulting in the change of nitrogen nutrients composition and organic pollutants pollution due to the difference of COD_Mn/TOC ratio. In addition to NH₃-N, the influence of floating debris on the water quality in front of the dam was greater than that in the bay area. For the bay area, this influence became more obvious during the impoundment period. There was no obvious stratification of water quality factors within 2 m in the vertical direction of the water body covered by floating debris. Comparing to the comprehensive floating debris, the effect of plant floating debris on water quality was more rapid and obvious. The floating debris only affected the nitrogen nutrient index within a small range of water covered by it. The increase of floating debris production led to the concentration increase of suspended matter, organic pollutants and reducing inorganic substances (COD_Mn) in the water near the dam, forming a certain influence law. Therefore, it is of great significance for water environment protection to arrange the floating debris cleaning operation points reasonably, to carry out floating debris cleaning efficiently and timely, to give priority to the salvage of plant floating debris in a short period time, to implement reservoir scheduling reasonably in order to slow down the accumulation and retention time of floating debris, to enhance the monitoring about the impact of floating debris on water quality near the dam.

Forecasting Past and Future Trend of Physio-Chemical Parameters in Dal Lake, Srinagar Kashmir, India using Statistical Analysis and Modelling

The paper presents an overview of recent physiochemical investigations on Dal lake with emphasis on lake, longterm water quality monitoring data from Lake and Water Development Authority (LAWDA1997-2017, published and unpublished data) with present analysis of Dal Lake to compare the water trends for pH, dissolved oxygen, chemical oxygen demand(COD),NO3 -N,Total Phosphorus(TP) and Transparency. The main sampling efforts include visit to 36 samplingsitesto find the past and future trend of these physio chemicalparameters(pH, DO, COD, NO3 -N, TP and Transparency).Maximum decreasing trendline was found for pH in Nigeen basin in summer season and lowertrends were found inNehru park basin in winter season. Maximum decreasing trendline was found for DO in Nigeen basin in summer season and lower trends were found in Nehru park basin in winter season. COD has shown maximum increasing trends in all basins mostly in Nigeen basin in summer season and lower decreasing trends in Hazratbal basin in autumn season, concentration of NO3 -N and TP have shown increasing trends in all basins of lake mostly in Nigeen basin in summer season and lower increasing trends in Nehru park basin in winter season. Trend of transparency has shown decreasing trends in all basins of lake particularly in Nigeen basin in summer season and lower trends can be seen mostly in Nehru park basin in winter season. Tourism influx,maximum use of pesticides and fertilizers in the horticultureandagriculture fields during the growing season (June–August) in the Dal Lake shows a drastic change of these parameters through these years and the influx of tourists visiting this lake has increased in the summer months which isresponsible for eutrophication of Dal Lake and needs serious managerial actions.

Impact of fecal contamination on surface water quality in the São Francisco River hydrographic basin in Minas Gerais, Brazil.

Proper water quality monitoring is a valuable tool for water resource management, helping to identify polluting sources and risks related to the use of water resources. One of the main types of contamination found in Brazilian water bodies is fecal contamination, which originates mainly from point source pollution through wastewater disposal. Thus, this study analyzed water quality monitoring data from the responsible environmental body (Minas Gerais Institute of Water Management, IGAM), related to the fecal contamination indicator (FCI), for the years 2000-2018. This was done for the Minas Gerais portion of the São Francisco River basin (SFRB-MG), one of the most important basins in the country. The 10 sub-basins in the area were compared using statistical tools. The work found significant differences between the sub-basins in terms of FCI concentration, highlighting the most impacted ones (SF2, SF3, and SF5) as also being the most densely populated. It is necessary to invest in sanitation measures in order to ensure that water resources are preserved, as well as to reduce the public health risks of downstream municipalities that are supplied with previously contaminated water.

