CNN Seismic Volume Segmentation for Subsurface Structure Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Interpretation of large seismic volumes is a daunting task, especially when performed manually, and the increasing amount of seismic data collected necessitates automated systems to reduce time and expense associated with seismic interpretation.
Innovation Solution
A system utilizing a convolutional neural network to automate geo-body segmentation in seismic data, specifically trained to identify subsurface structures like channel and salt geo-bodies, by processing three-dimensional seismic volumes and generating probability maps for accurate structure identification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual seismic interpretation is performed, then accuracy of structure identification can be maintained through expert analysis, but time consumption and cost increase significantly
Solution Approach 1:
The patent replaces manual mechanical interpretation processes with an automated computer-based system using machine learning algorithms. The system processes seismic data through trained models that automatically identify subsurface structures, replacing the need for manual expert analysis while maintaining identification accuracy and reducing time consumption by a factor of 1000 or more.
2Productivity
If automated seismic interpretation systems are implemented, then time and cost are reduced, but system complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-training machine learning models with labeled seismic data before deployment. The system performs offline training to establish patterns and relationships in the data, creating a ready-to-use model that can rapidly process new seismic volumes without requiring complex real-time computation, thus reducing operational complexity while maintaining high productivity.
3Device complexity
If conventional manual interpretation methods are used, then system complexity remains low, but productivity decreases due to time-consuming analysis
Solution Approach 1:
The patent uses copying by creating digital replicas of seismic data in the form of three-dimensional volumes and probability maps. The system generates multiple copies of processed data at different probability thresholds, allowing rapid analysis and interpretation without increasing physical system complexity. This digital copying approach enables high productivity through efficient data manipulation and visualization.
Data Source
AI summary
A subsurface structure identification system includes one or more processors and a memory coupled to the one or more processors. The memory is encoded with instructions that when executed by the one or more processors cause the one or more processors to provide a convolutional neural network trained to identify a subsurface structure in an input migrated seismic volume, and to partition the input migrated seismic volume into multi-dimensional sub-volumes of seismic data. The instructions also cause the one or more processors to process each of the multi-dimensional sub-volumes of seismic data in the convolutional neural network, and identify the subsurface structure in the input migrated seismic volume based on a probability map of the input migrated seismic volume generated by the convolutional neural network.