It is a well-established fact that the determination of reservoir facies and zones with high-quality plays a pivotal role in reservoir modelling and future drilling in developing gas fields. As an index that varies in line with changes in the reservoir characteristics, Flow Zone Indicator (FZI) could be an influential factor in determining the reservoir facies. The present study attempts to propose a modern, improved model by combining intelligent systems to estimate the FZI cube in the entire oil/gas field. This Committee Machine Inference System (CMIS) integrates the predicted results obtained from the intelligent neural, fuzzy, and neuro-fuzzy systems with proper weights. Optimal weights for each method are predicted using Ant Colony Optimisation for Continuous Domains (ACOR). To apply the aforementioned approaches, well logs and seismic data were extracted from one of the gas fields in south of Iran. At the first stage, seismic attributes which establish a stronger correlation with the target data (FZI) were selected through the application of stepwise regression. Subsequently, a 3D FZI cube in the entire field was estimated. At the final step, various facies were delineated by means of Fuzzy C-Means clustering algorithm. The results illustrate that CMIS, which utilises ACOR, outperforms other single systems acting alone.