Effect of Rainfall Intensity on the Content of Nitrogen and Phosphorus Components in Plateau Areas: A Case Study of the Fengyu River Watershed

The runoff formed by rainfall carrying various land surface materials into rivers and lakes is an important factor leading to a change in water quality, and the characteristics of nitrogen and phosphorus output of rivers under different rainfall intensities are different. This study explores the impact of rainfall intensity on the water quality of the Fengyu River Watershed in the plateau agricultural region, based on the water quality monitoring data of the export section of the Fengyu River Watershed from 2011 to 2013, combined with local rainfall monitoring. The effects of four rainfall intensities (light rain, moderate rain, heavy rain, and torrential rain) on the content of different nitrogen and phosphorus components in water were analyzed. The results show that the rainfall intensity has a significant effect on the nitrogen and phosphorus emissions of the Fengyu River Watershed. The average nitrogen and phosphorus concentrations of all components are lower in light rain (<10 mm) and moderate rain (10-25 mm), and higher in heavy rain (25-50 mm) and torrential rain (50-100 mm). The percentage of NH4+-N (57.14%-76.85%) to TN is larger than that of PN (23.15%-42.86%), and the percentage of TDP (22.73%-28.00%) to TP is smaller than that of PP (72.00%-77.27%). The nitrogen concentration of different forms is:TN > NH4+-N > PN; the phosphorus concentration of different forms is:TP > PP > TDP.

Characteristics and trends of water quality in underground caverns in island

Underground caverns can be used as a supplementary water resource in those islands away from the continent. The groundwater quality is then becoming an important condition for ensuring the safety of water supply. Based on the water quality monitoring data from April 2017 to July 2019, the trend of water quality indices such as pH, CODMn(permanganate index), NH3-N(ammonia nitrogen), turbidity, TN(total nitrogen), TP(total phosphorus) and chloride were analysed by Kendall-trend-test method. The Pearson-correlation-method is also used to analyse the relationship among these indices in this study. The results show that: (1) For different forms of underground caverns, the concentration of pollutants and the number of bacteria in fully closed cavern is relatively low compared to the semi-closed cavern, the total number of bacteria is only 9 CFU/mL, and the DO(the dissolved oxygen) is as low as 5.12 mg/L. The concentration of pollutants in underground caverns with surface water is higher than the rainwater, which demonstrates that the groundwater quality is actually worse than the water source. (2) The water quality of underground caverns will change variously with time. The concentrations of CODMn and NH3-N will decrease gradually with time, the TN will increase gradually, the concentration of TP will decrease significantly in fully closed caverns, while it will not change too much in semi-closed caverns. (3) Correlation analysis showed that there was no significant relationship among TP, TN and chlorophyll in different forms of caverns. In order to ensure the safety of water quality, the underground caverns should be disinfected, sterilized, and moreover, the sludge should also be cleaned up regularly.

Analysis of Water Quality Monitoring Data Based on LSTM

Water quality is a very important topic for lives. Nowadays, the intelligent science and technology is developing rapidly, and Internet of Things (IoT) plays a more prominent role in many fields. In this paper, we use IoT and intelligent technology to solve the problem of water quality analysis. With IoT linked with water quality monitoring, w1e first collect the data related to domestic water quality and prepare them for analysis. Then by selecting PH, DO, COD, NH3-H standards as the basis, and using LSTM algorithm to carry out digression and simulation, we build a training model for water quality prediction. The predicted values possibly mark the sudden upcoming of pollutions, which reminds the inspectors of attentions and preventions. As a result, it can ensure the safety of domestic water.

