Fast seismic waveform classification method based on semi-supervised algorithm

Abstract

The invention discloses a fast seismic waveform classification method based on a semi-supervised algorithm, which comprises the following steps: S1, getting seismic waveform data along the horizon, and reducing the dimensionality of the seismic waveform data through an SSDR algorithm based on linear transform; S2, using tag data in the seismic waveform data to train a distance measurement matrix; and S3, using a semi-supervised K-means classification algorithm to classify the seismic waveform data, and generating a seismic phase diagram. As original seismic waveform data is processed through a semi-supervised dimensionality reduction method, the similarity between similar waveform data is increased while redundant data is eliminated, the difference between different categories is enhanced, and the classification result is more accurate. A suitable distance measurement matrix is trained using existing logging data, and the distance measurement method is introduced to the subsequent classification method. Then, a weighted semi-supervised K-means classification method is put forward. Logging data is fully utilized. The classification accuracy is improved, and the classification rate is increased.

Description

technical field [0001] The invention belongs to the technical field of seismic data analysis, in particular to a fast seismic waveform classification method based on a semi-supervised algorithm. Background technique [0002] Energy is an indispensable material basis and important guarantee for economic development and social progress. In recent years, the economy has become more and more dependent on energy, and the demand for energy has continued to grow. In order to maintain a stable supply of energy, the oil and gas industry needs to continuously improve the technology of oil and gas reservoir exploration. During the exploration of subtle oil and gas reservoirs, it is very important to use the rich information contained in seismic data to identify sedimentary facies belts for the prediction of subtle oil and gas reservoirs. In the petroleum industry, the method of identifying sedimentary facies using seismic data is called seismic facies identification. The traditional ...

AI Technical Summary

Problems solved by technology

The commonly used dimensionality reduction algorithms PCA and LLE are both unsupervised dimensionality reduction. While reducing redundant seismic waveform data, they can also suppress some noise in seismic waveforms, but usually also make seismic waveforms of different seismic phases very different. are similar, and are finally classified into the same category during the classification process, resulting in inaccurate classification results

[0005] The existing seismic waveform classification methods are all unsupervised classification methods, these methods are driven by the data itself, without taking into account the prior knowledge of drilling, logging, geology, etc., and cannot be combined with the actual logging results

Images