The decolorization of a dye solution containing C.I. Direct Yellow 12 (DY12) was performed by photoelectro-Fenton (PEF) combined with photocatalytic process. Carbon nanotube-polytetrafluoroethylene (CNT-PTFE) electrode was used as cathode. The investigated photocatalyst was ZnO nanoparticles having specific surface area (BET) 32.23 m(2)/g, and mean crystal size of 15 nm immobilized on glass plates. A comparison of electro-Fenton (EF), UV/ZnO, PEF and PEF/ZnO processes for decolorization of DY12 solution was performed. Results showed that color removal follows the decreasing order: PEF/ZnO>PEF>EF>UV/ZnO. The influence of the basic operational parameters such as initial pH of the solution, initial dye concentration, applied current, kind of ultraviolet (UV) light and initial Fe3+ concentration on the decolorization efficiency of DY12 was studied. The mineralization of the dye was investigated by total organic carbon (TOC) measurements that showed 96.7% mineralization of 50 mg/l dye at 6 h using PEF/ZnO process. An artificial neural network (ANN) model was developed to predict the decolorization of DY12 solution. The findings indicated that artificial neural network provided reasonable predictive performance (R-2 = 0.980). (C) 2011 Elsevier B.V. All rights reserved.