Using Unsupervised Machine Learning to Characterize Capillary Flow and Residual Trapping

Abstract

Recent research has highlighted the impact mesoscale heterogeneity can have on larger‐scale multiphase fluid flow properties. However, currently, there is no consensus on how to quickly and reliably analyze coreflooding experimental data to gain insights into mesoscale capillary‐dominated flow behaviors and how rock petrophysical properties affect such behaviors. In this study, we combine a machine learning‐based clustering method with physics‐based hypothesis testing to analyze multistage steady‐state coreflooding experimental data. By examining five different sets of coreflooding data, we have found that under capillary‐dominated flow regimes, voxel‐level CO2 saturation fields are much more heterogeneous as capillary equilibrium is approached. CO2 saturation time series behaviors are distinctively different between high and low permeability voxels. However, the effect of mesoscale permeability greatly diminishes under viscous‐dominated flow regimes. By computing the maximum and optimal number of clusters on the CO2 saturation time series data, we are able to differentiate between these two flow regimes. Through this analysis method, it is now also possible to identify regions within a sandstone core with capillary heterogeneity trapping behaviors. It is confirmed that capillary heterogeneity trapping indeed occurs upstream of capillary barriers. Furthermore, we have discovered a new type of capillary heterogeneity trapping—one that occurs within the capillary barrier itself, which can cause parts of the core to achieve residual CO2 saturations much higher than expected based on existing models of residual gas trapping.

Characterizing the Effect of Capillary Heterogeneity on Multiphase Flow Pulsation in an Intermediate‐Scale Beadpack Experiment Using Time Series Clustering and Frequency Analysis

“…) but still within the strongly capillary-dominated flow regime (Jackson & Krevor, 2020;Ni & Benson, 2020;Ni et al, 2021).…”

“…The clustering algorithm is applied directly on the pixel-wise NWP saturation time series data without any statistical preprocessing or feature extraction steps (Ni & Benson, 2020). After clustering is done, we compute the cluster NWP volume time series by multiplying the cluster mean (arithmetic) NWP saturation by the cluster pore volume.…”

Harnessing the power of machine learning for carbon capture, utilisation, and storage (CCUS) – a state-of-the-art review

“…Each voxel was treated as one data point, and the time series properties at each voxel were treated as individual attributes (i.e., CO 2 saturation time series). The CO 2 saturation and the porosity maps were obtained through CT image manipulation, and the voxel-level permeability map was obtained using the extended Krause's method 199 . This study tested two clustering methods and found that K-means clustering was more suitable for characterizing flow behaviours and hierarchical clustering was more desirable for identifying the capillary heterogeneity trapping behaviours.…”

Review of Data Science Trends and Issues in Porous Media Research With a Focus on Image‐Based Techniques

“…As an example application of this algorithm in porous material research, Ni and Benson (2020) used both k ‐means and agglomerative hierarchical clustering algorithm on time series data to characterize flow and trapping behavior of during core flooding process. The goal was to describe that flow mechanisms are capillary or viscous dominated.…”