Approach towards Establishing Unified Petroleum Data Analytics Environment to Enable Data Driven Operations Decisions

Abstract

Exploration and Production companies are increasingly instrumenting their fields with the objective to proactively monitor and surveillance of its wells, reservoir, and facilities for safe and better operations. With this scenario, there is ever increase in the volume and variety of data being generated to support workflows such as real time drilling operations, production surveillance and reservoir monitoring. Data Analytics enables to get most value out of the vast volume of data being generated. In order to extend the present limits of digital oil field envelope from operations monitoring, companies need to harness data analytics to identify patterns, trends, correlation, forecasting out of its vast petroleum data. This includes exception based surveillance, case based reasoning, and condition based monitoring in order to facilitate advanced monitoring, and to support tactical and strategic decision-making process. To establish data analytics environment it requires systematic way of capturing, storing and managing data, integrating and embedding data analytics into the mainstream sub-surface, drilling, production and operations workflows which includes integrated reservoir monitoring, drilling and production optimization. Data analytics technology blends traditional data analysis with sophisticated algorithms and business rules for processing large volumes of diverse types through an Integrated Data Analytics Environment (IDE). Data governance is a vital part of IDE to ensure there is clear ownership and responsibilities as the accuracy of the results are as good as the quality of the data. IDE environment enables systematic harvesting of operational event, lessons learnt and best practices to enable knowledge based operations decisions. The integrated data analytics platform enables integrating E&P workflows and data analytics to enhance operations monitoring, predict well productivity, identify performance patterns and KPI, improve reservoir recovery factor, and predict equipment failure, towards achieving the objective of continuous optimization of oilfield performance.

Drilling data quality improvement and information extraction with case studies

“…It is important to identify, select and use right data with respect to predefined objectives or scenarios. • Data quality The issues related to systematic/random/ gross errors due to sensors failure, malfunction, incorrect calibration, user entry errors, sampling frequencies, corruptions and so on are often met, see the discussions in Bello et al (2017); Dickson (2014); Temer and Pehl (2017); David (2016); Nybo et al (2012). High quality is desired to provide valuable and useful information.…”