Machine-Learning Based Selection of Candidate Wells for Extended Shut-In Due to Fluctuating Oil Prices

Fluctuations in oil prices adversely affect decision making situations in which performance forecasting must be combined with realistic price forecasts. In periods of significant drops in the prices, shutting in wells for extended durations such as 6 months or more may be considered for economic purposes. For example, prices during the early days of the Covid-19 pandemic forced operators to consider shutting in all or some of their active wells. In the case of partial shut-in, selection of candidate wells may evolve as a challenging decision problem considering the uncertainties involved. In this study, a mature oil field with a long (50+ years) production history with 150+ wells is considered. Reservoirs with similar conditions face many challenges related to economic sustainability such as frequent maintenance requirements and low production rates. We aimed to solve this decision-making problem through unsupervised machine learning with the help of the data obtained during production. Average reservoir characteristics at well locations, well performance statistics and well locations are used as potential features that could characterize similarities and differences among wells. After a multivariate data analysis that explored correlations between all parameters, K-means clustering algorithm was used to identify groups of wells that are similar with respect to aforementioned features. Using the field’s reservoir simulation model, scenarios of shutting in different groups of wells were simulated. 3 years of forecasted reservoir performance was used for economic evaluation that assumed an oil price drop to $30/bbl for 6, 12 or 18 months. Results of economic analysis were analyzed to identify which group of wells should have been shut-in by also considering the sensitivity to different price levels. It was observed that well performances can be easily characterized in the 3-cluster case as low, medium and high performance wells. Analyzing the forecasting scenarios showed that shutting in all or high- and medium-performance wells altogether during the downturns results in better economic outcomes. The results were most sensitive to the oil price during the high-price era. This study demonstrated the effectiveness of unsupervised machine learning in well classification, particularly for the problem studied. Operating companies may use this approach for selecting wells for extended durations of shut-in in periods of low oil prices.