Double-sparse dictionary learning-based seismic data denoising method
A technique for sparse dictionaries and seismic data, applied in electrical digital data processing, special data processing applications, informatics, etc., can solve problems such as large calculation amount, increased calculation amount, and restricted application, so as to improve accuracy and signal-to-noise ratio , the effect of reducing computational complexity
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0131] Above-mentioned method of the present invention can be summarized as:
[0132] (1) Extract partial gathers from the complete noisy seismic records as training samples.
[0133] (2) Select the DCT dictionary as the base dictionary.
[0134] (3) Batch-OMP algorithm is used to solve the formula for sparse coding.
[0135] (4) Dictionary updating via double sparse dictionary learning.
[0136](5) Judging whether the iteration termination condition is met, if the condition is not met, return to step 3. If so, the iteration terminates and the dictionary is output.
[0137] (6) The complete noisy seismic records are divided into blocks, and each sub-block is sparsely represented according to the learned dictionary.
[0138] (7) Output the denoising result.
[0139] The main technical key points are: ①Batch-OMP algorithm; ②Double dictionary learning algorithm.
[0140] The research of this embodiment is tested with a synthetic single-shot record. The model parameters are...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


