Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Seismic Noise Suppression Method Based on Unequilibrium Depth Desired Block Log-Likelihood Network

A log-likelihood, noise suppression technology, applied in neural learning methods, biological neural network models, image data processing, etc., to avoid errors, improve block denoising effect, and improve denoising strength.

Active Publication Date: 2022-05-27
JILIN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Solving the Desert Noise Suppression Problem with Unequalized Deep Desired Block Log-Likelihood Networks

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Seismic Noise Suppression Method Based on Unequilibrium Depth Desired Block Log-Likelihood Network
  • Seismic Noise Suppression Method Based on Unequilibrium Depth Desired Block Log-Likelihood Network
  • Seismic Noise Suppression Method Based on Unequilibrium Depth Desired Block Log-Likelihood Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0069] 1. Working conditions

[0070] The experimental platform of the present invention adopts Intel(R) Core(TM) i5-7500 CPU@3.40GHz 3.40GHz, the memory is 8GB, the PC runs Windows 7, and the language is python language. The running environment is python==3.7, torch==1.0.1, scipy==1.3.1 and matplotlib.

[0071] 2. Experiment content and result analysis

[0072] The experimental effect of the present invention will be described below through experiments on synthetic data and field actual data:

[0073] like figure 2 As shown in the figure, 100 channels of synthetic clean seismic data contain 4 signal axes, which are respectively generated by rake wavelets with dominant frequencies of [19Hz, 18Hz, 17Hz and 16Hz]. The synthetic desert random noise is as follows: image 3 shown. Figure 4 for the image 3 take part in figure 2 The desert seismic data polluted by desert noise obtained in , the signal-to-noise ratio is -4dB. In this example, the denoising results of the me...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The seismic noise suppression method based on the unbalanced depth expected block log-likelihood network belongs to the field of machine learning and seismic image processing technology. The regularization term parameter in the expected block log-likelihood algorithm only changes with the variance of the overall noise, so that the strong noise cannot be completely suppressed. problem, the present invention proposes a seismic noise suppression method based on an unbalanced depth expected block log likelihood network, in which the end-to-end denoising network consists of an expected block log likelihood denoising main network and an unbalanced multi-layer The perceptron parameter estimation network is composed of noise-containing seismic images as the input and clean seismic images as the output to learn network parameters, and for the first time adopts unbalanced block signal-to-noise ratios to adjust multi-layer perceptrons to estimate network parameters. The invention can realize the Each block in the seismic image estimates accurate regularization parameters, better controls the denoising intensity of each block, and then improves the block denoising effect, and is superior to traditional seismic denoising in suppressing strong noise in the desert and maintaining signal details algorithm.

Description

technical field [0001] The invention belongs to the technical field of machine learning and seismic image processing, and in particular relates to a seismic noise suppression method based on an unbalanced depth expected block log-likelihood network. Background technique [0002] The exploration of oil, natural gas and other resources has been an enduring hotspot. Seismic exploration is currently the main means of exploration and exploitation of underground energy such as oil and gas. However, affected by the environment of seismic exploration areas, the collected seismic images are often mixed with a large amount of random noise. These noises seriously damage the effective signals and increase the difficulty of extracting reflected seismic signals. Therefore, the suppression of seismic random noise is the fundamental problem in seismic data processing to improve seismic quality and extract underground structure information from noise-disturbed signals. In recent years, my c...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T5/00G06N3/08
CPCG06T5/002G06N3/08G06T2207/20081G06T2207/20084
Inventor 林红波马阳叶文海
Owner JILIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products