Seismic elastic impedance low-frequency information extraction method and system and storage medium

Abstract

The invention discloses a seismic elastic impedance low-frequency information extraction method and system, and a storage medium. The method comprises the following steps: obtaining seismic data and actually measured elastic impedance data; inverting elastic impedance data through a neural network according to the seismic data; forward modeling seismic data are generated according to the elastic impedance data, and a seismic data loss value is obtained; obtaining a loss value of the elastic impedance according to the elastic impedance data and the actually measured elastic impedance data; obtaining a minimum total loss value and a low-frequency curve according to the seismic data loss value and the loss value of the elastic impedance; performing seismic inversion and reservoir prediction based on the minimum total loss value and the low-frequency curve; according to the scheme, the neural network method is introduced for seismic low-frequency information extraction, the extracted low-frequency characteristics are good, the calculation efficiency is high, the reservoir prediction precision can be remarkably improved, the exploration risk is reduced, and the method can be widely applied to the technical field of geophysical exploration.

Description

technical field [0001] The invention relates to the technical field of geophysical exploration, in particular to a method, system and storage medium for extracting seismic elastic impedance low-frequency information. Background technique [0002] With the development of seismic exploration technology, the geological problems faced by oil and gas exploration are becoming more and more complex, and the requirements for seismic data processing and interpretation are getting higher and higher. Fine description of reservoirs is one of the goals pursued by geophysicists. Low-frequency information plays an important role in the inversion process of converting seismic data into P-wave impedance and elastic impedance profiles, and finally into reservoir property parameter profiles. In addition, the low-frequency components of seismic waves attenuate slowly and have strong penetrating ability, which can improve the quality of seismic imaging in middle and deep layers, especially when...

AI Technical Summary

Problems solved by technology

[0005] However, at present, there are few methods for extracting low-frequency seismic information by introducing the Gated Recurrent Unit (GRU) neural network method. Traditional methods such as cluster analysis, genetic algorithm, and fuzzy theory, for the low-frequency information of long-term earthquake time series problems with a long time span The extraction effect is not ideal, it is greatly affected by subjective factors, the calculation efficiency is low, and the low-frequency characteristics of geological anomalies cannot be clearly reflected

Images