Analysis of Water Quality Monitoring Data Based on LSTM

Analysis of Water Quality Monitoring Data Based on LSTM

The effect of sampling frequency and strategy on water quality modelling driven by high-frequency monitoring data in a boreal catchment

With conventional water quality monitoring based on grab sampling, usually carried out once a month, it is quite challenging to obtain reliable sediment and nutrient loading estimates, which is a pre-requisite for testing of water quality models. Despite the growing availability of high-frequency water quality monitoring data obtained by using modern sensors, their use in the calibration of water quality models is still limited. The main objective of this study is to evaluate six years of continuous, high-frequency water quality monitoring data set from a case study carried out in a medium-sized, boreal catchment in southern Finland to be used as a source for the calibration and testing of the Soil & Water Assessment Tool (SWAT). This objective is accomplished by developing a set of ‘sub-sampling’ scenarios focused on quantifying the effect of the sampling frequency (12 vs. 26 samples per year) and strategy (regular vs. flow-proportional sampling) on the model performance and output uncertainty. The goodness-of-fit of the model calibrated against high-frequency data (‘benchmark’), evaluated using the Kling-Gupta Efficiency index for total suspended solids (TSS), nitrate and total nitrogen (NO3-N and TN) and total phosphorus (TP) daily loads ranged between 0.76 and 0.83 (0.69 and 0.73 in validation period). Overall, the model calibrated against low-frequency data performed worse when evaluated against high-frequency data and compared with the benchmark model for each of the studied water quality parameters. The results show that increasing the sampling frequency from 12 to 26 samples per year leads to an improvement in the model performance, particularly for TSS and TP loads. In contrast to the sampling frequency, the evidence for the effect of the sampling strategy on the model performance was much weaker. The model output uncertainty due to different realizations of sub-sampling scenarios was high for four analysed output indices: basin-averaged, long-term average annual values of soil erosion rate, denitrification rate, NO3-N yield and soluble P yield. This study demonstrates that more attention should be paid to the calibration data as a source of uncertainty in model predictions. It also provides evidence for either a wider adoption of modern sensors providing high-frequency data, or for increasing the grab sampling frequency to reduce the uncertainty of loading estimates, particularly in rivers with flashy flow regime such as the Vantaanjoki River.

Spatio-temporal Distribution Characteristics of Water Quality in Miju River and Erhai Lake

Liu, J.; Xu, J.; Chen, J.; Hong, X., and Zhou, M., 2019. Spatio-temporal distribution characteristics of water quality in Miju River and Erhai Lake. In: Guido-Aldana, P.A. and Mulahasan, S. (eds.), Advances in Water Resources and Exploration. Journal of Coastal Research, Special Issue No. 93, pp. 31–38. Coconut Creek (Florida), ISSN 0749-0208.In the research related to the water resources management and prevention of pollution, it is of great practical significance to analyze the spatial and temporal distribution characteristics of the water quality. The present work deals with the study on the actual water quality monitoring data obtained from the Miju River monitoring sections in the Erhai Lake during 2011-2016. Six water quality indicators were selected for investigation using the comprehensive pollution index method and the principal component analysis method, in order to analyze the spatial and temporal distribution characteristics of water quality in the Miju River Basin. The results of the comprehensive pollution index method showed that the water quality of the Miju River has not changed much in the past 6 years, and the water body has only been slightly polluted. Additionally, the water quality of the Jiangweiqiao section was slightly inferior to that of the Yinqiaocun section. Principal component analysis method showed that the nitrogen pollution was the dominant factor in the wet season, followed by phosphorus, pH and dissolved oxygen. In the normal season, the dissolved oxygen and pH of the water were the main factors, followed by phosphorus and ammonia nitrogen. In the dry season, the dissolved oxygen, ammonia nitrogen and organic matter pollution were the main influencing factors followed by phosphorus and pH. The water quality of the Miju River in the past 3 years was slightly worse than that in the initial 3 years, and the overall performance of the water quality of the Miju River was relatively best during the dry season followed by the normal season, while the water quality was worst during the wet season. Furthermore, the water quality variation trends of Yinqiaocun and the Jiangweiqiao sections were observed to be similar.

