Search

• The mutual information method was used as a feature selection method for choosing geological and hydraulic fracturing features. • The Gaussian process regression (GPR) method was applied to predict the open hole flow rate after fracturing work. • The performances of the GPR, random forest, and ANN models were compared based on the actual engineering data of 175 sample wells. • The Shapley additive explanation value method was applied to obtain the dominant factors influencing the initial gas production rate. In shale gas production rate prediction, data are commonly acquired through simulations, which offer benefits but cannot fully predict the outcome of real engineering projects. This paper applied a Gaussian process regression (GPR) model, which was trained on the geological and field data from 175 wells in the Fuling gas field, China. GPR was chosen because this method can be suitably applied to a small dataset. To improve the accuracy, reduce the computational consumption, and increase the interpretability of the model, the mutual information method was used for feature selection after Pearson coefficient analysis. Based on comparison of the GPR, random forest and artificial neural network models, GPR achieved the best performance with the mutual information feature selection method, exhibiting R2 values of 0.71 and 0.68 for the training and test datasets, respectively. After model training, the model applied the Shapley additive explanation (SHAP) value method. The results indicate that geological factors dominate the gas production rate in Fuling, China. The volume of fluid loss could exert a negative impact on production rates and increase the consumption of 40–70 mesh proppant could increase gas production in Fuling. [ABSTRACT FROM AUTHOR]