Artificial neural network modeling of photocatalytic removal of a disperse dye using synthesized of ZnO nanoparticles on montmorillonite Murat Kırans ßan a , Alireza Khataee b,⇑ , Semra Karaca a,⇑ , Mohsen Sheydaei b a Department of Chemistry, Faculty of Science, Atatürk University, 25240 Erzurum, Turkey b Research Laboratory of Advanced Water and Wastewater Treatment Processes, Department of Applied Chemistry, Faculty of Chemistry, University of Tabriz, Tabriz, Iran highlights  Synthesis and immobilization of zinc oxide nanoparticles on montmorillonite.  Characterization of the ZnO/MMT nanocomposite by XRD, SEM, TEM, and BET.  Photocatalysis of a disperse dye by synthesized ZnO/MMT nanocomposite.  ANN modeling of the effect of the ZnO/MMT/UV-C process in removal of the dye. graphical abstract Schematics of synthesis of ZnO nanoparticles on montmorillonite. Swelling MMT CTAB surfactant 1 M NaOH ZnCl2 solution Stirred for 6 h Raw MMT (1 g) Distilled water (100 mL) Stirred for 24 h Stirred for 6 h ZnCl2 (1 g) Distilled water (20 mL) Stirred for 20 min Stirred for 6 h (pH=12.5) Modified MMT Centrifuged washed/dried ZnO/MMT nanocomposite article info Article history: Received 30 September 2014 Received in revised form 11 November 2014 Accepted 28 December 2014 Available online 14 January 2015 Keywords: Artificial neural network Photocatalytic degradation ZnO nanoparticles ZnO/MMT nanocomposite abstract In this study, the photocatalytic ability of ZnO/Montmorilonite (ZnO/MMT) nanocomposite under UV-A, UV-B and UV-C radiation was investigated. ZnO nanoparticles were synthesized on the surface of MMT and used as photocatalyst in decolorization of Disperse Red 54 (DR54) solution. Synthesized nanocom- posite was characterized by X-ray diffraction (XRD), scanning electron microscopy (SEM), transmission electron microscopy (TEM) techniques and nitrogen adsorption/desorption isotherms curves. The average width of synthesized ZnO particles is in the range of 30–45 nm. Effect of UV light regions, initial dye con- centration, initial dosage of nanocomposite, and reusability of catalyst was studied on decolorization effi- ciency. The highest decolorization efficiency was achieved under UV-C radiation. A three-layered feed forward back propagation artificial neural network model was developed to predict the photocatalysis of DR54 under UV-C radiation. According to ANN model the ZnO/MMT dosage with a relative importance of 49.21% is the most influential parameter in the photocatalytic decolorization process. Ó 2015 Elsevier B.V. All rights reserved. Introduction Heterogeneous photocatalytic oxidation process, as an advanced oxidation process, has been widely applied and occupied an important place in the field of water and wastewater treatment over the past few decades [1,2]. The photochemical reactions relied on the in-situ generation of hydroxyl radicals ( Å OH) employing semiconductor photocatalyst such as TiO 2 and ZnO, and an ener- getic radiation source like UV light is considered as promising pro- cess for degradation of persistent organic pollutants such as herbicides, pesticides and dyes [3–5]. Heterogeneous photocatalyst has moderate energy band-gap between its valence and conduction bands [6]. The absorption of http://dx.doi.org/10.1016/j.saa.2014.12.100 1386-1425/Ó 2015 Elsevier B.V. All rights reserved. ⇑ Corresponding authors. Tel.: +98 411 3393165; fax: +98 411 3340191 (A. Khataee). Tel.: +90 442 2314435; fax: +90 442 2360948 (S. Karaca). E-mail addresses: a_khataee@tabrizu.ac.ir, ar_khataee@yahoo.com (A. Khataee), skaraca@atauni.edu.tr, semra_karaca@yahoo.com (S. Karaca). Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy 140 (2015) 465–473 Contents lists available at ScienceDirect Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy journal homepage: www.elsevier.com/locate/saa