Data-Driven Analytics for Oil and Gas Reservoir Production Forecasting
Date
2018-10
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Detailed uncertainty analysis on numerical flow simulation models preserving a robust and reliable model of oil and gas reservoir is often deterministic, cumbersome and expensive (manpower and time consuming). Presence of a high-dimensional data space consisting of a large number of operational and geological parameters impedes practical decision making and future performance prediction of oil and gas recovery processes. Thus, the rise of uncertainty-based reservoir development scenarios has provoked reservoir engineers to look for substitute modeling techniques that are capable of being re-evaluated numerous times to examine the impact of specific variables or probing a range of scenarios on production profiles. Static (well logs and core analyses) and dynamic (injection and production history) data sets existing within oil and gas companies are extremely valuable sources of information which can aid operators for a better future field development planning. Petroleum data-driven analytics workflow, which integrates a comprehensive petroleum data analysis and machine learning methods, suggest an attractive alternate for explicit models of the underlying process that can be instantaneously reassessed. The current study incorporates a systematic data analysis alongside with numerical flow simulations to create a comprehensive data set for different recovery processes such as SAGD, waterflooding, ploymerflooding, and etc. It also entails different characteristics labeling reservoir heterogeneities and key pertinent oil and gas recovery operational constraints. The collected big-data set will then be used to design data-driven models which can forecast production performance of different oil and gas recovery processes. This dissertation has developed and implemented algorithms for the development of novel data-driven models for CMG-CMOST AI 2017.10 version within Proxy Dashboard. This is the unique contribution of this thesis. The presented results and performance characteristics associated with data-driven models which can be re-evaluated much faster than explicit models of the underlying process highlight the great potential of this modeling approach to be integrated directly into most existing reservoir management routines. This research provides a viable tool to overcome challenges related to dynamic assessment of uncertainties during history matching of recovery processes and signifies the ability of data-driven analytics in future performance prediction of various oil and gas reservoirs.
Description
Keywords
Data-Driven, Data-Driven Analytics, Oil and Gas Reservoir, Production Forecasting
Citation
Amirian, E. (2018). Data-Driven Analytics for Oil and Gas Reservoir Production Forecasting (Doctoral thesis, University of Calgary, Calgary, Canada). Retrieved from https://prism.ucalgary.ca. doi:10.11575/PRISM/33217