Predicting turbidity and Aluminum in drinking water treatment plants using Hybrid Network (GA- ANN) and GEP

Abstract

Abstract. Turbidity is the most important parameter needed to check the status of drinking water, as it is an integrated parameter because its high values indicate high values of other parameters related to water quality. Coagulation and flocculation are the most essential processes for the removal of turbidity in drinking water treatment plants. Using alum coagulants increases the aluminum residuals in treated water, which have been linked to Alzheimer's disease pathogenesis.In this paper, a hybrid algorithm (GA-ANN) used to predict the turbidity values in the drinking water purification plant in Al Qusayr was used.The models were constructed using raw water data: turbidity of raw water, pH, conductivity, temperature, and coagulant dose, to predict the turbidity values coming out of the plant.Several models built and fitness detected for each model, the network with the highest fitness was selected, and then a hybrid prediction network was constructed.The selected network was the most able to predict turbidity of the outlet with high accuracy with a correlation coefficient (0. 9940) and a root mean square error of 0.1078.And 4 equations for determining the value of the residual aluminum was obtained using Gene expression method, and the best equation produced results with very good accuracy, in this regard it can be referred to RMSE = 0.02 R = 0.9 for the best model.

Prediction models for manganese, iron and ammonium in raw water for a drinking water treatment plant Butoniga (croatia)

“…Ayanshola et al [8] utilized MLR and ANN models to predict treated water turbidity in a water treatment plant, achieving reasonable prediction accuracy with both methods. Alsaeed et al [9] developed prediction models for turbidity and aluminium in drinking water treatment plants using GA-ANN and GEP which can be used as early warning systems to provide information about water treatment plants. Godo-Pla et al [1] employed ANN to predict the oxidant demand in a full-scale drinking water treatment plant.…”

“…In research made by Kim and Parnichkun [7] prediction of settled water turbidity and optimal coagulant dosage in drinking water treatment plant was done using a hybrid model of kmeans clustering and adaptive neuro-fuzzy inference system. Use of multiple linear regression (MLR) and artificial neural network (ANN) models were used by Ayanshola et al [8] to predict treated water turbidity in a water treatment plant, while Alsaeed et al [9] have done prediction of turbidity and aluminium in drinking water treatment plants using hybrid network algorithm (GA-ANN) and gene expression method (GEP). ANN were used also by Godo-Pla et al [1] for predicting the oxidant demand in full-scale drinking water treatment plant.…”

Data-driven modeling techniques for prediction of settled water turbidity in drinking water treatment

“…ANN and other nonlinear model configurations have shown promise in several applications throughout the water treatment industry. Researchers have developed ANN models for cost optimization (Taloba, 2022), prediction of coagulant dose (Valentin and Denceux, 1999;Deveughèle and Do-Quang, 2004;Tahraoui et al, 2021;Lin et al, 2023), potassium permanganate dose requirements (Godo-Pla et al, 2019), source water quality (Hameed et al, 2023), sodium absorption in groundwater (Hasanpour Kashani et al, 2023), regional water demand (Zhang et al, 2019, and settled water turbidity (Wu and Lo, 2008;Al-baidhani and Alameedee, 2017;Kim and Parnichkun, 2017;Haghiri et al, 2018;Abba et al, 2020;Alsaeed et al, 2021;Ghasemi et al, 2022;Lin et al, 2023). Although several modeling techniques have been developed recently to predict coagulant dose based on source water quality, most of the work reported in literature either used bench-scale data (Haghiri et al, 2018) or lacked a sufficiently large data set (Albaidhani and Alameedee, 2017;Abba et al, 2020).…”

Prediction of Optimum Dosage of Coagulant in Water Treatment Plant: A Comparative Study between Artificial Neural Network and Random Forest

“…The ANN models were trained using the Levenberg-Marquardt algorithm, the research findings suggest that ANN's can accurately predict the optimal coagulant dosage, offering a promising approach to optimizing water treatment processes [1]. Prediction of turbidity and aluminium in drinking water treatment plants using Hybrid Network (GA-ANN) and GEP was done by Alsaeed et al (2021). The authors developed a hybrid network model combining genetic algorithms (GA) and artificial neural network (ANN) to predict turbidity and aluminium concentration in drinking water treatment plants.…”

“…The study utilized input variables such as raw water quality parameters, coagulant type and dosage, and treatment process variables to develop the hybrid GA-ANN model. The results showed that the hybrid model was effective in predicting turbidity and aluminium concentration, and the study suggested that the model could be used as a tool to optimize coagulant dosage and improve water treatment performance [2]. Kote et al (2019) have done modelling of chlorine and coagulant dose in a water treatment plant by artificial neural network.…”