Prediction model for rock elastic modulus based on TPE-optimized ensemble learning

ObjectiveGeophysical data is often used to determine the elastic modulus of formations in oil and gas engineering, with experimental data from small core samples used for calibration. However, acquiring core samples from every stratum is impractical and often leads to inadequate performance under complex geological settings. To improve the predictive accuracy and generalizability of the rock elastic modulus, an intelligent prediction model based on fundamental rock physical properties is proposed. MethodsUsing 397 sets of core experimental data from diverse sources, with compressional and shear wave velocities and density as input variables, intelligent prediction models for rock elastic modulus were developed based on three ensemble learning algorithms (Random Forest, XGBoost, LightGBM). The TPE method was employed to optimize the models. The dynamic and static elastic modulus regression models were constructed based on current methods used in petroleum engineering to provide a comprehensive assessment of the performance of the intelligent predictive model using statistical indicators. Additionally, the SHAP attribution analysis was utilized to assess the contribution of each input variable to the model. ResultsThe research findings indicated that: ① The proposed intelligent prediction model using TPE was significantly better than traditional statistical regression models, achieving accurate predictions of the elastic modulus without distinguishing geological layers, with strong generalization ability. Among the three models, the XGBoost model performed the best (R2=0.87, RMSE=6.94, MAE=4.96). ②Shear wave velocity made the greatest contribution to the model, followed by compressional wave velocity, with density having the least impact. Accurate shear wave velocity was crucial for predicting the elastic modulus. ConclusionThis method allows for the precise prediction of elastic modulus without the need for prior identification of the work area and strata, providing valuable insights for the design and implementation of oil and gas engineering projects.