Well Production Forecasting Using Modern Deep Learning Models

Accurate well rate forecasting is essential for successful field development in the oil industry. Recurrent-based deep learning models have been used for production forecasting. However, recent advancements in the field have led to the use of transformer and transfer learning to overcome the need for large amounts of data. This dissertation presents an approach to using modern deep learning algorithms for oil production forecasting.
To enhance the accuracy of oil rate predictions in the Norwegian Volve and Norne fields, a combination of statistical models and deep learning models were investigated. These models included Autoregressive Integrated Moving Average (ARIMA), Light Gradient Boosting Machine (LightGBM), Block Recurrent Neural Network (BlockRNN), Temporal Fusion Transformer (TFT), and the Neural Basis Expansion Analysis for Interpretable Time Series Forecasting (N-BEATS) using transfer learning. The models used multivariate real time historical data, such as bottomhole pressure, wellhead pressure, wellhead temperature, and choke size, as input features to predict the oil rate of two wells in each field. The models were trained on 85% of the data and tested on the remaining 15%, with the advanced models TFT and N-BEATS being compared to the conventional models in terms of prediction performance.
The complex production data used in this forecasting problem showed no clear trends or seasonality. The advanced deep learning models, the Temporal Fusion Transformer (TFT) and the Neural Basis Expansion Analysis for Interpretable Time Series (N-BEATS), outperformed other models in terms of forecasting accuracy. The TFT model was able to significantly minimize the testing Mean Squared Error (MSE). Additionally, the model predicted a range of uncertainty between the 10th and 90th percentiles to consider the variability in the blind test intervals. The N-BEATS transfer learning model was better at capturing dynamic time series features from the M4 dataset and applying that knowledge to predict oil rates in the Norne field, without any input variables like reservoir pressure. The N-BEATS approach was superior to all other models in terms of the difference between the forecast and actual rate, resulting in a mean square error of 0.02 for well F-12 and 0.05 for well F-11 respectively.
Previously, machine learning and deep learning techniques in the petroleum sector mainly utilized only historical field data for their predictions. However, our study highlights the potential of transfer learning and the N-BEATS model in green fields or newly developed areas where historical data are scarce. Additionally, the TFT probabilistic deep learning model showed outstanding results, outperforming traditional models, and providing a range of forecast uncertainty, which is very useful in making well-informed decisions in field development.