Feasibility Assessment of Data-Driven Models in Predicting Pollution Trends of Omerli Lake, Turkey (original) (raw)
Related papers
Surface Water Quality Modeling by Regression Analysis and Artificial Neural Network
Advances in Waste Management, 2018
The major objective of the present study is to develop water quality prediction models after evaluation of water quality to predict water pollution of two lakes situated inside Tezpur University. The water quality parameters were analyzed using linear regression analysis and artificial neural network to predict the water quality. Correlation studies suggested a highly positive correlation between TS with turbidity and EC for both lakes. Modeling of TS and BOD by regression analysis suggests a good correlation between actual and predicted TS but a very poor correlation between actual and predicted BOD. Modeling of TS and BOD by ANN shows a very good correlation between the actual and predicted values for both TS and BOD for both the lakes studied. The error between the experimental and estimated ANN model is less than regression model, suggesting suitability of ANN model for prediction of studied parameters.
Environmental Science and Pollution Research, 2013
The aims of this study are to create an artificial neural network (ANN) model using non-specific water quality parameters and to examine the accuracy of three different ANN architectures: General Regression Neural Network (GRNN), Backpropagation Neural Network (BPNN) and Recurrent Neural Network (RNN), for prediction of dissolved oxygen (DO) concentration in the Danube River. The neural network model has been developed using measured data collected from the Bezdan monitoring station on the Danube River. The input variables used for the ANN model are water flow, temperature, pH and electrical conductivity. The model was trained and validated using available data from 2004 to 2008 and tested using the data from 2009. The order of performance for the created architectures based on their comparison with the test data is RNN > GRNN > BPNN. The ANN results are compared with multiple linear regression (MLR) model using multiple statistical indicators. The comparison of the RNN model with the MLR model indicates that the RNN model performs much better, since all predictions of the RNN model for the test data were within the error of less than ±10 %. In case of the MLR, only 55 % of predictions were within the error of less than ±10 %. The developed RNN model can be used as a tool for the prediction of DO in river waters. Keywords Modelling of dissolved oxygen. Modelling of water quality. Artificial neural network. Multiple linear regression Water quality modelling is increasingly recognised as a useful tool for acquiring valuable information for optimal water quality management (Vieira et al. 2013). Since a large number of factors, such as temperature, water discharge, sedimentation, reaeration, decomposition, nitrification and photosynthesis, affect the DO in water, a non-linear relationship between input variables and the DO can be expected. Artificial neural networks (ANNs) are flexible mathematical structures that are capable of identifying complex nonlinear relationships or patterns between input and output data sets and capable of estimating output values based on training
Ain Shams Engineering Journal, 2016
Manzala Lake, the largest of the Egyptian lakes, is affected qualitatively and quantitatively by drainage water that flows into the lake. This study investigated the capabilities of adaptive neuro-fuzzy inference system (ANFIS) to predict water quality parameters of drains associated with Manzala Lake, with emphasis on total phosphorus and total nitrogen. A combination of data sets was considered as input data for ANFIS models, including discharge, pH, total suspended solids, electrical conductivity, total dissolved solids, water temperature, dissolved oxygen and turbidity. The models were calibrated and validated against the measured data for the period from year 2001 to 2010. The performance of the models was measured using various prediction skill criteria. Results show that ANFIS models are capable of simulating the water quality parameters and provided reliable prediction of total phosphorus and total nitrogen, thus suggesting the suitability of the proposed model as a tool for onsite water quality evaluation.
A Case Study of Using Artificial Neural Networks to Predict Heavy Metal Pollution in Lake Iznik
Since high levels of heavy metals cause serious complications for water resources, plants, animals and human health, determining their presence and concentration is very important for the sustainability of the ecosystem. In recent years, rapid advances in the field of artificial neural networks (ANNs) brought them the forefront in water quality prediction. In this paper, various experiments were conducted with a model for predicting the presence of heavy metals using IBM SPSS statistics 23 software. In order to assess the water quality of Lake Iznik –an important source of water– in terms of heavy metals, water quality parameters of samples taken in the period 2015–2021 from five different water sources flowing into the lake were analyzed. A number of psychochemical were measured in samples taken from Karasu, Kırandere, Olukdere, and Sölöz streams flowing into the lake, and were used as input data for modeling, while fifteen heavy metal concentrations in Karsak stream flowing out of...
Applied Ecology and Environmental Research, 2018
The aim of this study was to develop faecal pollution model structures with artificial neural networks (ANNs) for cost-effective lake water quality management studies. In this study 5 artificial neural networks model structures were applied to predict the Faecal coliform concentrations for 4 different coast areas "Göllüce, İnciraltı, Darka, Orhangazi" and all data of the coasts in Lake İznik-Turkey. The Levenberg-Marquardt and backpropagation algorithm was proposed for feed-forward neural networks training. According to performance functions root mean squared error (RMSE), neural network model structures provided acceptable results. Correlation values (R) were found between 0.590 and 0.999. Increasing the number of hidden layer in the model structures was not raised the model efficiency in each trial. Type and number of input parameters were more effective for some model efficiency. Increasing the number of hidden layer and inputs in the model structures did not raise the model efficiency in each trial. Because depending on the numbers and chemical compositions of the substrates in the lake water microorganism's metabolism and their growth rates could be influenced differently and the larger error values of the modeling results determined in Göllüce and Orhangazi Coasts which influenced by pollution sources. Water quality modeling studies and increasing of monitoring would provide more productive results for protection and management of coastal.
