Experimental and neural network modeling of micellar enhanced ultrafiltration for arsenic removal from aqueous solution

Abstract

The optimization of micellar-enhanced ultrafiltration (MEUF) of arsenic (As) contaminated aqueous solution using cetylpyridinium chloride (CPC) as surfactant was studied through experimental and artificial neural network (ANN) modeling. Experimental studies were carried out by varying operational conditions such as time, pressure, molar ratio of CPC to As, concentration of As and pH of feed solution. Root mean square error (RMSE) and coefficient of determination (R<sup>2</sup>) were considered as performance criterion to evaluate the predicted results of ANN model. The experimental studies provided optimum operating parameters such as pressure 1.8 bar, molar ratio of CPC to As was 5:1, As concentration 1 mM and pH 8.0 of feed solution. ANN model presented reliable results with RMSE values 0.259, 0.553 and 0.623 for training, validation and testing datasets, respectively, while R<sup>2</sup> values for training, validation and testing dataset were noted as 0.962, 0.942 and 0.932, respectively. The proposed ANN model traced input-output relationship to predict As removal efficiency (RE) of MEUF process. Therefore, ANN model can be considered as a competitive, powerful and fast alternate because of its high computational speed, accuracy and economics in MEUF process optimization without doing laborious experimental work.

The Removal of As(III) Using a Natural Laterite Fixed-Bed Column Intercalated with Activated Carbon: Solving the Clogging Problem to Achieve Better Performance

“…where C 0 (mg/L) is the initial solute concentration, C t (mg/L) is the desired solute concentration at a defined breakthrough time, K B is the adsorption rate constant (L/(mg•h)) in hours, N 0 is the adsorption capacity (mg/L), Z is the column depth (cm), and t is the length of the operating time of the column (h). By fixing t = 0 and solving Equation ( 9), we obtain Equation (10) as follows:…”

“…Owing to its toxic effects and in the context of water shortages in developing countries, it is urgent to develop a simple and suitable methodology for the removal of arsenic from contaminated groundwaters. The most current approaches for arsenic removal include precipitation, coagulation by adding lime or coagulants to water, separation using membranes, an ion exchange process, adsorption, ultrafiltration, reverse osmosis, ozone oxidation, bioremediation, and electrochemical treatment [10][11][12][13][14][15][16][17]. Among all of these approaches, adsorption has been proven to be the most promising method because of its high efficiency, ease of handling, and the availability of several types of adsorbent materials.…”

Prediction of Groundwater Contamination in an Open Landfill Area Using a Novel Hybrid Clustering Based AI Model

“…Several studies have focused on developing predictive models that use a combination of statistical and machine learning techniques to identify the factors that contribute to groundwater contamination [1][2][3][4]. These models consider various parameters such as land use, hydrogeological characteristics, and environmental factors, to identify areas that are most vulnerable to contamination.…”

“…Groundwater samples were collected from various locations, including residential, industrial, and agricultural areas, and analyzed for various parameters, including heavy metals, pesticides, and organic compounds.Groundwater contamination prediction is a crucial component of groundwater management, as it helps to identify potential sources of contamination and take appropriate measures to prevent or mitigate the impacts of contamination. In recent years, there has been signi cant research in the eld of groundwater contamination prediction, aimed at developing reliable models and tools for assessing the vulnerability and risk of groundwater contamination.Several studies have focused on developing predictive models that use a combination of statistical and machine learning techniques to identify the factors that contribute to groundwater contamination [1][2][3][4]. These models consider various parameters such as land use, hydrogeological characteristics, and environmental factors, to identify areas that are most vulnerable to contamination.…”

A Combined CFD-Response Surface Methodology Approach for Simulation and Optimization of Arsenic Removal in a Fixed Bed Adsorption Column

“…RSM has been extensively used in a huge number of studies as an outstanding statistical tool for optimization [22][23][24]. It has been employed effectively for optimizing the performance of arsenic removal from aqueous solutions [25][26][27][28].…”