Short Communication The use of NARX neural network for modeling of adsorption of zinc ions using activated almond shell as a potential biosorbent Semra Çoruh a,⇑ , Feza Geyikçi b , Erdal Kılıç c , Ufuk Çoruh d a Department of Environmental Engineering, Ondokuz Mayıs University, 55200 Samsun, Turkey b Department of Chemical Engineering, Ondokuz Mayıs University, 55200 Samsun, Turkey c Department of Computer Engineering, Ondokuz Mayıs University, 55200 Samsun, Turkey d Department of Computer Education and Instructional Technology, Ondokuz Mayıs University, 55200 Samsun, Turkey highlights  The removal increased with the increasing adosorbant amount, pH and contact time.  The percentage of removal decreased with increasing concentration.  The values of optimum input parameters and efficiency are close to each other.  Activated almound shell can be effectively used for the removal of zinc ions. article info Article history: Received 24 July 2013 Received in revised form 30 September 2013 Accepted 6 October 2013 Available online 12 October 2013 Keywords: Zinc Biosorption Almond shell Isotherm NARX neural network abstract In this study, nonlinear autoregressive model processes with exogenous input (NARX) are applied for the prediction of percentage adsorption efficiency for the removal of zinc ions from wastewater by activated almond shell. The effect of operational parameters such as pH, dosage, particle size and initial metal ions concentration are studied to optimize the conditions for maximum removal of zinc ions. The model is first developed using a two layer NARX network. A comparison between the model results and experimental data showed that the NARX model is able to predict the removal of zinc ions from wastewater. The outcomes of suggested NARX modeling were then compared to batch experimental studies. The results show that activated almond shell is an efficient sorbent and NARX network, which is easy to implement and is able to model the batch experimental system. Ó 2013 Elsevier Ltd. All rights reserved. 1. Introduction Heavy metals have become major surface water and groundwa- ter contaminants. Electroplating, metal finishing, textile, storage batteries, mining, ceramic and glass industries discharge wastewa- ter with high heavy metal content. The release of heavy metals such as Ni 2+ , Cu 2+ , Zn 2+ , Pb 2+ and Co 2+ into the environment is a po- tential threat to water and soil quality as well as to plant, animal and human health (Cheung et al., 2000; El-Kamash et al., 2005; Aziz et al., 2008). One of the most important heavy metal is zinc. Various traditional methods, such as chemical precipitation, elec- trolyte reduction, solvent extraction, ion exchange, complexation/ sequestration, cementation, electrochemical operation, coagula- tion–flocculation, biological treatment, and adsorption are used to remove these heavy metal ions, but their applications are largely limited by harsh reaction conditions, high cost and secondary pol- lution. Several novel methods for removing heavy metal ions have been developed and explored, such as biosorption (Babel and Kurniawan, 2003; Aziz et al., 2008; Ding et al., 2012). Biosorption is the natural capability of the biomass to immobilize dissolved components, e.g. heavy metal ions, on its surface. Biomass is com- posed mostly of polysaccharides, proteins and fats, and has many functional groups able to bind heavy metal ions (Doulati et al., 2008; Kazemipour et al., 2008; Witek-Krowiak et al., 2011). A wide variety of materials derived from natural resources, plant wastes or industrial by-products such as peat, wood, barley, rice husk, plant straw, rice bran, peanut shell, almond shell, hazelnut shell, algal biomass, fruit stones, plum kernels, banana pith, soybean, cotton- seed hulls, humic acids, corn stalk, tree bark, sugar beet pulp, leaves, green algae, activated carbon fibers, coconut, fly ash, pine bark, black cumin, sawdust are being used as low cost alternatives to expensive adsorbents (Bulut and Tez, 2007; Kazemipour et al., 0960-8524/$ - see front matter Ó 2013 Elsevier Ltd. All rights reserved. http://dx.doi.org/10.1016/j.biortech.2013.10.019 ⇑ Corresponding author. Tel.: +90 362 312 19 19. E-mail address: semcoruh@omu.edu.tr (S. Çoruh). Bioresource Technology 151 (2014) 406–410 Contents lists available at ScienceDirect Bioresource Technology journal homepage: www.elsevier.com/locate/biortech