A Multi-wave Seismic Oil and Gas Reservoir Prediction Method Based on Deep Neural Network

Abstract

The invention discloses a multi-wave seismic oil and gas reservoir prediction method based on a deep neural network. The method includes the following steps: first, for the original data obtained from the longitudinal and transverse wave seismic attribute sets, the clustering analysis method of particle swarm optimization and Kernel principal component analysis is used to optimize seismic attributes, remove redundant information, and highlight the characteristics of multi-wave seismic oil and gas reservoirs, so as to obtain better deep neural network sample data; Study and perform simulation prediction to obtain the oil and gas reservoir evaluation map; finally, image enhancement processing is performed on the oil and gas reservoir evaluation map to improve the detail information and edge recognition of the image, thereby increasing the clarity of the image. In the prediction of oil and gas reservoirs, the method of the invention can improve the depiction accuracy of seismic oil and gas reservoirs, and provides a new approach for the identification and prediction of oil and gas reservoirs.

Description

technical field [0001] The invention belongs to the technical field of oil and gas reservoir prediction, in particular to a multi-wave seismic oil and gas reservoir prediction method based on a deep neural network. Background technique [0002] Seismic oil and gas reservoir prediction has always been a hot and difficult point in the exploration and development of oil and gas fields. Seismic data contain rich information on geological structures, physical properties of oil and gas, and underground strata. Therefore, using seismic data to obtain information on lithology and physical properties related to oil and gas is an effective prediction method. At present, the commonly used seismic oil and gas reservoir prediction technologies mainly include seismic attribute analysis technology, AVO technology, seismic fracture prediction technology, petrophysical analysis technology, forward modeling and multi-wave seismic oil and gas detection, etc. Seismic attribute analysis technol...

AI Technical Summary

Problems solved by technology

However, with the development of mathematics and computer technology, hundreds of seismic attributes can be obtained, but too much seismic attribute extraction will have a large amount of redundant data, and there will be problems such as unclear correspondence between the extracted attributes and geological significance. Therefore, how to optimize various attributes to improve production efficiency and reduce exploration costs is an urgent problem at this stage

Images