Harness Oil and Gas Big Data with Analytics: Optimize Exploration and Production with Data Driven Models

Chapter 2Data Management

One of the most critical design and architecture decisions adopters of advanced analytics must make is whether to store analytic data in a data warehouse or in a standalone analytic database. Where does the data go? Where is it managed? Where are we going to do our analytical processes?

Philip Russom, Senior Manager, TDWI Research

The integration of disparate data types across siloed upstream engineering disciplines is gaining momentum owing to the demand for accurate predictions and effective field engineering strategies that can address critical business issues across the exploration and production (E&P) value chain. Where the interpretation of a single data type is sufficient to provide insight into variations hidden in a limited set of physical properties or combinations thereof, a multivariate perspective enabled by integration of different data types will have potential for more robust estimates and more astute discrimination of different physical effects.

The oil and gas industry is collecting massive amounts of sensor data from operations spanning exploration, drilling, and production. The velocity and complexity of data growth has put immense strain on application and database performance. This rapid growth necessitates a fundamental change to the way data are collected, stored, analyzed, and accessed to support real-time intelligence and condensed decision-making cycles.

Oil and gas operators are faced with a daunting challenge as they strive ...