Water Quality Anomalies Research Articles

Detection to water quality for Yangtze River using a machine learning method

<p>The Yangtze River, the longest river in China and one of the most important water resources in the world, has been facing significant challenges regarding water pollution in recent years. The issue of water quality safety is related to the national economy and people's livelihood. Water pollution incidents not only damage the local water environment, but also seriously affect the drinking water safety of residents. Traditional chemical methods and other water quality anomaly detection methods are often time-consuming and may cause secondary pollution. This paper proposed a machine learning method used for detecting abnormalities of water quality in the Yangtze River, to provide technical support for ensuring water quality safety. The principle is that using the designed support vector machine separates anomalies and normal values, by doing so, anomalies can be mined. Since there are certain differences between the density of normal data and that of anomalous data, estimating the data density of both can assist promote the ability of the support vector machine to mine anomalies. Then, the probability of water quality anomalies is determined by analyzing the characteristics such as the density of outliers in the sequence. Finally, using the collected the data of water quality from forty different regions of the Yangtze River since 2018 to 2023 as the experimental dataset, and experimental results show that the proposed method can effectively detect the anomaly of water quality of Yangtze River.</p>

A remote sensing index for the detection of multi-type water quality anomalies in complex geographical environments

ABSTRACT Frequent water quality anomalies severely affect the ecological environment, hindering the protection, restoration, and sustainable use of inland freshwater ecosystems in Sustainable Development Goals (SDG) 15.1. Thus, there is an urgent need to conduct real-time monitoring and early warnings of various water quality anomalies. However, current remote sensing indices of water quality anomalies are aimed at only one specific water anomaly event in water regions, which makes it difficult to achieve high-precision and on-orbit detection of sudden water quality anomalies in complex geographical environments with the limited storage and computing resources of satellites. Therefore, this study proposed a remote sensing index for the detection of multi-type water quality anomalies in complex geographical environments by analyzing the spectral differences between different earth’s surfaces. The validation results indicated that the proposed index achieved satisfactory performance for the synchronous detection of most water quality anomalies and could be used directly in complex geographical environments to detect water anomalies. Overall, this study contributes to the realization of real-time water quality anomaly detection methods in complex geographical environments, which increases the possibility of on-orbit water quality anomaly detection.

An unsupervised water quality anomaly detection method based on a combination of time-frequency analysis and clustering.

Anomalies in water quality, which frequently arise due to pollution, constitute a substantial menace to human health. The preservation of public welfare critically entails the timely recognition of abnormal water quality. Conventional techniques for detecting water quality anomalies face obstacles such as the necessity of expert knowledge, limited accuracy in detection, and delays in identification. In this paper, we proposed an original unsupervised technique for identifying water quality anomalies combined with time-frequency analysis and clustering (TCAD). We chose time-frequency analysis because it effectively evaluates water quality changes, generating distinct multi-band signals that reflect different aspects of water quality dynamics. We also proposed a clustering technique which can identify water quality markers and amalgamate data from multi-band signals for accurate anomaly detection. We seek to clarify the reasoning behind our methodology by portraying how time-frequency analysis and clustering address the deficiencies of conventional methods. Our experiments evaluated various indicators of water quality, and the effectiveness of our proposed approach was supported by comparative analyses with commonly used models for detecting anomalies in water quality.

Associations of anomalous water temperature, salinity, and pH with change in water color of fish farming ponds

AbstractMaintaining proper green water is important for a fish farming pond. However, it remains unclear how to translate this important rule into specific water quality characteristics to associate or even forecast changes in water color. To address this issue, we conducted a study based on daily monitoring of six grouper ponds in Fangliao Township, Pingtung, Taiwan, from March to December 2018. We investigated the relationships between changes in water color and anomalies in water temperature, salinity, and pH, as these three parameters had the most complete records. We employed a long‐short‐term memory model to detect water quality anomalies by computing residual values. Our findings indicate that changes in water color were associated with anomalies in these parameters, with water temperature anomalies being the best indicator for early detection. In fact, the top 5% of water temperature anomalies could predict over 40% of the water color changes. Additionally, pH anomalies occurred immediately after the color changes. This rule‐to‐physicochemical‐parameter paradigm that we developed for grouper ponds could be applied to other aquaculture farms. We anticipate that with the help of advanced environmental surveillance models, such as the one we used, the prospect of autonomous fish farming will be realized.

