Full-waveform inversion method and device and electronic equipment

Abstract

The invention provides a full-waveform inversion method and device, and electronic equipment. The method comprises the steps of obtaining initial physical parameters, wherein the initial physical parameters are speed parameters of the underground structure; performing parameterization processing on the initial physical parameters to obtain physical parameters, and inputting the physical parametersinto a pre-trained machine learning model to enable the machine learning model to output a full-waveform inversion result according to the physical parameters, wherein the full-waveform inversion result and the weight coefficient of the machine learning model satisfy a preset relationship; and reconstructing a speed structure chart of the underground structure according to the full-waveform inversion result. According to the invention, the initial physical parameters are parameterized through the weight coefficient of the machine learning model; therefore, the full-waveform inversion problemis converted into the reconstruction problem of machine learning model network parameters, the problems that the existing full-waveform inversion cannot solve the nonlinear inversion problem and a large amount of calculation exists are solved, the calculation efficiency is improved, and the beneficial effect of high-precision inversion of a complex underground structure is achieved.

Description

technical field [0001] The invention relates to the technical field of exploration geophysics, in particular to a full waveform inversion method, device and electronic equipment. Background technique [0002] FWI (Full Waveform Inversion, Full Waveform Inversion) is an inversion method that can reconstruct subsurface structures with high resolution. Its purpose is to find an optimal model that minimizes the objective function of observation data and synthetic data. This process is usually achieved by employing local or global optimization strategies. From a computational point of view, the local optimization method is better than the global optimization method because the global strategy requires more computation. [0003] In practical applications, it is still challenging to apply the local convergence algorithm to the traditional FWI method. Due to the highly nonlinear and ill-posed nature of the objective function of the traditional FWI method, FWI often has multiple loc...

AI Technical Summary

Problems solved by technology

[0003] In practical applications, it is still challenging to apply the local convergence algorithm to the traditional FWI method. Due to the highly nonlinear and ill-posed nature of the objective function of the traditional FWI method, FWI often has multiple local minima, resulting in The local convergence algorithm is hindered by multiple local minima and large-scale calculations caused by the number of dimensions. Therefore, the existing FWI method is not suitable for nonlinear inverse problems, and has a large amount of calculation, resulting in inverse The resulting underground structure map is not ideal

Images