Community drinking water data on the National Environmental Public Health Tracking Network: a surveillance summary of data from 2000 to 2010

This report describes the available drinking water quality monitoring data on the Centers for Disease Control and Prevention (CDC) National Environmental Public Health Tracking Network (Tracking Network). This surveillance summary serves to identify the degree to which ten drinking water contaminants are present in finished water delivered to populations served by community water systems (CWS) in 24 states from 2000 to 2010. For each state, data were collected from every CWS. CWS are sampled on a monitoring schedule established by the Environmental Protection Agency (EPA) for each contaminant monitored. Annual mean and maximum concentrations by CWS for ten water contaminants were summarized from 2000 to 2010 for 24 states. For each contaminant, we calculated the number and percent of CWS with mean and maximum concentrations above the maximum contaminant level (MCL) and the number and percent of population served by CWS with mean and maximum concentrations above the MCL by year and then calculated the median number of those exceedances for the 11-year period. We also summarized these measures by CWS size and by state and identified the source water used by those CWS with exceedances of the MCL. The contaminants that occur more frequently in CWS with annual mean and annual maximum concentrations greater than the MCL include the disinfection byproducts, total trihalomethanes (TTHM), and haloacetic acids (HAA5); arsenic; nitrate; radium and uranium. A very high proportion of exceedances based on MCLs occurred mostly in very small and small CWS, which serve a year-round population of 3,300 or less. Arsenic in New Mexico and disinfection byproducts HAA5 and TTHM, represent the greatest health risk in terms of exposure to regulated drinking water contaminants. Very small and small CWS are the systems’ greatest difficulty in achieving compliance.

Characterization of Surface Water Quality along Ismailia Canal, Nile River, Egypt

Ismailia Canal, one of the main branches of the Nile River in Egypt, is considered as one of the most important irrigation and drinking water source for Ismailia, Port Said and Suez governorates. The canal received industrial, municipal and agricultural wastewater which caused deterioration in its water quality. To determine the spatial variability of Ismailia canal water quality and identify the sources of pollution that presently affect the canal water quality, the scope of study was divided into three main parts. In the first part, the assessment of water quality data was monitored at thirty different sampling station along the canal, over the period of two years (2017, 2018), using 30 physicochemical and biological water quality variables and using multivariate statistics of principal components analysis (PCA) to interpret before the step of analyzing the concealed variables that determined the variance of observed water quality of various source points was conducted. In the second part, the major dominant factors responsible for canal water quality variations was driven. In the third part, K-means algorithm was used for cluster characterization analysis.The result of PCA shows that 8 principal components contained the key variables and accounted for 87.34% of total variance of the canal water quality and the dominant water quality parameters were: Lead (Pb), Total Phosphorus (TP), Ammonia (NH3), Turbidity, Fecal Coliform (FC), Iron (Fe) and Aluminum (AL). However, the results from K-Means Algorithm for clustering analysis were based on the dominant parameters concentrations, determined 5 cluster groups and produced cluster centers (prototypes). Referring to the clustering classification, a noted water quality was deteriorating as the cluster number increased from 1 to 5, thus the cluster grouping could be used to identify the physical, chemical and biological processes creating the variations in the canal water quality parameters.This study provides an insight into the various statistical models, when water quality monitoring data are combined with spatial data for characterizing spatial and temporal trends, indicating their important potential for decreasing the costs associated with monitoring. This can also be very useful to international water resource authorities for the control and management of pollution and better protection of surface water quality.

Study on water and salt balance of plateau salt marsh wetland based on time-space watershed analysis

We analysed the eco-hydrological characteristics of the Bojiang Haizi River basin, which is the location of the Erdos Larus Relictus Nature Reserve plateau salt marsh wetland. The study found that the restoration of the plateau salt marsh is more of a water quality problem than a water quantity problem. Simply maintaining the balance of water volume without considering water quality will destroy the original stable ecosystem. Therefore, water balance analysis was conducted for the overall water resources in the basin on the basis of simulated data of the Soil and Water Assessment Tool module. We examined remote sensing and water quality monitoring data via geographic information system-3D technology to meet the requirements of water quality and quantity in wetland restoration. We established the hydrological dynamic relationship model of lake storage capacity-elevation-area-salinity and found that the lake presents an alternating cyclic rule of salt accumulation and dilution during seasonal changes. This pattern is an important guarantee for the healthy and sustainable development of the salt marsh wetland. Lastly, the survival salinity of the organism was selected as the target salinity (5 g/L), and the corresponding target water amount was simulated as 20.17 × 106 m3; the target lake area was 9.48 km2. Through an analysis of three water transfer scenarios, we found that under the optimum balance condition between water quantity and salt concentration, simulating the water transfer mode in precipitation replenishment is an effective means to restore the wetland during breeding season. The findings of this study may improve our understanding of the eco-hydrological characteristics of plateau salt marsh wetlands and help managers protect and restore water balance using water–salt dynamic models.

