In this paper, we propose an alternative approach to the problem of oil-production forecast based on the most straightforward feature-based machine-learning algorithm: the linear model. The method can be successfully applied to forecast both oil-rate and liquid-rate in oil fields under (i) water injection, (ii) gas injection, and (iii) simultaneous water and steam injection. Our data-driven algorithm learns the underlying reservoir dynamics from 3 sets of time-series, namely, (i) injection-rate, (ii) liquid and oil-rate, and (iii) number of producers. That is all the data we need to make reliable forecasts, no geological model or numerical reservoir simulators were used.

Keywords:
forecast, artificial intelligence, injection, model deliver accurate oil-rate forecast, prediction, production forecast, upstream oil & gas, steam injection, production control, reservoir surveillance
Subjects:
Well & Reservoir Surveillance and Monitoring, Information Management and Systems, Production logging, Artificial intelligence
This content is only available via PDF.
2019. Offshore Technology Conference
You can access this article if you purchase or spend a download.