Predicting the Gas Storage Capacity in Shale Formations Using the Extreme Gradient Boosting Decision Trees Method

Accurate shale gas reserves estimation is essential for development. Existing machine learning (ML) models for predicting gas isothermal adsorption are limited by small datasets and lack verified generalization. We constructed an “original dataset” containing 2112 data points from 11 measurements on samples from 8 formations in 3 countries to develop ML-based prediction models. Similar to previous ML models, total organic matter, pressure, and temperature are characterized as the three most significant features using the mean impurity method. In contrast to previous ML models, the study reveals that these three features are inadequate to be used to make reasonable predictions for the datasets from the measurements different from those used to train the models. Instead, the extreme gradient boosting decision trees (XGBoost) model with two more features (specific surface area and moisture) exhibits good robustness, generalization, and precision in the prediction of gas isothermal adsorption. Overall, An XGBoost model with optimal input features is developed in this work, which exhibits both good performance in gas adsorption prediction and good potential for the estimation of gas storage in shale gas development.