Towards Better Shale Gas Production Forecasting Using Transfer Learning
This work addresses the challenge of accurate production forecasting for shale gas operators in data-scarce regions, representing an incremental improvement over existing methods.
The paper tackles the problem of forecasting shale gas production in counties with limited sample wells by using transfer learning from adjacent counties, achieving a reduction in forecasting error between 11% and 47% compared to the Arps decline curve model.
Deep neural networks can generate more accurate shale gas production forecasts in counties with a limited number of sample wells by utilizing transfer learning. This paper provides a way of transferring the knowledge gained from other deep neural network models trained on adjacent counties into the county of interest. The paper uses data from more than 6000 shale gas wells across 17 counties from Texas Barnett and Pennsylvania Marcellus shale formations to test the capabilities of transfer learning. The results reduce the forecasting error between 11% and 47% compared to the widely used Arps decline curve model.