Desert seismic signal denoising method based on VMD approximate entropy and multi-layer perceptron

Abstract

The invention relates to a desert seismic signal denoising method based on the VMD approximate entropy and a multi-layer perceptron and belongs to the field of geophysical technology. The two-dimensional desert seismic record is subjected to variational mode decomposition to obtain a series of eigenmode components, the approximate entropy of each eigenmode component is calculated, all the eigenmode components are respectively divided into an effective signal dominant component and a noise dominant component, a characteristic quantity is constructed through effective signal correlation, the characteristic quantity is inputted into the multi-layer perceptron for classification, the valid signal portion determined by the multi-layer perceptron classifier is reserved, the noise portion determined by the multi-layer perceptron classifier is removed, the noise dominant component is denoised through combining an autocorrelation coefficient with tzhe multi-layer perceptron, and lastly, desertseismic signal denoising is realized through reconstruction. The desert seismic signal denoising method is advantaged in that noise removal under strong noise and low signal to noise ratio conditionsis achieved, the desert seismic signal denoising method has fast speed, high accuracy and strong anti-interference ability, and denoising of desert seismic signals under low frequency and low SNR canbe realized.

Description

technical field [0001] The invention belongs to the technical field of geophysics, in particular to a method for denoising desert seismic signals. Background technique [0002] Seismic exploration is a major method of oil and gas exploration and the main means for people to obtain geological information. Seismic exploration uses seismic waves to have different reflection, scattering and transmission in different geology to explore the underground situation. In recent years, the demand for oil and gas resources has been increasing, and the resources that are easy to exploit and explore have been decreasing, thus putting forward higher requirements for the quality of seismic data. Desert area is one of the main seismic exploration sites at present, so noise suppression in desert area is an important topic that needs to be studied by us. The complexity and randomness of random noise in seismic exploration in my country's desert areas have brought great difficulties to the pro...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a desert seismic signal denoising method based on VMD approximate entropy and multi-layer perceptron to solve the inaccurate desert noise denoising under extremely low signal-to-noise ratio, and desert noise overlaps with effective signals at low frequencies, resulting in The problem of difficult signal-to-noise separation

Images