Reliable data on the properties of the porous medium are necessary for the correct description of the process of displacing hydrocarbons from the reservoirs and forecasting reservoir performance. The true permeability of the reservoir is one of the most important parameters which determination is time-consuming, costly and require skilled labor. The paper describes the methodology for determining the permeability of a porous medium, based on machine learning. The results of laboratory experiments, available in the database (terrigenous reservoirs with permeability in the range from 12 to 1132 md), are used to train the neural network, and then to predict the reservoir permeability. Comparison of the predicted and calculated permeability values showed a fairly good match between them with the determination coefficient of 0.92. The last task considered in this paper is to obtain an analytical expression describing a fluid flow in a porous medium using machine learning. This procedure enabled to obtain a resultant equation of fluid flow in a wide range of reservoir parameters and pressure gradients, which can be used in reservoir simulators.

Suspended solids in the injection water cause impairment of water injectivity during waterflooding operations. Suspended solids affect reservoir properties and decrease the permeability of reservoir rocks causing an increase of injection pressure and a decrease in water injectivity. Removal of all suspended solids from injection water is an expensive and economically unfeasible process. To minimize the effects of suspended solids to the formation, it is necessary to determine an impairment mechanism of suspended solids on oil displacement and, therefore, optimize the water treatment process. In this paper, an analytical model that describes the relationship between injection water quality and impairment mechanisms on oil displacement is presented. A formation impairment was calculated, introducing the parameter called impairment ratio, which represents the ratio between suspended solids and pore size distribution of reservoir rock. Based on the impairment ratio, decreases in porosity and permeability were calculated with changes in capillary pressure, relative permeability, and displacement efficiency. The model was tested for three different types of injection water. Results indicated the presence of formation impairment even with the smallest particles. Suspended solids had the greatest influence on porosity and permeability impairment. The model could be used as input for reservoir modelling studies for monitoring and controlling displacement efficiency during waterflooding as well as for planning and modification of water treatment units.

This article examines the nonlinear effects of fluid flow in a porous medium, governed by a new semi-analytical equation, from three aspects: equation derivation, experimental verification, and macroscale simulation modelling. The rigorous derivation of the new equation is presented with a semi-analytical approach in which the gas slippage effect and inertial forces are described. The latter effect is controlled by Fochheimer number, which is defined as a product of tortuosity and Reynolds number. The new equation successfully predicts the deviations from Darcy’s law in low-permeability media when the gas slippage effect occurs. The Klinkenberg gas slippage factor is obtained as a function of porous media’s structural parameter (porosity and intrinsic permeability) and gas property (mean free path of gas molecules). The equation validations are performed by core flow experiments for a wide range of reservoir properties, which yield good matching relationship between modelled and observed values. In addition, the proposed semi-analytical equation is used to simulate gas flow in the radial model.