Graphical Model for Seismic Hydrocarbon Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The interpretation and analysis of large three-dimensional seismic data sets are time-consuming and labor-intensive, requiring months of manual work for geologists to identify hydrocarbon formations, and existing automated systems are unreliable due to variance in geological object shapes and characteristics.
Innovation Solution
A method using a graphical model with predefined rules to preprocess, process, and post-process seismic data, identifying and ranking clusters that satisfy these rules, thereby automating the identification of bounded hydrocarbon formations and reducing analysis time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analysis methods are used by geologists, then identification accuracy can be maintained through expert judgment, but the analysis time becomes excessively long (months required)
Solution Approach 1:
The patent replaces manual mechanical analysis by geologists with an automated computer-based system using machine learning algorithms and graphical models. The system processes seismic data through pre-processing, graphical model evaluation with domain-specific rules, and post-processing to identify bounded hydrocarbon formations automatically, eliminating the time-consuming manual review while maintaining expert-level accuracy through trained algorithms
Solution Approach 2:
The patent transforms the analysis approach by changing from manual expert judgment to automated algorithmic evaluation using graphical models with probabilistic inference. The system evaluates multiple seismic attributes simultaneously through defined rules and relationships, scoring and ranking potential hydrocarbon formations based on computed probabilities rather than manual assessment
2Loss of time
If existing automated systems are used, then analysis time is reduced, but reliability deteriorates due to inability to handle variance in geological object shapes and characteristics
Solution Approach 1:
The patent implements a dynamic and flexible graphical model framework that can adapt to varying geological object shapes and characteristics. The system uses probabilistic graphical models with domain-specific rules that evaluate multiple seismic attributes and their relationships, allowing the analysis to dynamically adjust to different formation geometries and properties while maintaining consistent evaluation criteria
Solution Approach 2:
The patent segments the complex analysis into distinct phases: pre-processing of seismic data, evaluation through graphical models with specific rules for different geological features, and post-processing of results. This segmentation allows specialized handling of different geological object types and shapes through domain-specific rules while maintaining overall system reliability
3Measurement precision
If comprehensive seismic data analysis is performed to ensure accurate identification, then the quality of results improves, but the complexity of the process increases
Solution Approach 1:
The patent divides the complex analysis process into three manageable segments: pre-processing (data preparation and attribute calculation), graphical model evaluation (rule-based assessment of seismic attributes and their relationships), and post-processing (result interpretation and ranking). This segmentation reduces perceived complexity while maintaining comprehensive analysis through structured progression through each phase
Solution Approach 2:
The patent introduces graphical models with domain-specific rules as an intermediary layer between raw seismic data and final interpretation. These models serve as mediators that systematically evaluate multiple attributes and their relationships, providing a structured framework that manages complexity while ensuring comprehensive and accurate identification of bounded hydrocarbon formations
Data Source
AI summary
A method of identifying bounded hydrocarbon formations of interest in a seismic data set includes obtaining a seismic data set, pre-processing the seismic data set, inputting the plurality of graphical model inputs and one or more rules to a graphical model, wherein the rules define a relationship between a plurality of attributes of a bounded hydrocarbon formation, running a graphical model on the graphical model inputs, post-processing the graphical model outputs, and displaying the ranked clusters in order of rank.