Application of LSTM intelligent algorithm in shale gas development

Abstract

Shale gas is regard as a clean, low-carbon and green energy, and the utilization and efficient development of shale gas is of great significance for achieving the dual carbon goals. Horizontal well hydraulic fracturing is an important way to develop shale gas resources. Predicting the production of shale gas under different engineering or geological conditions of shale reservoirs is crucial to the optimal fracturing design of shale gas development. This study proposes a LSTMbased intelligent model to predict the gas production of shale, and this novel smart model predicts gas production quickly and accurately. We comprehensively evaluate and compare the performance of the AI network, and the results of test show that the LSTM-based AI model can output gas production data by inputting reservoir and engineering parameters. The mean value of relative error of the LSTM-based AI model is 5.32%, which is reliably for the prediction of gas production. The peak of relative errors of this AI model in this study on day 100, 300, and 500 are 4.67%, 6.53%, and 8.23%, respectively. This study can provide an effective and quick method for shale gas prediction and improve the intelligence level of energy development.