A generative well-pattern-design (GWPD) work flow was benchmarked against traditional manual designs to leverage three reservoir-development planning opportunities applicable to a giant mature Middle Eastern carbonate field. People remained central in ensuring efficient problem setup and exploration guidance, but the work flow proved able to identify substantially better patterns than the traditional approach for each of the opportunities at the cost of only a few hundred simulations.
GWPD Overview
The work flow used to tackle the different problems of this study, which the authors call the GWPD “well-improvement scheme” (WISH), consists of the following steps. Each step is detailed in the complete paper.
- Definition of design space
- Constraint of design space
- Qualification of design space
- Nondominated sorting (a specific ranking of all of the cells of the constrained design space according to the value of their quality indicators
- Candidate design investigation
- Investigation of preferred designs
- Optimization of preferred design
GWPD Application
Context. The application study was conducted at the beginning of the industrialization of WISH, a proprietary software tool dedicated to GWPD. The authors call the work flow GWPD-WISH.
In the studied oil field, more than 400 oil producers and water- or gas-injector strings have been drilled from approximately 100 platforms in a series of reservoirs.