Temporal–spatial distribution characteristics and combinatorial risk probabilities of water pollutants in the Guo River Basin, China

This study used water-quality monitoring data from seven monitoring stations in the Guo River Basin from 2003 to 2012 and three selected water-quality indexes (total phosphorus: TP, ammonium nitrogen: NH3–N, and permanganate index: CODMn) that were divided into five categories (classes I, II, III, IV, and V) according to Chinese environmental quality standards for surface water (GB 3838–2002). The results indicated that the concentrations of TP, NH3–N, and CODMn showed a significant decreasing trend at Xuanwu Sluice, Huangzhuang, Boxian Sluice, Guoyang, and Mengcheng Sluice by the Mann–Kendall trend analysis; the water pollution was worse in the upstream region, but it was relatively good in the downstream region, and the water pollutant concentrations improved significantly by the cluster analysis. In this study, a marginal distribution of water-quality indexes and a combinatorial probability distribution of the copula function are established based on the basic principle of the copula function. The Gaussian copula function was selected to calculate the combinatorial risk probability of the water pollutants by the fit test of copula function and the goodness-of-fit evaluation. Results show that the combinatorial risk probability varies substantially when the water-quality indexes reach different states under different combinations, such as the combinatorial risk probability showed a decreasing trend with increasing TP concentration when the NH3–N concentration was certain and CODMn reached the class III or class IV level at Xuanwu Sluice and Boxian Sluice; the combinatorial risk probability presented a decreasing trend with increasing TP concentration when the NH3–N and CODMn concentrations were certain at Mengcheng Sluice and Longkangji; the combinatorial risk probability presented a trend that first increased and then decreased with increasing CODMn concentration when the TP and NH3–N concentrations were certain. The temporal–spatial distribution characteristics and combinatorial risk probabilities obtained in this study will provide a basis for management, water pollution control, water resources protection, and sustainable development of the basin.

A flood of information: Using Sentinel-3 water colour products to assure continuity in the monitoring of water quality trends in the Great Barrier Reef (Australia)

An operational method to assess trends in marine water composition and ecosystem health during flood periods has been developed for the Great Barrier Reef (GBR), Queensland, Australia. This method integrates satellite water colour data with field water quality and ecosystem monitoring data and involves the classification of Moderate-Resolution Imaging Spectroradiometer (MODIS satellite) pixels into six distinct water bodies using a “wet season” colour scale developed specifically for the GBR. Using this information, several monitoring and reporting products have been derived and are operationally implemented into a long-term water quality monitoring program for the GBR. However, MODIS sensors are aging and a long-term monitoring solution is needed. This study reviewed the water colour monitoring products currently used in the GBR. It tested the feasibility to transition these methods from historical MODIS satellite imagery to the new Sentinel-3 satellite of the European Space Agency and from the wet season colour scale to the historical Forel-Ule colour scale, using a freely-distributed Forel Ule (FU) Satellite Toolbox. Monitoring products derived from both satellites and colour scales showed very similar patterns across two case study regions of the GBR, the Wet Tropics and Burdekin marine regions, over the 2017-18 wet season. The results obtained in this study highlighted the potential of using FU Sentinel-3 imagery for the mapping of GBR marine water bodies, including flood conditions. Furthermore, the operational monitoring products and frameworks developed for the GBR are likely to provide valuable foundations for analysis of FU Sentinel-3 data in the future. Such satellite water colour datasets and frameworks will be instrumental to better understand the impact of floods and reduced water clarity on marine ecosystems, as well as to support water quality management and facilitate catchment management policy in the GBR and worldwide.

