Moving-Window Subsurface Analysis Without Pre-Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional subsurface data analysis requires time-consuming and subjective segmentation of unsegmented continuous data, making it difficult to characterize subsurface regions effectively.
Innovation Solution
A system and method that utilizes moving windows to analyze unsegmented continuous data without pre-segmentation, determining probabilities of subsurface features by scanning with multiple moving windows of varying sizes and applying classifiers for pattern matching and statistical analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional segmentation methods are used to analyze subsurface data, then the analysis can be performed with traditional methods, but the process becomes time-consuming and subjective
Solution Approach 1:
The patent applies segmentation by dividing the continuous subsurface data into multiple segments along the trace direction and across different traces. This segmentation enables parallel processing of data blocks, significantly improving analysis efficiency while maintaining objective classification through systematic division of the workload across multiple processing units
Solution Approach 2:
The patent implements dynamic parallel processing where multiple processing units simultaneously analyze different segments of the subsurface data. The system dynamically distributes computational tasks across available processors, adapting to data size and computational requirements to optimize analysis speed and reduce processing time
2Ease of operation
If manual segmentation is performed on subsurface data, then the data can be analyzed, but the process becomes subjective and difficult
Solution Approach 1:
The system performs self-service through automated classification algorithms that objectively analyze subsurface data without requiring manual intervention. The processing units automatically segment, analyze, and classify data based on predetermined criteria, eliminating subjectivity while managing complexity through systematic automation rather than manual operations
3Productivity
If pre-segmentation of subsurface data is performed, then traditional analysis methods can be applied, but the need for pre-segmentation adds complexity and time
Solution Approach 1:
The patent merges the segmentation and analysis operations into a unified parallel processing framework. Rather than performing pre-segmentation as a separate preparatory step, the system integrates segmentation with the classification process, allowing multiple processing units to simultaneously segment and analyze different data portions, thereby reducing overall complexity and improving throughput
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Unsegmented continuous subsurface data may be analyzed using one or more moving windows to characterize a subsurface region. Unsegmented continuous subsurface data may be scanned using the moving window(s). Probabilities that portions of the subsurface region include a subsurface feature may be determined based on analysis of the portions of the unsegmented continuous subsurface data within the moving window(s).