A Supervised Learning Approach for Accurate Modeling of CO₂–Brine Interfacial Tension with Application in Identifying the Optimum Sequestration Depth in Saline Aquifers

Abstract

The CO 2 −brine interfacial tension (IFT) is a key parameter affecting the CO 2 storage capacity in saline aquifers and therefore should be accurately characterized to ensure the optimal design of CO 2 sequestration projects. This paper proposed the use of the extreme gradient boosting (XGBoost) trees for the fast and accurate modeling of the CO 2 −brine IFT. Results show that the novel model is capable of not only estimating the IFT but also reproducing the underlying correlation between the IFT and each input variable with remarkably high accuracies. Statistical matrices and point-wise error analyses demonstrate that the new model outperforms previous machine learning (ML) methods significantly. The estimation model was then applied for determining the optimum CO 2 sequestration depth in saline aquifers, which reveals that higher pressure and/or lower geothermal gradients result in a significant increase in the maximum structural trapping capacity that occurs at noticeably shallower formations.

Investigation of the Solubility of Elemental Sulfur (S) in Sulfur-Containing Natural Gas with Machine Learning Methods

“…In addition to its predictive accuracy, the interpretability of ML models is of equal importance. Compared to commonly used measures, such as Pearson (PR) correlation, gPOIM is able to avoid exaggerating the contribution of input variables and accurately assess the effect of the non-monotonicity of input variables; it is now used in practical engineering applications [ 44 , 45 ]. To compensate for the black box nature of the ML model, the study used gPOIM to visualize the contribution of the input variables, as shown in Figure 10 .…”

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

“…They found that RBFNN-ABC would yield to the most accurate prediction in the tests among all combinations. Zhang et al 201 proposed a work to model the CO 2 −brine IFT using extreme gradient boosting (XGBoost) trees. The generated model was then employed to determine the optimal CO 2 sequestration depth in saline aquifers.…”

An automatic modeling approach for the potential evaluation of CO2 geological storage in the deep saline aquifer

“…The process of classification of fault-affected areas is shown in Figure 6. The burial depth of CO 2 is the distance from the top surface of the reservoir to the ground surface, namely the depth of the reservoir (Zhang et al, 2020). According to the supercritical CO 2 state condition, the theoretical depth of CO 2 geological storage is 800 m. Considering the current internationally accepted economic level, the economic depth of CO 2 geological storage is 3500 m. The depth of the reservoir can be modeled by the three-dimensional spatial interpolation method, as shown in Figure 7.…”