Exploring the application of artificial intelligence technology for identification of water pollution characteristics and tracing the source of water quality pollutants.

Point sources are important routes through which pollutants enter rivers. It is important to identify the characteristics of and trace the origins of water pollutants. In this study, an artificial intelligence system called the integrated long short-term memory network (LSTM), using cross-correlation and association rules (Apriori), was used to identify the characteristics of water pollutants and trace industrial point sources of pollutants. Water quality monitoring data from Shandong Province, China, were used to verify the applicability of the artificial intelligence system using a cross-correlation method to develop a water quality cross-correlation map. The map was used to identify highly correlated pollutants affecting water quality, then the association rules (Apriori) were used to track the pollutants to industries common in the study area. The highly correlated water pollutants and relevant industries were used as inputs for the LSTM to determine how well the LSTM traced sources of water pollutants. The results showed that (1) changes in water quality were affected in different ways by different industries and different distributions and production cycles of the pollutant point sources; (2) water quality correlation maps can be used to identify regular and abnormal fluctuations in point source pollutant emissions by identifying changes in water quality characteristics and frequent itemsets in water quality indices can be used to trace the industries that most strongly affect water quality; and (3) the LSTM accurately traced point sources of future changes in water quality. In conclusion, the artificial intelligence scheme described here can be applied to aquatic systems.

Multi-scale relationship between land use/land cover types and water quality in different pollution source areas in Fuxian Lake Basin.

The spatial-temporal evolution of land use and land cover (LULC) and its multi-scale impact on the water environment is becoming highly significant in the LULC research field. The current research results show that the more significant scale impact on LULC and water quality in the whole basin and the riparian buffer scale is unclear. A consensus has not been reached about the optimal spatial scale problem in the relationship between the LULC and water quality. The typical lake basin of the Fuxian Lake watershed was used as the research area and the scale relationship between the LULC and water quality was taken as the research object. High resolution remote sensing images, archival resources of surveying, mapping and geographic information, and the monitoring data of water quality were utilized as the main data sources. Remote sensing and Geometric Information Technology were applied. A multi-scale object random forest algorithm (MSORF) was used to raise the classification accuracy of the high resolution remote sensing images from 2005 to 2017 in the basin and the multi-scale relationship between the two was discussed using the Pearson correlation analysis method. From 2005 to 2017, the water quality indicators (Chemical Oxygen Demand (COD), Total Phosphorous (TP), Total Nitrogen (TN)) of nine rivers in the lake’s basin and the Fuxian Lake center were used as response variables and the LULC type in the basin was interpreted as the explanation variable. The stepwise selection method was used to establish a relationship model for the water quality of the water entering the lake and the significance of the LULC type was established at p < 0.05.The results show that in the seven spatial scales, including the whole watershed, sub-basin, and the riparian buffer zone (100 m, 300 m, 500 m, 700 m, and 1,000 m): (1) whether it is in the whole basin or buffer zone of different pollution source areas, impervious surface area (ISA), or other land and is positively correlated with the water quality and promotes it; (2) forestry and grass cover is another important factor and is negatively correlated with water quality; (3) cropping land is not a major factor explaining the decline in water quality; (4) the 300 m buffer zone of the river is the strongest spatial scale for the LULC type to affect the Chemical Oxygen Demand (COD). Reasonable planning for the proportion of land types in the riparian zone and control over the development of urban land in the river basin is necessary for the improvement of the urban river water quality. Some studies have found that the relationship between LULC and water quality in the 100 m buffer zone is more significant than the whole basin scale. While our study is consistent with the results of research conducted by relevant scholars in Aibi Lake in Xinjiang, and Erhai and Fuxian Lakes in Yunnan. Thus, it may be inferred that for the plateau lake basin, the 300 m riparian buffer is the strongest spatial scale for the LULC type to affect COD.