A method to reduce the non-uniqueness of electromagnetic sounding inversion results

Abstract

The invention discloses a method for reducing the non-uniqueness of an electromagnetic sounding inversion result. The method comprises the following steps: acquiring the electromagnetic sounding data of an exploration area to obtain at least over two two-dimensional inversion depth-resistivity models; performing regularization to obtain regularized two-dimensional depth-resistivity model inversion results; determining a learning sample and a target sample; establishing a BP (Back Propagation) neural network system; inputting the inner section of the area into a neural network in sequence point after point and depth point after depth point to obtain the desired prediction results of each measuring point and each depth point; reducing the prediction results into a real inversion resistivity value to obtain an optimized two-dimensional inversion result. According to the processing method for rapidly optimizing the inversion non-uniqueness of electromagnetic sounding data, neural network processing is performed on a plurality of inversion results, and known information is learned, so that the non-uniqueness is reduced, and the method is practical and effective for obtaining a real model of a complex area target body.

Description

technical field [0001] The invention relates to a geophysical prospecting method, which is an electromagnetic prospecting data processing technology, in particular a method for reducing the non-uniqueness of electromagnetic sounding inversion results. Background technique [0002] Electromagnetic sounding is a geophysical exploration method to understand the change of the resistivity of the underground medium by observing the change of the electromagnetic field on the ground. In recent years, with the rapid development of theoretical research and computer technology, inversion methods for converting collected frequency-resistivity data into depth-resistivity data emerge in endlessly, such as 2D layered model inversion, 2D continuum inversion, and even 3D inversion. The calculation method has gradually matured, the calculation speed has been greatly improved, and the underground geoelectric model can be obtained relatively quickly, so that the electromagnetic sounding method ...

AI Technical Summary

Problems solved by technology

[0003] However, no matter it is 2D inversion or 3D inversion, even if the fitting error is very small, the obtained inversion results are often not completely consistent with the actual underground electrical structure. The reason is due to the non-uniqueness of geophysical inversion. The result is that the geophysical measurement data has multiple models corresponding to it, and the non-uniqueness of electromagnetic sounding inversion is unavoidable

[0004] How to reduce the non-uniqueness of inversion results has always been the direction of efforts of geophysicists, among which the optimization of inversion algorithms is the most researched, but the results are not completely satisfactory

This has always been the reason why the results of electromagnetic sounding inversion are difficult to meet the actual production needs

Images