Prediction of phycoremediation of As(III) and As(V) from synthetic wastewater by Chlorella pyrenoidosa using artificial neural network

Abstract

An artificial neural network (ANN) model was developed to predict the phycoremediation efficiency of Chlorella pyrenoidosa for the removal of both As(III) and As(V) from synthetic wastewater based on 49 data-sets obtained from experimental study and increased the data using CSCF technique. The data were divided into training (60%) validation (20%) and testing (20%) sets. The data collected was used for training a three-layer feed-forward back propagation (BP) learning algorithm having 4-5-1 architecture. The model used tangent sigmoid transfer function at input to hidden layer (tansing) while a linear transfer function (purelin) was used at output layer. Comparison between experimental results and model results gave a high correlation coefficient (R allANN 2 equal to 0.99987 for both ions and exhibited that the model was able to predict the phycoremediation of As(III) and As(V) from wastewater. Experimental parameters influencing phycoremediation process like pH, inoculum size, contact time and initial arsenic concentration [either As(III) or As(V)] were investigated. A contact time of 168 h was mainly required for achieving equilibrium at pH 9.0 with an inoculum size of 10% (v/v). At optimum conditions, metal ion uptake enhanced with increasing initial metal ion concentration.

Prediction of arsenic removal in aqueous solutions with non‐neural network algorithms

“…The ranges of different statistical parameters for previous ANN algorithm-and analytical isotherm-based models are 99.994 > R 2 > 80.5, 4.289 > RMSE >0.25, and 14.166 > MAE > 0.001. [11,15,16,18,21,25,29,[43][44][45]47,48] The comparative results for the current models are 99.3 > R 2 > 82.0, 5.1 > RMSE >1.3, and 2.8 > MAE > 0.3 (Table 3), that is, the non-NN models presented here are competent of predicting the capability of an adsorbent to adsorb As, with reasonable accuracy. Furthermore, both SVR and RF models have the advantage of requiring comparatively less preprocessing accompanied by a simpler training process that involves optimizing a fixed number of parameters.…”

“…Seven experimental data sets were selected from the literature. [29,[43][44][45][46][47][48] A wide variety of adsorbents/biosorbents were used for measuring the adsorption efficiency of As in various aqueous solutions in these studies. The adsorption or biosorption experimentation was followed by constructing a computational or statistical model for As removal based on several input parameters, such as initial As concentration, bio-sorbent or adsorbent dose, pH, contact time, agitation speed, and temperature.…”

Prediction of Arsenic Removal from Contaminated Water Using Artificial Neural Network Model

“…Seven experimental datasets were selected from the literature [15][16][17][18][30][31][32] for the current study. These studies were considered suitable, as a variety of absorbents or biosorbents were used to remove As(III) from contaminated aqueous solutions or ground/wastewater.…”

“…The mostly used ML algorithm for modeling various adsorption processes is the artificial neural network (ANN) [28,29]. It has been used all across the world for classification and prediction purposes in a wide range of real-time adsorption applications [14][15][16][17][18][22][23][24][25][26][27]. The ANN correlates the input(s) to the output(s) with nodes arranged in single or multiple hidden layers.…”

Phycoremediation mechanisms of heavy metals using living green microalgae: physicochemical and molecular approaches for enhancing selectivity and removal capacity

“…These negatively charged groups permit the binding of ions from the surrounding environment, making the outer layer of the cell wall as the first participator in the removal of HMs ( Leong and Chang, 2020 ; Saavedra et al., 2018 ; Singh et al., 2021 ). Therefore, understanding the structure, composition, and properties of the cell wall is essential when studying biosorption mechanisms ( Podder and Majumder, 2017 ). In addition, this non-metabolic mechanism depends closely on the operating conditions, the influence of the physicochemical conditions including pH, temperature, presence of other ions and the ratio of adsorbate adsorbent must be controlled ( Zeraatkar et al., 2016 ).…”