Nonparametric Seismic Wave Feature Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting S-waves in seismic data are unreliable due to error propagation from parameter estimation and require manual analysis, making automated detection challenging and inaccurate.
Innovation Solution
A nonparametric time series classification method that uses similarity scoring between seismic data and training data to identify seismic wave features, such as S-waves, without computing intermediate parameters, employing a k-nearest neighbors approach and scaling techniques to improve detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If parameter-based approaches (kurtosis, AIC) are used to detect S-waves, then detection can be automated, but error propagation from parameter estimation reduces reliability
Solution Approach 1:
The patent extracts and removes the intermediate parameter estimation step from the detection pipeline. Instead of using parameter-based methods (kurtosis, AIC) that propagate errors, the system directly compares raw seismic waveforms to training data using similarity metrics, eliminating the source of error propagation while maintaining automation
Solution Approach 2:
The patent uses copying by creating a library of training waveforms representing S-wave features and comparing unknown seismic data against these copies. This direct waveform matching approach replaces parameter estimation with direct pattern recognition, improving reliability while maintaining automated detection
2Reliability
If manual analysis is used to identify S-waves, then detection accuracy can be maintained, but productivity and time efficiency decrease
Solution Approach 1:
The system performs self-service by automatically comparing seismic waveforms against a pre-existing training library without human intervention. The automated waveform similarity comparison processes data at the same accuracy level as manual analysis while achieving much higher productivity and processing speed
3Extent of automation
If parameter estimation is used to build detection models, then automation is achieved, but measurement precision deteriorates due to error propagation
Solution Approach 1:
The patent removes the error-prone parameter estimation intermediate step from the detection process. By directly comparing raw waveforms using similarity metrics rather than estimating parameters first, the system achieves both automation and improved measurement precision for phase arrival time detection
Data Source
AI summary
Systems and methods for automatically detecting and identifying seismic wave features in seismic data are provided. In general, the systems and methods utilize a nonparametric time series classification method to detect seismic wave features that may otherwise be difficult to automatically identify in seismic data. Instead of building a model by estimating parameters from the seismic data, the data itself is used to define a trained model. The systems and methods described here provide the ability to detect and identify seismic wave features with reasonably fast and extremely accurate results without needing to compute parameters.