Artificial neural network approach for lead removal from aqueous solution by agricultural waste derived biochars
Artificial neural network approach for lead removal from aqueous solution by agricultural waste derived biochars
Lead (Pb2+) which is one of the most important heavy metals found in water sources, has a toxic effect on living things in aquatic environment. Therefore, the removal of Pb2+ ions from wastewater is very important if its concentration is above the determined discharge limits. Due to its advantage such as high efficiency, the adsorption process is a widely used successful technique for heavy metals removal from an aqueous solutions. On the other hand, determining the adsorption efficiencies of different adsorbents experimentally is both costly, and time-consuming considering that there are large number of process variables. Therefore, ANN can be used to make theoretical predictions with high efficiency in this treatment process. In this study, modeling of Pb2+ removal from an aqueous solution by using biochars that produced by pyrolyzing of hazelnut, and walnut shell was studied at different adsorption conditions; pH (2.5-5), temperature (25-45oC), initial Pb2+ concentration (15-45 mg/L), adsorbent amount (1-3 g/L), and mixing speed (200-600 rpm). The purpose of modeling studies with ANN approach was to estimate lead ions removal (%) as an output. Inputs for ANN modeling approach were selected as pH, initial Pb2+ concentration, temperature, adsorbent dosage, and mixing speed. Experimental data were categorized 50:25:25 for two adsorption systems. Levenberg-Marquardt (LM) was preferred as a training function, and tansig was used as an activation function. The number of hidden neurons in the hidden layer was found by trial, and error. Values of correlation coefficient (R2), and Mean Square Error (MSE) were taken to be performance criteria of the ANN modeling. R2 values were found to be 97%, and 98% for biochars derived from walnut, and hazelnut shells, respectively. Results showed that ANN is an effective tool for modeling of adsorption system for the removal of lead ions from an aqueous solution. Additionally, different training algorithms such as Bayesian Regularization (BR), and Scaled Conjugate Gradient (SCG) were used to compare the prediction capability.
___
- [1] Arbabi M, Hemati S, Amiri M. Removal of lead ions from industrial wastewater: A review of Removal methods. Int J Epidemiol Res 2015;2:105–109.
- [2] Flora G, Gupta D, Tiwari A. Toxicity of lead: A review with recent updates. Interdiscip Toxicol 2012;5:47–
58. [CrossRef]
- [3] Vidu R, Matei E, Predescu AM, Alhalaili B, Pantilimon C, Tarcea C, et al. Removal of heavy metals from wastewaters: A challenge from cur-rent treatment methods to nanotechnology applica-tions. Toxics 2020;8: 101. [CrossRef]
- [4] Gunatilake SK. Methods of removing heavy metals from industrial wastewater. J Multidiscip Eng Sci Studi 2015;1:12–18.
- [5] Burakov AE, Galunin EV, Burakova IV, Kucherova AE, Agarwal S, Tkachev AG, et al. Adsorption of heavy metals on conventional and nanostructured materials for wastewater treatment purposes: A review. Ecotoxicol Environ Saf 2018;148:702–712.[CrossRef]
- [6] Ahmad S, Ali A, Ashfaq A. Heavy metal pollu-tion, sources, toxic effects and techniques adopted for control. Int J Curr Res Aca Rev 2016;4:39–58.[CrossRef]
- [7] Akgul G. Biochar: Production and applications. Selcuk Univ J Eng Sci Tech 2017;5:485–499. [CrossRef]
- [8] Crini G, Lichtfouse E, Wilson LD, Morin-Crini N. Adsorption-oriented processes using conventional and non-conventional adsorbents for wastewater treatment. In: Crini G, Lichtfouse E, editors. Green adsorbents for pollutant removal. 1st ed. Berlin: Springer; 2018. pp. 23–71. [CrossRef]
- [9] Mete T, Ozkan G, Hapoglu H, Alpbaz M. Control of dissolved oxygen concentration using neural net-work in a batch bioreactor. Comput Appl Eng Educ 2012;20:619–628. [CrossRef]
- [10] Ozkan G, Ucan L, Ozkan G. The prediction of SO2 removal using statistical methods and artificial neu-ral network. Neural Comput Appl
2010;19:67–75.[CrossRef]
- [11] Ozkan G, Akin BA. The prediction of chemical oxygen demand (COD) or suspended solid (SS) removal using statistical methods and the
artifical neural network in the sugar industrial wastewaters. J Eng Appl Sci 2013;8:978–983.
- [12] Deniz ST, Ozkan P, Ozkan G. The accuracy of the prediction models for surface roughness and micro hardness of denture teeth. Dent Mater
J 2019;38:1012–1018. [CrossRef]
- [13] Mjalli FS, Al-Asheh S, Alfadala HE. Use of artificial neural network black-box modeling for the prediction of wastewater treatment plants per-
formance. J Environ Manage 2007;83:329–338. [CrossRef]
- [14] Yetilmezsoy K, Demirel S. Artificial neural network (ANN) approach for modeling of Pb(II) adsorption from aqueous solution by Antep
pistachio (Pistacia Vera L.) shells. J Hazard Mater 2008;153:1288–1300. [CrossRef]
- [15] Khan T, Mustafa MRU, Isa MH, Manan TSBA, Ho YC, Lim JW, et al. Artificial neural network (ANN) for modelling adsorption of lead (Pb (II)) from
aqueous solution. Water Air Soil Pollut 2017;228:1–15. [CrossRef]
- [16] Sadrzadeh M, Mohammadi T, Ivakpour J, Kasiri N. Neural network modeling of Pb2+ removal from wastewater using electrodialysis. Chem Eng Process Process Intensif 2009;48:1371–1381.
