Reservoir Well Targeting With Opportunity Index Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current well target identification in reservoir simulation models is labor-intensive, time-consuming, and lacks efficient knowledge transfer, making it difficult to share expert expertise when experts leave an organization.
Innovation Solution
An automated system and method for identifying potential well targets using expert knowledge capture and machine learning algorithms to generate opportunity indexes and classify reservoir sections based on embedding spaces, enabling faster and more comprehensive well target identification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated machine learning algorithms are used to identify well targets, then productivity and speed are improved, but device complexity increases
Solution Approach 1:
The patent introduces an automated machine learning system as an intermediary between geological data and well target identification decisions. This system processes reservoir simulation models, generates opportunity indexes, and classifies reservoir sections automatically, replacing manual expert analysis while managing complexity through standardized algorithms and embedding spaces.
2Reliability
If expert knowledge is captured and automated, then knowledge transfer and reliability are improved, but device complexity increases
Solution Approach 1:
The patent captures expert knowledge by creating computational copies of expert decision-making processes. Machine learning models are trained on expert-identified well targets and reservoir characteristics, reproducing expert reasoning patterns in an automated system. This allows knowledge to be transferred and applied consistently across multiple realizations without depending on individual experts.
3Manufacturing precision
If manual expert analysis is used for well target identification, then manufacturing precision is maintained, but loss of time increases
Solution Approach 1:
The patent performs preliminary actions by pre-processing reservoir simulation models and pre-computing embedding spaces for reservoir sections before actual well target identification is needed. Opportunity indexes are generated in advance based on reservoir properties, so that when well targets need to be identified, the system can quickly query and classify pre-computed data rather than analyzing raw simulation data from scratch.
Data Source
AI summary
A system and method are provided for identifying a wellsite target for drilling, including receiving a plurality of data regarding a wellsite, generating a distribution of reservoir properties using the plurality of data for an area of a reservoir defined within the wellsite, determining at least one opportunity index for an area in the reservoir based on at least one of the corresponding reservoir properties, classifying a section of the reservoir based on at least one computed embedding space, wherein the at least one computed embedding space of the section is based on the at least one opportunity index.