Simulation, evaluation and prediction modeling of river water quality properties (case study: Ireland Rivers)

Salami, E. S.; Ehteshami, Majid

doi:10.1007/s13762-015-0800-7

Cited by 34 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the number of times the observations are greater than the mean error as discussed by Ritter and uñoz-Carpena (2013), models 1, 2, 3 and 4 can be classified as good. The evaluation statistics indicated in Table 4 concurs with those found by Salami and Ehteshami (2015) where R 2 of 0.82, 0.85 and 0.92 for chloride, alkalinity and hardness respectively were obtained for prediction of dissolved oxygen. However, the RMSE values in Table 4 are slightly higher than those found by Zhang et al (2010) temperature, BOD and ammonium had higher correlations with DO.…”

Section: Resultssupporting

confidence: 85%

Dissolved oxygen modelling using artificial neural network: a case of River Nzoia, Lake Victoria basin, Kenya

Kanda

Kipkorir

Kosgei

2016

Journal of Water Security

View full text Add to dashboard Cite

River Nzoia in Kenya, due to its role in transporting industrial and municipal wastes in addition to agricultural runoff to Lake Victoria, is vulnerable to pollution. Dissolved oxygen is one of the most important indicators of water pollution. Artificial neural network (ANN) has gained popularity in water quality forecasting. This study aimed at assessing the ability of ANN to predict dissolved oxygen using four input variables of temperature, turbidity, pH and electrical conductivity. Multilayer perceptron network architecture was used in this study. The data consisted of 113 monthly values for the input variables and output variable from 2009-2013 which were split into training and testing datasets. The results obtained during training and testing were satisfactory with R 2 varying from 0.79 to 0.94 and RMSE values ranging from 0.34 to 0.64 mg/l which imply that ANN can be used as a monitoring tool in the prediction of dissolved oxygen for River Nzoia considering the non-correlational relationship of the input and output variables. The dissolved oxygen values follow seasonal trend with low values during dry periods.

show abstract

Section: Resultssupporting

confidence: 85%

Dissolved oxygen modelling using artificial neural network: a case of River Nzoia, Lake Victoria basin, Kenya

Kanda

Kipkorir

Kosgei

2016

Journal of Water Security

View full text Add to dashboard Cite

show abstract

“…They applied a self-organizing map (SOM), a stratified method, to construct a topological map to visualize the clustered input variables, thereby ensuring that the statistical properties of the subsets were similar. Levenberg-Marquardt algorithm [24,[136][137][138][139] and Bayesian methods were conducted to train the network. Results showed that ANN models could achieve high accuracy.…”

Section: Artificial Neural Network Models For Water Quality Predictionmentioning

confidence: 99%

A Review of the Artificial Neural Network Models for Water Quality Prediction

et al. 2020

View full text Add to dashboard Cite

Water quality prediction plays an important role in environmental monitoring, ecosystem sustainability, and aquaculture. Traditional prediction methods cannot capture the nonlinear and non-stationarity of water quality well. In recent years, the rapid development of artificial neural networks (ANNs) has made them a hotspot in water quality prediction. We have conducted extensive investigation and analysis on ANN-based water quality prediction from three aspects, namely feedforward, recurrent, and hybrid architectures. Based on 151 papers published from 2008 to 2019, 23 types of water quality variables were highlighted. The variables were primarily collected by the sensor, followed by specialist experimental equipment, such as a UV-visible photometer, as there is no mature sensor for measurement at present. Five different output strategies, namely Univariate-Input-Itself-Output, Univariate-Input-Other-Output, Multivariate-Input-Other(multi), Multivariate-Input-Itself-Other-Output, and Multivariate-Input-Itself-Other (multi)-Output, are summarized. From results of the review, it can be concluded that the ANN models are capable of dealing with different modeling problems in rivers, lakes, reservoirs, wastewater treatment plants (WWTPs), groundwater, ponds, and streams. The results of many of the review articles are useful to researchers in prediction and similar fields. Several new architectures presented in the study, such as recurrent and hybrid structures, are able to improve the modeling quality of future development.

show abstract

“…Automated detection of pipe bursts approach came to the limelight, using different Artificial Intelligence (AI) tools to predict the leakage prior to its taking place with some variables like pressure and flow signal value [45]. AI has shown significance capability to deal with missing data, decreases the cost of testing [46][47][48], can easily classify the point source of the leakage [49], and predict the life of the distribution system components [50]. These advantages make the potential of AI models useful in developing countries where there are lacks of uniform and regular data, funding for data collection and testing, advanced sensors to pinpoint the leakage sources, and lack of regular maintenance system.…”

Section: Recommendationsmentioning

confidence: 99%

Evaluating Physical and Fiscal Water Leakage in Water Distribution System

Bhagat

Tiyasha

Welde

et al. 2019

Water

View full text Add to dashboard Cite

With increasing population, the need for research ideas on the field of reducing wastage of water can save a big amount of water, money, time, and energy. Water leakage (WL) is an essential problem in the field of water supply field. This research is focused on real water loss in the water distribution system located in Ethiopia. Top-down and bursts and background estimates (BABE) methodology is performed to assess the data and the calibration process of the WL variables. The top-down method assists to quantify the water loss by the record and observation throughout the distribution network. In addition, the BABE approach gives a specific water leakage and burst information. The geometrical mean method is used to forecast the population up to 2023 along with their fiscal value by the uniform tariff method. With respect to the revenue lost, 42575 Br and 42664 Br or in 1562$ and 1566$ were lost in 2017 and 2018, respectively. The next five-year population was forecasted to estimate the possible amount of water to be saved, which was about 549627 m3 and revenue 65,111$ to make the system more efficient. The results suggested that the majority of losses were due to several components of the distribution system including pipe-joint failure, relatively older age pipes, poor repairing and maintenance of water taps, pipe joints and shower taps, negligence of the consumer and unreliable water supply. As per the research findings, recommendations were proposed on minimizing water leakage.

show abstract

Simulation, evaluation and prediction modeling of river water quality properties (case study: Ireland Rivers)

Cited by 34 publications

References 19 publications

Dissolved oxygen modelling using artificial neural network: a case of River Nzoia, Lake Victoria basin, Kenya

Dissolved oxygen modelling using artificial neural network: a case of River Nzoia, Lake Victoria basin, Kenya

A Review of the Artificial Neural Network Models for Water Quality Prediction

Evaluating Physical and Fiscal Water Leakage in Water Distribution System

Contact Info

Product

Resources

About