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

Shi, Bin; Wang, Peng; Jiang, Jiping; Liu, Rentao

doi:10.1016/j.scitotenv.2017.08.232

Cited by 85 publications

(35 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In 2005, the United States Environmental Protection Agency (USEPA) introduced a framework for integrating early warning systems into water distribution systems to monitor, analyze, interpret and communicate data, which can protect public health [ 1 ]. Subsequently, numerous studies has been performed on water quality early warning technologies all over the world, including water quality sensor technologies, event detection algorithms, hydrological models, and decision-making systems (DSS) [ 2 , 3 ]. Establishing an early warning system has been recognized as an effective means of: (1) avoiding or reducing the impact of water contamination events; and (2) protecting water sources and ensuring the safety of drinking water [ 4 ].…”

Section: Introductionmentioning

confidence: 99%

Application of Least-Squares Support Vector Machines for Quantitative Evaluation of Known Contaminant in Water Distribution System Using Online Water Quality Parameters

Wang

Wen

Hou

et al. 2018

Sensors

View full text Add to dashboard Cite

In water-quality, early warning systems and qualitative detection of contaminants are always challenging. There are a number of parameters that need to be measured which are not entirely linearly related to pollutant concentrations. Besides the complex correlations between variable water parameters that need to be analyzed also impairs the accuracy of quantitative detection. In aspects of these problems, the application of least-squares support vector machines (LS-SVM) is used to evaluate the water contamination and various conventional water quality sensors quantitatively. The various contaminations may cause different correlative responses of sensors, and also the degree of response is related to the concentration of the injected contaminant. Therefore to enhance the reliability and accuracy of water contamination detection a new method is proposed. In this method, a new relative response parameter is introduced to calculate the differences between water quality parameters and their baselines. A variety of regression models has been examined, as result of its high performance, the regression model based on genetic algorithm (GA) is combined with LS-SVM. In this paper, the practical application of the proposed method is considered, controlled experiments are designed, and data is collected from the experimental setup. The measured data is applied to analyze the water contamination concentration. The evaluation of results validated that the LS-SVM model can adapt to the local nonlinear variations between water quality parameters and contamination concentration with the excellent generalization ability and accuracy. The validity of the proposed approach in concentration evaluation for potassium ferricyanide is proven to be more than 0.5 mg/L in water distribution systems.

show abstract

Section: Introductionmentioning

confidence: 99%

Application of Least-Squares Support Vector Machines for Quantitative Evaluation of Known Contaminant in Water Distribution System Using Online Water Quality Parameters

Wang

Wen

Hou

et al. 2018

Sensors

View full text Add to dashboard Cite

show abstract

“…Evaluation theory and evaluation methods have enjoyed great developments in the recent years. For instance, the index evaluation method [33], fuzzy evaluation method [34], Grey theory evaluation method [35], and neural network evaluation method have been put forth by different researchers [36].…”

Section: Related Workmentioning

confidence: 99%

Integration Multi-Model to Evaluate the Impact of Surface Water Quality on City Sustainability: A Case from Maanshan City in China

2019

View full text Add to dashboard Cite

Water pollution is a worldwide problem that needs to be solved urgently and has a significant impact on the efficiency of sustainable cities. The evaluation of water pollution is a Multiple Criteria Decision-Making (MCDM) problem and using a MCDM model can help control water pollution and protect human health. However, different evaluation methods may obtain different results. How to effectively coordinate them to obtain a consensus result is the main aim of this work. The purpose of this article is to develop an ensemble learning evaluation method based on the concept of water quality to help policy-makers better evaluate surface water quality. A valid application is conducted to illustrate the use of the model for the surface water quality evaluation problem, thus demonstrating the effectiveness and feasibility of the proposed model.

show abstract

“…In recent years, in order to further reduce water quality monitoring cost, indirect methods of concentration prediction of BOD, COD, TDS, NH3-N and TP in influent and effluent are increasingly investigated on the basis of various machine learning algorithms, such as k-nearest neighbours (KNN), artificial neural networks (ANN), self-organising map (SOM) and support vector machine (SVM) (Harrou et al 2018;Lotfi et al 2019;Shi et al 2018;Zhang et al 2008). In the aforementioned water quality monitoring strategies, difficult or expensive target water quality indices are replaced with low-cost ones as prediction model inputs (e.g.…”

Section: Introductionmentioning

confidence: 99%

Effect of Dilution on the Pollutant Monitoring in Decentralised Treatment Facilities Using Electrical Conductivity Sensors: Experimental and Modelling Insights

Qian

Liu

Liang

et al. 2021

Preprint

View full text Add to dashboard Cite

Electrical conductivity (EC) is a common and cheap water monitoring sensor, and in some way reflects the water body pollution level qualitatively. In this study, the domestic sewage characteristic analysis for decentralised treatment facilities in plain and mountainous rural areas, Eastern China, showed that influent TN/NH3-N/TP concentrations were strongly and linearly correlated with influent EC values. EC source apportionment indicated that although no single ion in rural domestic sewage dominated the EC value, EC was packed with vast amounts of information on pollutant content and colud be precisely predicted by support vector machine (SVM) regression model (R = 0.9520). According to field investigation and dilution simulation analysis, the mechanism of correlations between influent TN/NH3-N/TP concentrations and EC values was confirmed and attributed to dilutions by background water during pipeline transport. Particularly, although the dilution processes in plain and mountainous areas were similar and the dilution coefficients were speculated to both obey a Poisson distribution, the average dilution coefficient in plain area was 0.35 ± 0.16 with λ=4 while that in mountainous area was 0.23± 0.15 with λ=2. Our results demonstrate that the EC sensor provides a cheap, rapid and reliable alternative pollutant monitoring method for decentralised treatment facilities in rural areas with mechanism clear.

show abstract

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

Cited by 85 publications

References 34 publications

Application of Least-Squares Support Vector Machines for Quantitative Evaluation of Known Contaminant in Water Distribution System Using Online Water Quality Parameters

Application of Least-Squares Support Vector Machines for Quantitative Evaluation of Known Contaminant in Water Distribution System Using Online Water Quality Parameters

Integration Multi-Model to Evaluate the Impact of Surface Water Quality on City Sustainability: A Case from Maanshan City in China

Effect of Dilution on the Pollutant Monitoring in Decentralised Treatment Facilities Using Electrical Conductivity Sensors: Experimental and Modelling Insights

Contact Info

Product

Resources

About