Over the years, there have been advances in the processes used in the drilling of oil and the transportation by the use of pipelines. Combining multiple computational intelligence methods so as to create a single hybrid flow model has become something common over the years. Furthermore, the sector discovered that there is the possibility of increasing the efficiency of the pipeline transportation method of oil by adding water. The addition of water to crude seems to be a pivotal technique of decreasing the gradient of pressure in a particular oil throughput. To calculate the extent to which the pressure gradient reduced in the pipeline after the introduction of water, the use of Navier-Stokes equations are applied and solved using a numerical procedure in a pipe that is circular. Furthermore, in this paper, the use of prediction techniques such as data mining and computational intelligence aided in the determination of permeability and the porosity of the petroleum reservoirs. The data from these techniques shows that the pressure gradient reduction factor was observed to be between the ranges of 1.12 and 1.31. The results seemed to be lower in practice as compared to the theoretical value, but they did support the theory that there was a reduction in the pressure and the wave motion due to the mixture. Moreover, it brought to light the fact that the use of hybrid computational intelligence played a role in the determination of the permeability of the oil reservoirs and thus the equipment to be used in the drilling processes. Looking at the execution time, the hybrid models showed that a shorter time would be taken provided the training techniques were used, and the services carried out in a particular method.