Stratum Surface Correlation via Dynamic Time Warping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual correlation of stratum surfaces across multiple well logs is time-consuming, subjective, and prone to errors, while software-based correlation may not always match manual accuracy, leading to deviations and inaccuracies in geological interpretation.
Innovation Solution
A computing device analyzes well logs to identify and correlate stratum surfaces, allowing for user-input corrections to update stratum-surface correlations, using dynamic time warping and error matrix analysis to recalibrate correlations based on manual inputs, ensuring interdependency of stratum surfaces is accounted for.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual correlation of stratum surfaces is performed, then accuracy of geological interpretation is improved, but processing time and labor intensity increase
Solution Approach 1:
The patent segments the correlation process into two distinct phases: (1) an automated initial correlation phase that quickly processes well logs to establish preliminary stratum surface correlations, and (2) a manual refinement phase where experts review and correct specific correlations. This segmentation allows the system to benefit from both the speed of automation and the accuracy of manual expertise, resolving the contradiction between processing time and correlation accuracy.
Solution Approach 2:
The system performs self-correction by automatically adjusting correlations based on detected inconsistencies and expert feedback. The automated system initially performs the correlation work, then uses manual corrections as training data to improve future automated correlations, reducing the need for extensive manual review while maintaining high accuracy over time.
2Productivity
If software-based correlation is used, then processing speed is improved, but accuracy and reliability decrease due to deviations from manual interpretation
Solution Approach 1:
The patent implements a feedback mechanism where expert manual corrections are fed back into the automated correlation system. The system learns from these corrections and continuously improves its algorithms, allowing it to maintain high processing speeds while progressively achieving accuracy that matches or exceeds manual interpretation quality.
Solution Approach 2:
The automated system performs preliminary correlation actions before manual review, establishing a first-pass interpretation that captures the majority of correlations correctly. This preliminary action filters out the bulk of work, leaving only minor refinements for manual experts, thus maintaining both speed and accuracy.
3Reliability
If comprehensive manual review of all well logs is performed, then correlation accuracy is improved, but device complexity and operational difficulty increase
Solution Approach 1:
Instead of requiring comprehensive manual review of all well logs, the system applies partial manual action only where needed. The automated system handles the majority of correlations, and manual experts intervene only for specific cases requiring refinement or validation, significantly reducing operational complexity while maintaining reliability.
Data Source
AI summary
Strata surfaces can be identified in well logs and correlated across the well logs taking into account manual corrections. For example, a computing device can receive well logs. The computing device can determine multiple stratum-surface correlations based on the well logs. Then, the computing device can receive user input indicating a correction to a particular stratum-surface correlation. Based on the correction to the particular stratum-surface correlation, the computing device can update some or all of the other stratum-surface correlations.