Uncertainty Quantification in CO 2 Trapping Mechanisms: A Case Study of PUNQ-S3 Reservoir Model Using Representative Geological Realizations and Unsupervised Machine Learning

Evaluating uncertainty in CO 2 injection projections often requires numerous high-resolution geological realizations (GRs) which, although effective, are computationally demanding. This study proposes the use of representative geological realizations (RGRs) as an efficient approach to capture the uncertainty range of the full set while reducing computational costs. A predetermined number of RGRs is selected using an integrated unsupervised machine learning (UML) framework, which includes Euclidean distance measurement, multidimensional scaling (MDS), and a deterministic K-means (DK-means) clustering algorithm. In the context of the intricate 3D aquifer CO 2 storage model, PUNQ-S3, these algorithms are utilized. The UML methodology selects five RGRs from a pool of 25 possibilities (20% of the total), taking into account the reservoir quality index (RQI) as a static parameter of the reservoir. To determine the credibility of these RGRs, their simulation results are scrutinized through the application of the Kolmogorov–Smirnov (KS) test, which analyzes the distribution of the output. In this assessment, 40 CO 2 injection wells cover the entire reservoir alongside the full set. The end-point simulation results indicate that the CO 2 structural, residual, and solubility trapping within the RGRs and full set follow the same distribution. Simulating five RGRs alongside the full set of 25 GRs over 200 years, involving 10 years of CO 2 injection, reveals consistently similar trapping distribution patterns, with an average value of D max of 0.21 remaining lower than D critical (0.66). Using this methodology, computational expenses related to scenario testing and development planning for CO 2 storage reservoirs in the presence of geological uncertainties can be substantially reduced.