Machine learning - based shale wettability prediction: Implications for H₂, CH₄ and CO₂ geo-storage

Shale wettability determines shale gas productivities and gas (H₂, CH₄ and CO₂) geo-storage efficiencies. However, shale wettability is a complex parameter which depends on multiple influencing factors, thus very time-consuming and costly to measure experimentally. Herein, we combined the eXtreme gradient boosting (XGBoost) and Shapley additive explanation (SHAP) machine learning methods to accurately predict brine advancing (θ_A) and receding (θ_R) contact angles and estimate shale wettability. The XGBoost model demonstrated much higher prediction accuracies than the commonly-used multiple linear regression and partial least squares regression models, e.g., R² was 0.946–0.999, 0.794–0.821, and 0.635–0.674, respectively for these three models. The SHAP sensitivity analyses showed that total organic carbon content and gas molecular weight (M_G) were the two most significant factors influencing shale wettability. In addition, shale hydrophobicity positively correlated with M_G, calcite content, pressure and brine ionic strength, while negatively correlated with temperature and quartz content. This work provides an efficient approach for shale wettability estimation, thus aiding in the implementation of improved gas recovery and gas geo-storage processes, to further guarantee energy security and mitigate climate change.