Unsupervised Machine Learning for 3D Seismic Facies Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The extraction and identification of appropriate seismic facies labels for training data in seismic facies classification is expensive in terms of computing resources, and supervised ML models are costly in terms of computing time, while methods like computed self-organizing maps introduce spatial uncertainties in translating two-dimensional maps into 3D seismic volumes.
Innovation Solution
An unsupervised machine learning (USML) approach is used to transform 3D seismic data into a linear representation, allowing for efficient clustering without labeled data, using partition-based models like K-means clustering and Gaussian mixture models, selecting the best model and cluster number through elbow method and silhouette scoring, and resampling back to a 3D grid for accurate seismic facies modeling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If supervised ML models are used for seismic facies classification, then classification accuracy can be improved, but computing resource usage and training time increase significantly
Solution Approach 1:
The system uses unsupervised learning algorithms that automatically discover patterns and cluster seismic data without requiring manual labeling or supervised training. The algorithm self-organizes the data into meaningful facies classes based on intrinsic characteristics, eliminating the need for expensive supervised learning processes while maintaining classification accuracy.
Solution Approach 2:
The invention extracts and utilizes only the essential seismic attributes and their statistical relationships, removing the need for extensive labeled training data and complex supervised models. By focusing on the core clustering problem rather than full supervised learning, the system reduces computing requirements while preserving classification effectiveness.
2Measurement precision
If supervised ML models are trained for seismic facies classification, then classification performance improves, but training time and computing costs increase
Solution Approach 1:
The unsupervised learning algorithm performs self-organization of seismic data into facies classes without requiring time-consuming supervised training processes. The algorithm automatically identifies patterns and relationships in the data, significantly reducing training time while achieving comparable or superior classification performance.
Solution Approach 2:
The system segments the seismic data into distinct facies classes based on inherent characteristics, avoiding the need for extensive training data and time-consuming supervised learning. This segmentation approach allows rapid classification by directly organizing data into meaningful groups rather than learning from labeled examples.
3Productivity
If self-organizing maps are used for seismic facies classification, then computational efficiency improves, but spatial uncertainties are introduced when translating 2D maps to 3D seismic volumes
Solution Approach 1:
The invention transitions from two-dimensional self-organizing maps to three-dimensional clustering directly within the seismic volume framework. By performing clustering in the 3D attribute space rather than mapping to 2D and back, the system maintains spatial accuracy while preserving computational efficiency. The clusters are formed directly in the seismic data space, eliminating translation uncertainties.
Data Source
AI summary
Seismic facies modeling of an area of study at an oil and gas exploration site includes obtaining a seismic dataset. A set of unsupervised machine learning (USML) models processes a test dataset of the seismic dataset. Respective USML models of the set are configured with different cluster numbers. A USML model and corresponding elbow point cluster number is selected from the set of USML models. The selected USML model, configured with the elbow point cluster number, processes the seismic dataset to obtain clusters of the data points. Cluster profiles based on seismic cell attributes of the data points of each cluster are generated. Seismic facies labels are assigned to the clusters based on corresponding cluster profiles. The clusters are sampled to a three-dimensional (3D) grid representation of the area of study to obtain a seismic facies model displayed in a visualization tool of a seismic modeling platform.