Seismic phase feature recognition waveform inversion method based on full convolutional neural network

A technology of convolutional neural network and waveform inversion, which is applied in the field of exploration seismic waveform recognition technology and deep learning, can solve the problems of slow convergence, non-convergence, waveform window accuracy and efficiency of inversion, etc., to improve convergence, The effect of improving inversion efficiency

Active Publication Date: 2020-09-29
NANJING UNIV +1
View PDF3 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Purpose of the invention: In order to overcome the accuracy and efficiency of waveform window selection in

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
  • Seismic phase feature recognition waveform inversion method based on full convolutional neural network
  • Seismic phase feature recognition waveform inversion method based on full convolutional neural network
  • Seismic phase feature recognition waveform inversion method based on full convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] Below in conjunction with accompanying drawing and specific embodiment, further illustrate the present invention, should be understood that these examples are only for illustrating the present invention and are not intended to limit the scope of the present invention, after having read the present invention, those skilled in the art will understand various aspects of the present invention All modifications of the valence form fall within the scope defined by the appended claims of the present application.

[0037] A waveform inversion method for phase feature recognition based on fully convolutional neural network, such as figure 1 As shown in Fig. 1, a full convolutional neural network window selection mechanism is added to the traditional full waveform inversion process to avoid cycle jumps, including the following steps:

[0038] Step 1. Obtain the actual observed seismic records as observed waveform data. Obtain earthquake training data samples, and use the traditi...

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 seismic phase feature recognition waveform inversion method based on a full convolutional neural network. The method comprises the steps of: preliminarily screening a seismicwave time window through a conventional seismic facies screening method FLEXWIN, manually screening data with higher quality as a training set, building a full convolutional neural network, and training the full convolutional neural network through the training set; performing seismic phase identification and window division on seismic waveform data by using the full convolutional neural network;and comparing the waveform similarity between the theoretic and observed data in the windows, and screening the waveform meeting the fitting condition to perform waveform inversion. Through a full convolutional neural network seismic phase feature recognition technology, the problem of efficient waveform window pickup in waveform inversion is solved, the problem of periodic jump is effectively improved, and the convergence rate of waveform inversion is increased.

Description

technical field [0001] The invention relates to an exploration seismic waveform identification technology and a deep learning technology, and is especially suitable for solving the accuracy and efficiency problems of automatic data picking in waveform inversion. Background technique [0002] Modeling and inversion of seismic wave velocity has always been a core issue in geophysics. As a high-precision velocity modeling and inversion method, full waveform inversion (FWI) has become one of the research hotspots in geophysics and seismology. It performs inversion by fitting all the waveform information of the observed waveform data and the calculated data. Compared with other inversion methods, it can obtain a higher resolution subsurface medium structure. The full waveform inversion method has been widely used in petroleum and mineral resource exploration, global scale structure imaging and so on. The gradient calculation of the FWI method is realized by propagating the wave...

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
IPC IPC(8): G06F17/10G06N3/04G06N3/08G01V1/30G01V1/28G01V1/36G01V1/24
CPCG06F17/10G06N3/084G01V1/303G01V1/282G01V1/36G01V1/247G06N3/045
Inventor 阮友谊江文彬奚成朋王文闯
Owner NANJING UNIV
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