Real-time water quality detection based on fluctuation feature analysis with the LSTM model

AbstractSignal analysis and anomaly detection for water pollution early warning systems are important and necessary. In view of the nonlinear and volatile characteristics of water quality time series, this paper proposes a new method for water anomaly detection based on fluctuation feature analysis. The method has two steps. First, the water quality time series data are used to calculate the residuals between the observed value and the predicted value with the long short-term memory (LSTM) network. Second, the dynamic features are extracted by sliding time window and described by the Approximate Entropy (ApEn) which are input to the anomaly detection model with Isolation Forest. Compared with traditional anomaly detection methods, the results obtained by the proposed method show better performance in distinguishing water quality anomalies. The proposed method can be applied to real-time water quality anomaly detection and early warning.

Monitoring groundwater quality with real-time data, stable water isotopes, and microbial community analysis: A comparison with conventional methods

Groundwater provides much of the world's potable water. Nevertheless, groundwater quality monitoring programmes often rely on a sporadic, slow, and narrowly focused combination of periodic manual sampling and laboratory analyses, such that some water quality deficiencies go undetected, or are detected too late to prevent adverse consequences. In an effort to address this shortcoming, we conducted enhanced monitoring of untreated groundwater quality over 12 months (February 2019–February 2020) in four shallow wells supplying potable water in Finland. We supplemented periodic manual sampling and laboratory analyses with (i) real-time online monitoring of physicochemical and hydrological parameters, (ii) analysis of stable water isotopes from groundwater and nearby surface waters, and (iii) microbial community analysis of groundwater via amplicon sequencing of the 16S rRNA gene and 16S rRNA. We also developed an early warning system (EWS) for detecting water quality anomalies by automating real-time online monitoring data collection, transfer, and analysis – using electrical conductivity (EC) and turbidity as indirect water quality indicators. Real-time online monitoring measurements were largely in fair agreement with periodic manual measurements, demonstrating their usefulness for monitoring water quality; and the findings of conventional monitoring, stable water isotopes, and microbial community analysis revealed indications of surface water intrusion and faecal contamination at some of the studied sites. With further advances in technology and affordability expected into the future, the supplementary methods used here could be more widely implemented to enhance groundwater quality monitoring – by contributing new insights and/or corroborating the findings of conventional analyses.

Deep Learning Methods for Predicting Tap-Water Quality Time Series in South Korea

South Korea currently lacks a real-time monitoring and anomaly detection system for detecting continuous tap water quality changes from the water source to faucet and pre-diagnosing hazards that threaten tap water safety. In this study, we constructed an accurate water quality prediction model that could comprehensively cover all water treatment facilities supplying tap water nationwide and verified the model using an integrated approach. To address the uncertainty of continuously changing water quality, we collected five years (2017–2021) of hourly water quality data from 33 large water purification plants and applied various deep learning techniques to construct an optimal prediction model. We repeated water quality prediction and evaluation over the following 24 h through a time series cross-validation of an untrained dataset of the previous five months. The optimized deep learning model achieved average and maximum prediction accuracy of 98.78 and 99.98%, respectively, and showed excellent performance in terms of the root mean squared error (0.0006), mean absolute error (0.0003), and Nash–Sutcliffe efficiency (0.9894). Thus, deep learning technology greatly improved the accuracy and efficiency of water quality prediction. The proposed model could provide prompt and accurate water quality information for large-scale water supply facilities nationwide and improve public health through the early diagnosis of water quality anomalies.

Preliminary investigation of saline water intrusion (SWI) and submarine groundwater discharge (SGD) along the south-eastern coast of Andhra Pradesh, India, using groundwater dynamics, sea surface temperature and field water quality anomalies.