Abstract- This is attributable to pollution due to human activities such as plunging of idols of deity and divinity in the festival season, surface runoff due to heavy rainfall, washing exercises and sewage disposal everywhere in lakes. Water environment is a complex system where theological methods cannot meet the demands of water environment preservation. To demonstrate the usefulness of the Back Propagation Neural Network (BPNN), the Water Quality Index (WQI) has been used on the basis of physico-chemical parameters of different sources of water. Water from different sources like Gandhisagar, Ambazari and Futala Lake revealed significant water pollution as compared to Gorewada Lake for Nagpur city with hot and dry climate, in Maharashtra, center of India. Water quality assessment on the basis of physico-chemical analysis such as pH, Electrical Conductivity (EC), Turbidity (Turb) ,Total Dissolved Solids ( TDS), Total Hardness (TH), Calcium (Ca2+), Magnesium (Mg2+), Chloride (Cl-), Sulphate (SO4) ,Total Alkalinity (TA) and Dissolved Oxygen (DO) etc., have been investigated in the present work .Regression model has been developed to relate between variables which shows that one variable actually causes changes in another variable. Two methods, namely, Correlation Coefficient (CC) and Artificial Neural Network (ANN) were used to predict the responses of results proved to be a useful mean for rapid monitoring of water quality and with the help of systematic calculations of correlation coefficient between water parameters. In this study, an attempt was made to assess WQI using Multi-Layer Perceptrons (MLP) architecture. Keywords: Physico-Chemical Properties, Water Quality Index, Regression Coefficient, ANN
The Journal of The University of Duhok
The purpose of this study is to develop a feed-forward neural network (FFNN) model with back-propagation learning algorithm to predict the dissolved oxygen from water temperature and 5 days-biological oxygen demand in the Tigris River, Baghdad-Iraq. The Artificial Neural Networks model was implemented utilizing measured data that were gathered from laboratories of water treatment plant, Baghdad-Iraq, during the year 2008. The correlation analysis between dissolved oxygen and dependent parameters were utilized in selecting the major inputs from water quality parameters for commencing of ANN models. The performance of ANN models were tested utilizing the coefficient of correlation (R), the efficiency coefficient of Nash-Sutcliffe (NS), mean square error (MSE) and mean absolute errors (MAE). The outputs revealed that the feed-forward neural networks using back-propagation learning algorithm which was prepared by temperature and biological oxygen demand offered a relatively high correlation coefficient of 0.885, and efficiency coefficient of 0.782, meanwhile a reasonably low mean square errors of 1.133, and mean absolute errors of 0.369 values for whole array period. The results of the present study demonstrate that the artificial neural networks using FFNN model is capable to forecast the dissolved oxygen values with acceptable accuracy. This is suggesting that the artificial neural network is a useful tool for Tigris River management in Baghdad-Iraq.
Forecasting of dissolved oxygen in the river danube using neural networks
Hungarian Agricultural Engineering, 2015
The Danube is the second-largest river in Europe and the conservation of its water quality is very important because it influences the lives of millions people. The aim of this research is to predict one of the most important water quality parameters, dissolved oxygen, with the help of water pH, runoff, water temperature and electrical conductivity data. Multivariate Linear Regression (MLR), Back-propagation Neural Networks (BPNN) and General Regression Neural Networks (GRNN) were applied and their performances compared in this study. The most accurate prediction proved to be GRNN. This paper describes the influence of single input parameters on the prediction.
Dissolved oxygen (DO) concentrations have been used as primary indicator of stream water quality. A problem of great social importance is determining how to best retain the quality of stream water and maintain DO concentrations using various pollution control activities. This paper presents the use of artificial neural network (ANN) technique to estimate the DO concentrations at the downstream of Mathura city, India, located at the bank of River Yamuna in the state of Uttar Pradesh, India. In the analysis, the most commonly used feed forward error back propagation neural network technique has been applied. Monthly data sets on flow discharge, temperature, pH, biochemical oxygen demand (BOD) and dissolved oxygen (DO) at three locations, namely, Mathura (upstream), Mathura (central) and Mathura (downstream) have been used for the analysis. Feed forward error back propagation algorithm, the most commonly used ANN technique, was used to develop three types of ANN models using different combinations of input variables and input stations, namely: (a) All the data sets for stations Mathura (upstream), Mathura (central) and Mathura (downstream) except DO values at Mathura (downstream) (b) All data sets for the stations Mathura (upstream), and Mathura (central), and (c) All the data sets for the stations Mathura (upstream). The performance of the ANN technique has been evaluated using statistical tools (in terms of root mean square error and coefficient of correlation). The predicted values of DO showed prominent accuracy by producing high correlations (upto 0.9) between measured and predicted values.