Multi-wave matching method based on convolutional neural network

Abstract

The invention discloses a multi-wave matching method based on a convolutional neural network. The method includes the steps of pre-processing transverse wave and longitudinal wave data, dividing spacegrids on the basis of the transverse wave and longitudinal wave data according to preset steps, calculating grid point displacement of the space grids, merging the transverse wave and longitudinal wave data together and extracting feature vectors, training a convolutional neural network, processing the transverse wave and longitudinal wave data to obtain a matching data body, establishing a three-dimensional time window to perform traversal on the matching data body and obtaining displacement of all points, and re-sampling longitudinal waves on the basis of the obtained displacement to finally complete multi-wave matching. The transverse wave and longitudinal wave data is matched through training of the convolutional neural network, so the matching precision and the matching efficiency are improved greatly and the workload is reduced.

Description

technical field [0001] The invention belongs to the technical field of multi-wave matching, and in particular relates to a multi-wave matching method based on a convolutional neural network. Background technique [0002] Multi-wave seismic exploration is a very potential method for the exploration of lithologic and subtle oil and gas reservoirs. However, due to many reasons, the combination of multi-wave and multi-component theoretical research and the actual exploration geological requirements of oil and gas fields, and the conversion under complex conditions No significant progress has been made in issues such as wave seismic data processing, multi-wave comprehensive interpretation, and geological application of full-wave attributes, and has become a "bottleneck" restricting the further development of multi-wave seismic exploration technology. The basis for solving these problems is to do a good job in multi-wave and multi-component data processing, and provide high-qualit...

AI Technical Summary

Problems solved by technology

[0002] Multi-wave seismic exploration is a very potential method for the exploration of lithologic and subtle oil and gas reservoirs. However, due to many reasons, the combination of multi-wave and multi-component theoretical research and the actual exploration geological requirements of oil and gas fields, and the conversion under complex conditions Issues such as wave seismic data processing, multi-wave comprehensive interpretation, and geological application of full-wave attributes have not made significant progress, and have become the "bottleneck" that restricts the further development of multi-wave seismic exploration technology.

The main problem of the current multi-wave matching technology is that the accuracy is not high

First, the current multi-wave initial matching is basically done by simply matching the layers of PP waves and PS waves, so the accuracy of the initial matching will be rough and not high

Second, current seismic exploration requires higher and higher accuracy of multi-wave matching, but the current accuracy of multi-wave fine matching is not ideal, and low-precision fine matching has seriously affected the joint interpretation and joint inversion of multi-wave

The disadvantage of this method is that the matching is only based on the coaxial axis, and the matching of a large number of other points is not considered. The correction is only performed on a small number of points, and the relationship between the coaxial axis and the surrounding data is not considered. If explained If the error is large, it is bound to have a huge impact on the final result.

Therefore, the matching degree of the existing method is relatively rough.

Images