Search

• Siliciclastic reservoirs comprise cm-scale lithological heterogeneity. • Expressing heterogeneity is challenging due to a large number of rock interfaces. • A new approach is presented which identifies the unique interface associations. • This helps in reducing the variables required to express heterogeneity. Recent developments in subsurface data capturing technologies have presented the opportunity of representing high-resolution information in field scale reservoir models of CO 2 geo-sequestration sites. While the wealth of geological data is critical for the accurate prediction of CO 2 flow and trapping in the subsurface, it often presents computational challenges. This is especially true for the representation of rock, or lithological, interfaces which are small-scale features in reservoirs and significantly control CO 2 migration and trapping. It is important to reduce this information to ensure that numerical simulations are completed within a reasonable time. However, care must be taken to ensure that none of the key lithological interface associations are lost during data reduction. This study presents a machine learning based approach for expressing the amount of rock interfaces characteristic of sedimentary CO 2 storage reservoirs in terms of a reduced number of principal components which capture the necessary geological information. The workflow is applied to a high-resolution reservoir model of the Paaratte Formation, Otway Basin, Australia, which is coastal to shallow marine siliciclastic reservoir. The information in the reservoir model was captured using 922 k rock interfaces. However, the algorithm predicts that the same information could be represented using only 7 principal lithological interface associations. The outcomes are validated using multiphase flow simulations which show the uniqueness of these principal components in terms of their impact on CO 2 flow and trapping. [ABSTRACT FROM AUTHOR]