TX 75083-3836, U.S.A., fax 01-972-952-9435. AbstractThis study presents the development of reservoir characterization inverse model equipped with ANN type of ISGA and MSGA parallel processing algorithms. In order to efficiently run the developed model, homogeneous PC-cluster was constructed by connecting four PC which have the same features. The model was adapted ANN to automatically determine optimum GA parameters of operator, number of individuals and operation rate, which is appropriate for the reservoir heterogeneity.By utilizing the developed model in this study, inverse calculation was conducted for the synthetic reservoir system with the aid of an ISGA-PP. As a result, it was found that convergence is stably progressed. In the result of permeability distribution, it shows that low permeable zone in central area for the system studied is appeared to be little different comparing to the result obtained by Kriging method which is using only static data. In the matching result of pressure, maximum relative error of 1.54% was presented at OP-4, and hence, the calculated permeability distribution is thought to be quite reliable. When MSGA-PP was applied to the same reservoir system as ISGA-PP, it converged stably similar to ISGA-PP. The difference between ISGA-PP and MSGA-PP is appeared only at convergence rate and the resulting permeability distribution is very similar to each other.In the evaluation of computing efficiency of ISGA-PP and MSGA-PP against GA-SP, the result shows that the efficiency of parallel processing system is more greater as the number of individuals increases. Also, regardless of the number of individuals, the calculating time in parallel processing system was greatly reduced by 3.6 times comparing to serial processing system of GA-SP. Finally, inverse calculation was carried out with MSGA-PP-ANN. As a result, it converged much more faster than MSGA-PP without having a artificial neural network system. It was expected that the model takes only superior individuals at the beginning obtained by optimum GA operator set, which have greater fitness values.