Dilation Module for Seismic Fault Characterization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current models for hydrocarbon exploration lack the accuracy and resolution to effectively identify and characterize subterranean faults, often misidentifying features or failing to detect faults in geological areas of interest, which can lead to incorrect hydrocarbon resource location and extraction strategies.
Innovation Solution
A deep learning neural network with a dilation module is employed, utilizing dilated convolution layers with varying dilation rates to analyze seismic data and attributes, enhancing feature identification and providing more accurate fault probability outputs, thereby improving the resolution and accuracy of fault characterization in subterranean formations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional models are used for fault identification, then the model complexity is low, but the measurement precision and reliability of fault location are insufficient
Solution Approach 1:
The model segments the feature extraction process into multiple parallel convolutional pathways, each with different dilation rates (1, 2, 4, 8, 16), allowing simultaneous analysis of fault features at multiple scales without increasing overall model complexity
Solution Approach 2:
The patent introduces a new dimension (dilation rate) to the convolutional operation, transforming the traditional single-scale feature extraction into multi-scale analysis by varying the receptive field size across different parallel channels
2Productivity
If conventional models are used, then the computational resources required are low, but the productivity and accuracy of hydrocarbon exploration are reduced
Solution Approach 1:
The model applies partial action by selectively processing seismic data through multiple parallel convolutional pathways only when fault features are present, rather than applying full processing to all data, thus improving exploration accuracy while controlling computational resource usage
3Reliability
If conventional models are used, then the ease of operation is maintained, but the reliability of fault identification is insufficient due to misidentification of features
Solution Approach 1:
The pooling layer acts as an intermediary that aggregates features from multiple parallel convolutional pathways with different dilation rates, combining multi-scale fault features into a unified representation that improves identification reliability while maintaining operational simplicity
Data Source
AI summary
A system can receive seismic data that can correlate to a subterranean formation. The system can derive a set of seismic attributes from the seismic data. The seismic attributes can include discontinuity-along-dip. The system can determine parameterized results by analyzing the seismic data and the seismic attributes using a deep learning neural network. The deep learning neural network can include a dilation module. The system can determine one or more fault probabilities of the subterranean formation using the parameterized results. The system can output the fault probabilities for use in a hydrocarbon exploration operation.