A Horizontal Tracking Method of Seismic Image Based on Signal Classification

Abstract

The invention discloses a seismic image layer tracking method based on signal classification. Without manual intervention, the FSSCEM algorithm is used to optimize the selection and clustering of the obtained characteristic parameters, and the dip texture attribute is combined with the correlation search method to apply The follow-up processing after clustering realizes the full horizon tracking on the 2D section, and then combines the semi-supervised classification method, dip pointing and correlation-based horizon tracking algorithm to realize the precise tracking of the horizon surface in the 3D seismic image . The method of the invention does not require a large amount of manual intervention; while reducing the calculation amount of the clustering algorithm, the reliability of the clustering is guaranteed; and the continuity of horizon identification is enhanced.

Description

technical field [0001] The invention relates to the field of seismic image processing, in particular to a method for layer tracking of seismic images based on signal classification. Background technique [0002] With the development of the economy, the social demand for oil, natural gas and other resources is increasing. However, to exploit oil and gas, the underground geological structure must first be clear, so seismic interpretation plays an important role in the process of geological exploration. Seismic horizon tracing plays a very important role in seismic interpretation. By means of seismic horizon tracing, strata that may contain oil and gas and the storage depth of oil and gas can be found. [0003] Since the event in the seismic image is a mapping of the geological horizons in the actual geological structure of the exploration area, seismic horizon tracking can be realized by tracking the event in the seismic image. In the process of downward propagation, due to t...

AI Technical Summary

Problems solved by technology

Moreover, the acquisition of training samples requires a lot of manual intervention

[0007] (3) Genetic Algorithm Level Tracking Algorithm: The specific idea is to use a model-based method to deal with the problem of crossing faults, and then convert the problem into a constrained optimization problem, and then use the genetic algorithm to solve it. There are two methods in this method: Problems: One is the degree of approximation to complex geological conditions; the other is the problem of solution accuracy and suboptimal solutions

[0008] (4) The full horizon tracking algorithm based on finite mixture Gaussian is suitable for complex geological environments, but requires manual intervention and cannot fully realize the automatic extraction and separation of horizons

Images