Intensive anthropogenic activities along the coastal plains of Andhra Pradesh (such as urbanisation, agriculture and aquaculture) rely extensively on coastal fresh groundwater resources that are pumped at unsustainable rates causing groundwater decline and water quality problems due to saline water intrusion. Hydrogeological studies are imperative to implement groundwater conservation strategies in coastal Andhra Pradesh, which is experiencing a severe freshwater shortage due to overexploitation and saline water intrusion as well as clean water loss through the aquifer system close to the coastal plains. An attempt is made in this study to demarcate the submarine groundwater discharge (SGD) and saline water intrusion (SWI) zones adopting a three-tier validation system, i.e. groundwater dynamic, LANDSAT resultant sea surface temperature (SST) variance and site-specific water characteristics along the southeast coast of Andhra Pradesh, India. A total of 234 water samples (139 porewater, 31 groundwater and 64 seawater samples) were evaluated along ~ 450km southeast coastline of Andhra Pradesh. In situ porewater physio-chemical parameters, i.e. EC, TDS, pH, DO, temperature, and salinity, at every 1km except non-accessible areas and groundwater for every 5km were analysed and used for identification of SGD zones in the study area. The hydraulic gradient values vary from - 11 to 250m in post-monsoon and - 14 to 250m in pre-monsoon. And sea surface temperature anomaly for 2017, 2018 and 2019 varies between 21-39°C, 15-34°C and 20-39°C. Three districts out of the four districts studied (Krishna, Guntur and Nellore) were shown to be prone to SWI, whereas Prakasam district was susceptible for SGD. For the first time, this kind of preliminary study was carried out in the coastal Andhra Pradesh region, and it will serve as a basis for the meticulous analysis of the fresh and saline water mixing zones/process as well as to develop and manage the groundwater resources along the water-stressed coastal plains of Andhra Pradesh, India.

Impacts of different types of El Niño events on water quality over the Corn Belt, United States

Abstract. The United States Corn Belt region, which primarily includes two large basins, namely, the Ohio–Tennessee River basin (OTRB) and the Upper Mississippi River basin (UMRB), is responsible for the Gulf of Mexico hypoxic zone. Climate patterns such as El Niño can affect the runoff and thus the water quality over the Corn Belt. In this study, the impacts of eastern Pacific (EP) and central Pacific (CP) El Niño events on water quality over the Corn Belt region were analyzed using the Soil and Water Assessment Tool (SWAT) models. Our results indicated that, at the outlets, annual total nitrogen (TN) and total phosphorus (TP) loads decreased by 13.1 % and 14.0 % at OTRB and 18.5 % and 19.8 % at UMRB, respectively, during the EP El Niño years, whereas during the CP El Niño years, they increased by 3.3 % and 4.6 % at OTRB and 5.7 % and 4.4 % at UMRB, respectively. On the subbasin scales, more subbasins showed negative (positive) anomalies of TN and TP during EP (CP) El Niño. A seasonal study confirmed that water quality anomalies showed the opposite patterns during EP and CP El Niño years. At the outlet of OTRB, seasonal anomalies in nutrients matched the El Niño–Southern Oscillation (ENSO) phases, illustrating the importance of climate variables associated with the two types of El Niño events on water quality in the region. At the UMRB, TN and TP were also influenced by agricultural activities within the region, and their anomalies became greater in the growing seasons during both EP and CP El Niño years. A quantitative analysis of precipitation, temperature, and their effects on nutrients suggested that precipitation played a more important role than temperature did in altering the water quality in the Corn Belt region during both types of El Niño years. We also found specific watersheds (located in Iowa, Illinois, Minnesota, Wisconsin, and Indiana) that faced the greatest increases in TN and TP loads and were affected by both the precipitation and agricultural activities during the CP El Niño years. The information generated from this study may help proper decision-making for water environment protection over the Corn Belt.

Feature Extraction of Marine Water Pollution Based on Data Mining

The ocean occupies more than two-thirds of the earth’s area, providing a lot of oxygen and materials for human survival and development. However, with human activities, a large number of sewage, plastic bags, and other wastes are discharged into the ocean, and the problem of marine water pollution has become a hot topic in the world. In order to extract the characteristics of marine water pollution, this study proposed K-means clustering technology based on cosine distance and discrimination to study the polluted water. In this study, the polygonal area method combined with six parameters of water quality is used to analyze the marine water body anomalies, so as to realize the rapid and real-time monitoring of marine water body anomalies. At the same time, the cosine distance method and discrimination are used to classify marine water pollutants, so as to improve the classification accuracy. The results show that the detection rate of water quality anomalies is more than 88.2%, and the overall classification accuracy of water pollution is 96.3%, which proves the effectiveness of the method. It is hoped that this study can provide timely and effective data support for the detection of marine water bodies.

Water Quality Anomalies following the 2017 Hurricanes in Southwestern Puerto Rico: Absorption of Colored Detrital and Dissolved Material

Absorption of colored dissolved organic matter or detrital gelbstoff (aCDOM/ADG) and light attenuation coefficient (Kd490) parameters were studied at La Parguera Natural Reserve in southwestern Puerto Rico, before and following Hurricanes Irma (6–7 September) and María (20–21 September) in 2017. Water quality assessments involving Sentinel 3A ocean color products and field sample data was performed. The estimated mean of ADG in surface waters was calculated at >0.1 m−1 with a median of 0.05 m−1 and aCDOM443 ranged from 0.0023 to 0.1121 m−1 in field samples (n=21) in 2017. Mean ADG443 values increased from July to August at 0.167 to 0.353 m−1 in September–October over Turrumote reef (LP6) with a maximum value of 0.683 m−1. Values above 0.13 m−1 persisted at offshore waters off Guánica Bay and over coral reef areas at La Parguera for over four months. The ADG443 product presented values above the median and the second standard deviation of 0.0428 m−1 from September to October 2017 and from water sample measurement on 19 October 2017. Mean Kd490 values increased from 0.16 m−1 before hurricanes to 0.28 right after Hurricane Irma. The value remained high, at 0.34 m−1, until October 2017, a month after Hurricane María. Analysis of the Sentinel (S3) OLCI products showed a significant positive correlation (rs = 0.71, p = 0.0005) between Kd490_M07 and ADG_443, indicating the influence of ADG on light attenuation. These significant short-term changes could have ecological impacts on benthic habitats highly dependent on light penetration, such as coral reefs, in southwestern Puerto Rico.

An integrated data-driven framework for surface water quality anomaly detection and early warning

Abstract The surface water quality anomaly detection for rapid early warning is essential to prevent potential harmful compounds, resulting from river environmental spills or intentional releases, from dispersing in large scale. In this study, an effective data-driven framework for surface water quality anomaly detection is developed to provide early warnings for dealing with river environmental pollution in advance. The developed framework is constructed by an integration of Bayesian autoregressive (BAR) model for water quality variation prediction and Isolation Forest (IF) algorithm for water quality anomaly detection. First, an autoregressive method based on Bayesian inference is used to forecast the tendencies of water quality variations. Second, an IF algorithm is applied to identify the features of water quality anomalies using the prediction residuals obtained in the previous stage. The integration framework is then applied to analyze and detect the surface water quality variations and anomalies in Potomac River of West Virginia, USA, comparing with prediction-based anomaly detection method, classification-based anomaly detection method, and different scenarios. The results demonstrate that the developed integration framework not only could enhance water quality anomaly detection accuracy, but also effectively provide early warning for emergency operations in a quick response.

Vibrio Species in Wastewater Final Effluents and Receiving Watershed in South Africa: Implications for Public Health.

Wastewater treatment facilities in South Africa are obliged to make provision for wastewater effluent quality management, with the aim of securing the integrity of the surrounding watersheds and environments. The Department of Water Affairs has documented regulatory parameters that have, over the years, served as a guideline for quality monitoring/management purposes. However, these guidelines have not been regularly updated and this may have contributed to some of the water quality anomalies. Studies have shown that promoting the monitoring of the current routinely monitored parameters (both microbial and physicochemical) may not be sufficient. Organisms causing illnesses or even outbreaks, such as Vibrio pathogens with their characteristic environmental resilience, are not included in the guidelines. In South Africa, studies that have been conducted on the occurrence of Vibrio pathogens in domestic and wastewater effluent have made it apparent that these pathogens should also be monitored. The importance of effective wastewater management as one of the key aspects towards protecting surrounding environments and receiving watersheds, as well as protecting public health, is highlighted in this review. Emphasis on the significance of the Vibrio pathogen in wastewater is a particular focus.

Applying high-frequency surrogate measurements and a wavelet-ANN model to provide early warnings of rapid surface water quality anomalies

It is critical for surface water management systems to provide early warnings of abrupt, large variations in water quality, which likely indicate the occurrence of spill incidents. In this study, a combined approach integrating a wavelet artificial neural network (wavelet-ANN) model and high-frequency surrogate measurements is proposed as a method of water quality anomaly detection and warning provision. High-frequency time series of major water quality indexes (TN, TP, COD, etc.) were produced via a regression-based surrogate model. After wavelet decomposition and denoising, a low-frequency signal was imported into a back-propagation neural network for one-step prediction to identify the major features of water quality variations. The precisely trained site-specific wavelet-ANN outputs the time series of residual errors. A warning is triggered when the actual residual error exceeds a given threshold, i.e., baseline pattern, estimated based on long-term water quality variations. A case study based on the monitoring program applied to the Potomac River Basin in Virginia, USA, was conducted. The integrated approach successfully identified two anomaly events of TP variations at a 15-minute scale from high-frequency online sensors. A storm event and point source inputs likely accounted for these events. The results show that the wavelet-ANN model is slightly more accurate than the ANN for high-frequency surface water quality prediction, and it meets the requirements of anomaly detection. Analyses of the performance at different stations and over different periods illustrated the stability of the proposed method. By combining monitoring instruments and surrogate measures, the presented approach can support timely anomaly identification and be applied to urban aquatic environments for watershed management.

Model-Based Event Detection for Contaminant Warning Systems

AbstractSecurity issues have become increasingly important within distribution systems, which have led to the development of event detection algorithms (EDAs) to provide timely detection of intrusion events. The current study develops a localized model-based event detection algorithm that utilizes nonspecific water quality sensors to identify water quality anomalies. The proposed EDA focuses on evaluating a series of multivariate error signals between the observed signals and the model estimated signals based on a moving time-window of error statistics. The likelihood of the multivariate error signals is estimated using the product of univariate kernel density estimation (KDE), which is a type of nonparametric representation of the error distribution. A comprehensive analysis was performed using synthetic events to explore the combination of the moving window-pairs and bandwidth with respect to three injection strengths and two injection durations. In addition to the synthetic events, the EDA was also eva...

Distribution water quality anomaly detection from UV optical sensor monitoring data by integrating principal component analysis with chi-square distribution.

The issue of distribution water quality security ensuring is recently attracting global attention due to the potential threat from harmful contaminants. The real-time monitoring based on ultraviolet optical sensors is a promising technique. This method is of reagent-free, low maintenance cost, rapid analysis and wide cover range. However, the ultraviolet absorption spectra are of large size and easily interfered. While within the on-site application, there is almost no prior knowledge like spectral characteristics of potential contaminants before determined. Meanwhile, the concept of normal water quality is also varying due to the operating condition. In this paper, a procedure based on multivariate statistical analysis is proposed to detect distribution water quality anomaly based on ultraviolet optical sensors. Firstly, the principal component analysis is employed to capture the main variety features from the spectral matrix and reduce the dimensionality. A new statistical variable is then constructed and used for evaluating the local outlying degree according to the chi-square distribution in the principal component subspace. The possibility of anomaly of the latest observation is calculated by the accumulation of the outlying degrees from the adjacent previous observations. To develop a more reliable anomaly detection procedure, several key parameters are discussed. By utilizing the proposed methods, the distribution water quality anomalies and the optical abnormal changes can be detected. The contaminants intrusion experiment is conducted in a pilot-scale distribution system by injecting phenol solution. The effectiveness of the proposed procedure is finally testified using the experimental spectral data.

Water Quality Detection Using UV Spectra Based on the PCA Algorithm

Nowadays water pollution is a major problem facing our country, how to detect the water quality anomalies quickly is a major issue which needs to be solved urgently. In this paper, using PCA and cluster analysis methods, the similarities and differences of different water samples are analyzed. Meanwhile, two water samples belonging to the same river can be classified into different clusters due to different pollution degrees. It is promising that detecting the abnormal events based on the ultraviolet spectrum of water is possible. The research and results of this paper provide theoretical support and feasibility roadmap of the technology.

Linking distribution system water quality issues to possible causes via hydraulic pathways

Our limited understanding and quantification of the variety and complexity of chemical, physical and biological reactions and interactions occurring within drinking water distribution systems currently prohibit the development of a deterministic model of water quality. The causes of known water quality anomalies can however be investigated through mining the large volumes of water quality, hydraulic and asset data currently being collected by utility companies.The data-driven methodology described here permits historical cause–effect linkages to be identified in a scalable, largely automatable fashion. Under Distribution System Integrated Modelling (DSIM), spatio-temporal searches within the set of pipes that typically lie upstream of a known water quality anomaly are used to identify possible causes. Understanding of the flow paths that connect causes and effects are derived from the results of hydraulic network simulations.DSIM was used to investigate contacts regarding discolouration and smell/taste issues from customers within a Water Supply Zone in England, UK, over a six-year period. 17.6% of discolouration issues and 17.4% of smell/taste issues were linked to maintenance jobs using the methodology, much smaller proportions than were identified using radial cause searches. The DSIM search results contained a greater proportion of one-to-one linkages and so are less ambiguous than the results of the radial spatio-temporal searches. DSIM was found to be a useful and informative tool for data mining multiple water quality related datasets.

Ground Water Quality Anomalies Encountered During Well Construction, Sampling and Analysis in the Environs of a Hazardous Waste Management Facility

Ground Water Quality Anomalies Encountered During Well Construction, Sampling and Analysis in the Environs of a Hazardous Waste Management Facility