Seismic facies pickup method

A technology of seismic phase and waveform data, applied in the field of seismic phase picking, can solve the problem that seismic phase cannot be picked accurately

Active Publication Date: 2019-07-19
CTBT BEIJING NAT DATA CENT
View PDF12 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a method for picking up seismic phases, which sol

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 facies pickup method
  • Seismic facies pickup method
  • Seismic facies pickup method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0041] According to the above method, build a multi-task convolutional neural network model, the structure is as follows figure 1shown. The designed convolutional neural network model is trained, verified and tested by using 2 million pieces of data from the Southern California Seismic Network (SCSN). The data is the marked data of the seismic phase of the three-point station. The seismic phase is mainly the direct wave P, S and noise N, and the noise data is the data of the first 5s of the detection signal. The data sampling rate is 100, and the data is intercepted with the time window of 4 s centered on the arrival time of the manually picked seismic phase. Data preprocessing includes delinearizing the data, filtering in the (0-20HZ) frequency band, and normalizing the data with the maximum value of each segment of data. figure 2 It is the decrease of the joint loss value with the number of iterations during model training. It can be seen that the overall loss value of th...

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 facies pickup method. According to the method, a multi-task deep convolutional neural network model is constructed; a weighted classification loss function is defined; a classification and regression combined loss function is designed; training, verifying and testing are carried out on the model by utilizing an acquired large-scale three-directional station waveform data set of a station network in a certain region, and the seismic phase is detected, recognized and accurately picked up when arriving at time, then a transfer learning and data enhancement methodis adopted, the model is applied to training, verification and testing of a small-scale data set of a transformer network in a target area, and seismic phase picking-up in the target area is achieved. According to the method, the multi-task convolutional neural network is utilized to simultaneously realize detection identification and time-of-arrival estimation of the seismic facies, accurate seismic facies pickup of a target area with only a small data set is realized by utilizing transfer learning, and the problem of seismic facies pickup is solved.

Description

technical field [0001] The invention belongs to the field of seismic signal detection and estimation, and in particular relates to a method for picking up seismic phases. Background technique [0002] The picking of seismic phase is based on the data recorded by the seismic monitoring station, the process of detecting signal, distinguishing the seismic phase and estimating the arrival time, which is an important link in the data processing of the seismic station. Since the seismic waveform from the seismic source to the receiving end of the station sensor is affected by various factors such as source mechanism, stress drop, dispersion, site effect, seismic phase conversion, and interference from various noise sources, the seismic signal recorded by the station It is very complicated. The traditional method is based on one or several features of the seismic phase to realize the detection and identification of the seismic phase, which cannot cover all the features contained in...

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): G06K9/00G06K9/62G01V1/30
CPCG01V1/307G06F2218/02G06F2218/08G06F2218/12G06F18/214
Inventor 李健王晓明刘哲函商杰盖磊邱宏茂
Owner CTBT BEIJING NAT DATA CENT
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