Borehole Texture Modeling Through Segmentation and Feature Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Interpreting borehole images to identify and classify texture features is difficult and inefficient in terms of time and computing resources, which hinders depositional environment analysis and reservoir characterization.
Innovation Solution
A method involving segmentation of borehole images into zones based on pixel and covariance data, merging these zones, and clustering features using a classification algorithm to generate a borehole texture model, which is trained using petrophysical logs for efficient rock property classification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual interpretation of borehole images is used to identify and classify texture features, then measurement precision can be achieved, but loss of time and computing resources increases significantly
Solution Approach 1:
The patent replaces manual mechanical interpretation with an automated machine learning-based system. The classification algorithm automatically analyzes borehole images, segments them into zones based on pixel data and covariance data, and clusters features to identify texture types, eliminating the need for manual visual inspection while maintaining or improving classification accuracy.
Solution Approach 2:
The system creates a digital copy of the borehole image and processes this copy through segmentation and clustering algorithms. By working with a digital replica rather than the original physical image, the system can perform repeated analyses, store results, and process multiple images efficiently without the time constraints of manual review.
2Measurement precision
If comprehensive texture analysis is performed on borehole images, then measurement precision improves, but device complexity and computing resources increase
Solution Approach 1:
The patent divides the borehole image into multiple zones based on pixel data and covariance data, then further segments these zones into clusters representing different texture types. This segmentation approach allows the system to process complex images by breaking them down into manageable units, reducing the computational burden while maintaining comprehensive analysis.
Solution Approach 2:
The system applies different analysis methods to different zones of the borehole image based on their local characteristics. By identifying regions with similar pixel patterns and covariance properties, the system can optimize processing for each local area, using appropriate algorithms for each texture type rather than applying a uniform complex analysis to the entire image.
Data Source
AI summary
A method may include segmenting a borehole image of a first well into a first plurality of zones based on pixel data, segmenting the borehole image of the first well into a second plurality of zones based on covariance data, merging the first plurality of zones and the second plurality of zones to generate an updated borehole image, clustering one or more sets of features of the updated borehole image into one or more clusters based on a classification algorithm, and generating a borehole texture model representative of expected properties of an additional borehole based on the one or more clusters.