Repository hosted by TU Delft Library

Home · Contact · About · Disclaimer ·
 

Deep learning history matching for real time production forecasting

Publication files not online:

Author: Loh, K.K.L. · Shoeibi Omrani, P. · Linden, R.J.P. van der
Type:article
Date:2018
Publisher: European Association of Geoscientists and Engineers EAGE
Source:1st EAGE/PESGB Workshop on Machine Learning, 29-30 November 2018
Identifier: 861889
ISBN: 9789462822719
Keywords: Physics · Forecasting · Long short-term memory · Machine learning · Natural gas wells · Offshore gas well production · Precipitation (chemical) · Uncertainty analysis · Computational costs · Data assimilation methods · Ensemble Kalman Filter · History matching · Operational decision making · Prediction model · Real-time production · Salt precipitation · Deep learning · Industrial Innovation

Abstract

The forecasting of gas production from mature gas wells, due to their complex end-of-life behaviour, is challenging and often associated with uncertainties (both measurements and modelling uncertainties). Yet, having good forecasts are crucial for operational decision making. In this paper, we present a purely black-box based approach, which combines the use of a data assimilation method, the Ensemble Kalman Filter (EnKF) and a modified deep LSTM model as the prediction model within the approach. This approach is tested on two mature gas wells in the North Sea which were suffering from salt precipitation. Results showed that the approach of combining a deep LSTM model within EnKF can be effective when deployed in a real-time production optimization environment. We observed that having the EnKF increases the robustness of the forecasts by the black box prediction model while reducing computational cost of retraining the black-box models for every individual well.