Artificial Neural Network (ANN) modelling of scale dependent dynamic capillary pressure effects in two-phase flow in porous media

A number of numerical simulations and experimental investigations have reported the impact of specific domain size on the dynamic capillary pressure which is one of the forces that govern two-phase flow in porous media. These investigations are often achieved with time-consuming experiments and/or costly/complex computational methods. In view of this, a computationally efficient and simple alternative platform for the prediction of the domain scale dependence of the dynamic capillary pressure effects, defined in terms of a coefficient named as dynamic coefficient ( ), is developed using artificial neural network (ANN). The input parameters consist of the phase saturation, media permeability, capillary entry pressure, viscosity ratio, density ratio, temperature, pore size distribution index, porosity and domain volume with corresponding output obtained at different domain scales. Good generalization of the model was achieved by acquiring data from independent sources comprising experiments and numerical simulations. Different ANN configurations as well as linear and non-linear multivariate regression models were tested using a number of performance criteria. Findings in this work showed that the ANN structures with two hidden layers perform better than those with single hidden layer. In particular, the ANN configuration with 13 and 15 neurons in the first and second hidden layers, respectively, performed the best. Using this best-performing ANN, effects of increased domain size were predicted for three separate experimental results obtained from literature and our laboratory with different domain scales. Results showed increased magnitude of as the domain size increases for all the independent experimental data considered. This work shows the applicability and techniques of using ANN in the prediction of scale dependence of two-phase flow parameters.