Automated Well Monitoring: From Data Pre-processing to Well Performance Profile

Automated well operations is a rapidly growing area with recent progress in automated drilling extending now into automated well monitoring and control during production operations. In reservoir engineering, although the industry continues to guide decision making processes mainly based on physics-based models and simulations, the focus of further developments of the industrial workflows has shifted towards hybrid solutions incorporating machine learning and big data analytics. Development of such solutions requires new approaches to integrate the reservoir physics into the workflows suitable for machine learning and big data analytics.

We present one of such hybrid solutions focused on well monitoring using pressure and rate measurements with permanent gauges and flowmeters. Data-driven methods employed for data preprocessing like automated pressure transient identification and recognition of patterns in time-lapse pressure responses are combined with physics-informed methods used to evaluate well performance. Application of this hybrid workflow is illustrated with well examples from the Norwegian Continental Shelf. Potential application areas of this automated workflow include analysis of big well datasets already accumulated in the industry, on-the-fly data interpretation with real-time alarming of performance issues as well as providing input data for full-field reservoir simulations.