Networks of large pores connected by narrower throats (pore networks) are essential inputs into network models which are routinely used to predict transport properties from digital rock images. Extracting pore networks from micro-computed tomography (micro-CT) images of rocks involves a number of steps: filtering, segmentation, skeletonisation etc. Because of the amount of clay and their distribution, segmentation of micro-CT images is not trivial and different algorithms exist for doing this. Similarly, several methods are available for skeletonising the segmented images and for extracting the pore networks. The non-uniqueness of these processes raises questions about the predictive power of network models. In the present work, we evaluate the effects of these processes on the computed petrophysical and multiphase flow properties of reservoir rock samples.
Using micro-CT images of reservoir sandstones, we first apply three different segmentation algorithms and assess the impacts of the different algorithms on estimated porosity, amount of clay and their distribution. Single-phase properties are computed directly on the segmented images and compared with experimental data. Next, we extract skeletons from the segmented images using three different algorithms. On the generated pore networks, we simulate two-phase oil/water and three-phase gas/oil/water displacements using a quasi-static pore network model.
Analysis of the segmentation results show differences in the amount of clay, total porosity and computed single-phase properties. Simulated results show that there are differences in the network-predicted single-phase properties as well. However, predicted multiphase transport properties from the different networks are in good agreement. This indicates that the topology of the pore space is well preserved in the extracted skeleton. Comparison of the computed capillary pressure and relative permeability curves for all networks with available experimental data show good agreements.
By using a segmentation which captures porosity and microporosity, we show that the extracted networks can be used to reliably predict multiphase transport properties irrespective of the algorithms used.