Well-Log Clustering Using Representative Segments for Faster Interpretation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Well-log interpretation is time-consuming and subjective due to manual processing of large data sets, leading to inconsistent results and impractically long runtime in clustering processes.
Innovation Solution
A method and computing system that automates well-log interpretation by partitioning data into segments, simplifying to representative points, determining reachability distances, and initializing clusters using density-based clustering algorithms like OPTICS, reducing runtime from O(n^2) to O(n log n.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual interpretation of well logs is performed by human interpreters, then subjectivity and inconsistency in interpretation occur, but the process remains flexible and adaptable to complex geological scenarios
Solution Approach 1:
The patent replaces the manual mechanical interpretation process with an automated computer-based system that uses clustering algorithms to analyze well log data. The system automatically segments logs into electrofacies based on numerical analysis of multiple parameters simultaneously, eliminating human subjectivity and inconsistency while maintaining interpretive capability through algorithmic pattern recognition.
Solution Approach 2:
The system enables the well log data to self-organize into meaningful electrofacies groups through unsupervised clustering algorithms. The data automatically segments itself based on inherent patterns in the log measurements without requiring manual intervention, allowing the system to serve itself in the interpretation process while reducing human workload to validation and parameter tuning.
2Measurement precision
If traditional clustering algorithms are used on large well log data sets, then comprehensive analysis is achieved, but runtime becomes impractically long (weeks or more)
Solution Approach 1:
The patent divides the large well log data set into smaller, manageable segments or intervals based on depth or other criteria. Each segment is processed independently through the clustering algorithm, reducing the computational burden on any single processing step while maintaining overall analysis accuracy. The results are then integrated to form the complete electrofacies interpretation.
Solution Approach 2:
The system performs preliminary data processing and preprocessing steps before applying the main clustering algorithm. This includes data normalization, outlier detection, and initial segmentation that prepares the data in advance, reducing the complexity of the subsequent clustering operation and significantly decreasing overall processing time while preserving analytical accuracy.
Data Source
Figure 1A~1D
Figure 2
Figure 3
AI summary
Computing systems, computer-readable media, and methods interpreting well logs, of which the method includes receiving data that comprises one or more well logs acquired using a tool disposed at a plurality of depths423 in a bore in a subterranean environment, partitioning the data into segments, the individual segments containing data points, representing the segments as representative points in a parameter domain, determining reachability distances for the representative points in the parameter domain, initializing a cluster based on the reachability distances, identifying one or more segments as part of the cluster, and determining a physical feature represented in the one or more well logs based on the cluster.