基于Granger-LSTM模型的东营凹陷页岩油产量预测OA

The production dynamics of shale oil horizontal wells are highly complex,and existing prediction techniques often fail to achieve satisfactory accuracy.In this study,production data from wells X1 and X2 in Dongying Depression were ana-lyzed.Granger causality analysis was first employed to identify time-varying factors strongly correlated with shale oil produc-tion,thereby optimizing the model input features.Subsequently,a long short-term memory(LSTM)network was developed to construct the production prediction model,with its hyperparameters optimized using the particle swarm optimization(PSO)algorithm.The predictive performance of the LSTM model was compared with recurrent nural ntworks(RNN),gted rcurrent uits(GRU),and temporal cnvolutional ntworks(TCN).The results highlight the critical role of feature selection in produc-tion forecasting.For example,for well X1,the LSTM model incorporating Granger-based features reduced the root mean square error by 3.41 m3 compared with the model using features selected via Spearman analysis,significantly enhancing pre-diction accuracy.Although various time-series models exhibit strong predictive capabilities,the LSTM model outperforms others in capturing dynamic temporal characteristics,providing a solid theoretical basis and technical support for complex shale oil production forecasting.