Prediction of two-metal biosorption equilibria using a neural network

A feedforward neural network model with a single hidden layer was used to correlate and predict biosorption equilibrium data in a binary metal system. Experimental data on the biosorption of Fe(III) and Cr(VI) by the microalga Chlorella vulgaris reported in the literature was used to assess the performance of the neural network. It was demonstrated that the neural network approach was significantly more accurate than the traditional modeling approach based on Langmuir-type models. To assess the predictive capability of the neural network model, the network was trained using a subset of available data. The suitably trained neural network was found to be capable of predicting fresh data not belonging to the training set. However, training data should be selected carefully if the best results are to be achieved. © 2003 SDU. All rights reserved.

[1]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[2]  Q. Yu,et al.  Binary adsorption of copper(II) and cadmium(II) from aqueous solutions by biomass of marine alga Durvillaea potatorum , 1999 .

[3]  Neural Network Modeling of Adsorption of Binary Vapour Mixtures , 1999 .

[4]  B. Volesky,et al.  Description of two‐metal biosorption equilibria by Langmuir‐type models , 1995, Biotechnology and bioengineering.

[5]  D. R. Baughman,et al.  Neural Networks in Bioprocessing and Chemical Engineering , 1992 .

[6]  Seppo Palosaari,et al.  Neural Networks for Chemical Engineering Unit Operations , 1999 .

[7]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[8]  T. Kutsal,et al.  Lead, copper and zinc biosorption from bicomponent systems modelled by empirical Freundlich isotherm , 2000, Applied Microbiology and Biotechnology.

[9]  Min-Gyu Lee,et al.  Biosorption Characteristics in the Mixed Heavy Metal Solution by Biosorbents of Marine Brown Algae , 2002 .

[10]  R. Rathbone,et al.  A Neural Network Model for Prediction of Binary Adsorption Using Single Solute and Limited Binary Solute Adsorption Data , 1996 .

[11]  A. B. Bulsari,et al.  Neural Networks for Chemical Engineers , 1995 .

[12]  M. Syu,et al.  Artificial neural network modeling of adsorptive separation , 1993 .

[13]  R. Buchholz,et al.  Comparative analysis of the biosorption of cadmium, lead, nickel, and zinc by algae. , 2001, Environmental science & technology.

[14]  S. Schiewer,et al.  Modeling Multi-Metal Ion Exchange in Biosorption , 1996 .

[15]  M. Blazquez,et al.  Biosorption of copper and zinc by Cymodocea nodosa. , 1999, FEMS microbiology reviews.

[16]  K. Paknikar,et al.  Influence of co-cations on biosorption of lead and zinc – a comparative evaluation in binary and multimetal systems , 1999 .

[17]  Jo‐Shu Chang,et al.  Quantitative Analysis and Equilibrium Models of Selective Adsorption in Multimetal Systems Using a Bacterial Biosorbent , 1998 .

[18]  Z. Aksu,et al.  Application of multicomponent adsorption isotherms to simultaneous biosorption of iron(III) and chromium(VI) on C. vulgaris , 1997 .