Pre-stack seismic reflection pattern recognition method based on multi-scale feature fusion

A multi-scale feature, prestack seismic technology, applied in character and pattern recognition, seismology, seismic signal processing, etc. Effect

Active Publication Date: 2019-12-24
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF15 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In order to solve the above-mentioned technical problems, the present invention proposes a pre-stack seismic reflection pattern recognition method based on multi-scale feature fusion, which intelligently excavates features that can characterize the behavior of multi-dimensional seismic reflection patterns from uncertain (noise and other factors) multi-dimensional seismic data, Intelligent identification of seismic reflection patterns without supervision, and finally precise division of seismic facies

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Pre-stack seismic reflection pattern recognition method based on multi-scale feature fusion
  • Pre-stack seismic reflection pattern recognition method based on multi-scale feature fusion
  • Pre-stack seismic reflection pattern recognition method based on multi-scale feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] figure 1 As a flow chart of seismic reflection pattern recognition, the seismic signal should be preprocessed first, and the appropriate time window size should be selected on the horizon to obtain the seismic signal of the target horizon segment. Then, combined with the seismic signal feature extraction method and machine learning classification algorithm, the seismic signal reflection characteristics of the target layer are classified, and the corresponding seismic phases are distinguished by class labels, and then the distribution of various target geological structures can be studied. . In the process of seismic reflection pattern recognition, feature extraction and feature classification are the two most critical steps. The premise of identifying seismic reflection patterns is that the features that completely characterize the target signal can be extracted. Therefore, the seismic signal feature extraction method is The focus of the present invention's research. ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a pre-stack seismic reflection pattern recognition method based on multi-scale feature fusion. The pre-stack seismic reflection pattern recognition method is applied to the field of seismic reflection mode identification, aiming at the problem that an existing pre-stack seismic signal in pre-stack seismic emission mode recognition is large in data amount, it is difficult tolabel each data manually and single features are insufficient; a multi-scale feature fusion network is constructed, an adversarial network is generated by introducing deep convolution, and the network structure is improved, so that the low-level features and the high-level features of the pre-stack seismic signal can be effectively extracted; and in addition, a fusion module is added on the basisof the improved convolution generative adversarial network, and the complete characterization of the pre-stack seismic signal reflection mode is obtained by multi-scale fusion of the high-layer and low-layer features.

Description

technical field [0001] The invention belongs to the field of seismic reflection pattern recognition, in particular to a pre-stack seismic reflection pattern recognition technology. Background technique [0002] With the emergence of a large number of emerging technologies such as deep learning, the traditional oil exploration industry has also begun to adopt advanced technologies on a large scale to improve production efficiency, which has led to the rapid development of the oil industry and brought huge economic benefits to the national economy. However, with the continuous enhancement of oil exploration capabilities, it is becoming more and more difficult to find new oil and gas fields under the condition of limited resources. This requires people to understand and understand the storage status of underground oil and gas fields in a more scientific way, improve the ability of exploration and prediction, and mine more new information from existing geophysical, geological, a...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G01V1/28G01V1/30G06K9/62G06N3/04G06N3/08
CPCG01V1/282G01V1/307G06N3/08G01V2210/63G06N3/045G06F18/23G06F18/241
Inventor 钱峰袁英淏胡光岷
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap