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.
Improving the speed and accuracy of unconventional natural gas production forecasts is the key to scientific and efficient development of unconventional resources. The existing prediction methods based on the transmission mechanism make assumptions and simplifications on the model, and it is difficult to comprehensively and accurately evaluate the main control factors of production capacity, resulting in large production prediction errors. This paper proposes a productivity prediction method for unconventional natural gas wells based on artificial intelligence (AI) and data mining technologies. We use the Pearson correlation coefficient and grey relational analysis to screen out the main control factors, and select the best yield intelligent forecasting model by training and comparing a variety of commonly used machine learning methods. This paper takes the Alberta tight gas field in Canada as an example to illustrate the effectiveness and practicability of this method.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.