[CrossRef]
- [17] Ma X, Guan Y, Mao R, Zheng S, Wei Q. Modeling of lead removal by living Scenedesmus obliquus using backpropagation (BP) neural
network algo-rithm. Environ Technol Innov 2021;22:101410. [CrossRef]
- [18] Kardam A, Raj KR, Arora JK, Srivastava S. Artificial neural network modeling for bio-sorption of Pb (II) ions on nanocellulose
fibers. BioNanoSci 2012;2:153–160. [CrossRef]
- [19] Afroozeh M, Sohrabi MR, Davallo M, Mirnezami SY, Motiee F, Khosravi M. Application of artificial neural network, fuzzy inference system and
adap-tive neuro–fuzzy inference system to predict the removal of Pb(II) ions from the aqueous solutionby using magnetic graphene/nylon 6.
Chem Sci J 2018;9:1000185. [CrossRef]
- [20]Amiri MJ, Abedi-Koupai J, Eslamian S, Mousavi SF, Arshadi M. Modelling Pb(II) adsorption based on synthetic and industrial
wastewaters by ostrich bone char using artificial neural network and multivari-ate non-linear regression. Int J Hydrol Sci Technol 2013;3:221–
240. [CrossRef]
- [21] Kaya N, Arslan F, Yildiz Uzun Z. Production and characterization of carbon-based adsorbents from waste lignocellulosic biomass: their
effectiveness in heavy metal removal. Fuller Nanotub Carbon Nanostructures 2020;28:769–780. [CrossRef]
- [22] Gurney K. An Introduction to Neural Networks. 1st ed. Florida: CRC Press; 1997. [CrossRef]
- [23] Zhang G, Patuwo BE, Hu MY. Forecasting with artificial neural networks: The state of the art. Int J Forecast 1998;14:35–62. [CrossRef]
- [24] Kim SK, Huh JH. Artificial neural network block-chain techniques for healthcare system: Focusing on the personal health
records. Electronics 2020;9:763. [CrossRef]
- [25] Mansourian A, Ghanizadeh AR, Golchin B. Modeling of resilient modulus of asphalt concrete containing reclaimed asphalt pavement
using feed-forward and generalized regression neural net-works. J Rehabil Civ Eng 2018;6:132–147.
- [26] Jiang J, Trundle P, Ren J. Medical image analysis with artificial neural networks. Comput Med Imaging Graph 2010;34:617–631.
[CrossRef]
- [27] Bailer-Jones CAL, Gupta R, Singh HP. An Introduction to Artificial Neural Networks. In: Gupta R, Singh HP, Bailer-Jones CAL editors. Automated
data analysis in astronomy. New Delhi: Narosa Publishing House; 2001. pp. 1–18.
- [28] Ranasinghe RATM, Jaksa MB, Kuo YL, Nejad FP. Application of artificial neural networks for predict-ing the impact of rolling dynamic
compaction using dynamic cone penetrometer test results. J Rock Mech Geotech Eng 2017;9:340–349. [CrossRef]
- [29] Borovicka T, Jirina Jr M, Kordik P, Jirina M. Selecting Representative Data Sets. In Karahoca A, editor. Advances in data mining
knowledge discovery and applications. London: IntechOpen; 2012. pp. 43–70. [CrossRef]
- [30] Barzilai J. On Neural-Network Training Algorithms. In: Lawless WF, Mittu R, Sofge DA, editors. Human-machine shared contexts.
Massachusetts: Academic Press; 2020. pp. 307–313. [CrossRef]
- [31] Erdem F. Artificial neural network (ANN) approach to remazol yellow (RR) removal with S. cerevi-siae. Uludağ Univ J Fac Eng 2019;24:289–
297. [CrossRef]
- [32] Tiwaric CS, Naresh R, Jha R. Comparative study of backpropagation algorithms in neural network based identifıcation of power
system. Int J Comput Sci Inf Technol 2013;5:93–107. [CrossRef]
- [33] Karlik B, Vehbi A. Performance analysis of various activation functions in generalized mlp architec-tures of neural networks. Int J Artif Intell Expert Syst 2011;1:111–122.
- [34] Urban S. Neural Network Architectures and Activation Functions: A Gaussian Process Approach. 1st ed. München: Universitätsbibliothek
der TU München; 2018.
- [35] Hajduk Z. Hardware implementation of hyperbolic tangent and sigmoid activation functions. Bull Pol Acad Sci Tech Sci 2018;66:563–
577.
- [36] Seyedmohammadi J, Esmaeelnejad L, Ramezanpour H. Determination of a suitable model for prediction of soil cation exchange capacity. Model Earth Syst Environ 2016;2:156. [CrossRef]
- [37] Daliakopoulos IN, Coulibaly P, Tsanis IK. Groundwater level forecasting using artificial neural networks. J Hydrol 2005;309:229–240. [CrossRef]