Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Seismic inversion big data generation method based on convolutional neural network

A convolutional neural network, seismic inversion technology, applied in neural learning methods, biological neural network models, seismology for logging records, etc., can solve problems such as the reduction of resolution and accuracy of exploration data

Active Publication Date: 2019-11-22
SOUTHWEST PETROLEUM UNIV
View PDF12 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the complex geological conditions on the surface such as deserts, Gobi or piedmont, and the underground structures such as faults, cracks, buried hills, etc., the resolution and accuracy of exploration data are greatly reduced.
Low-quality exploration big data makes it a huge challenge to efficiently separate the effective information of the data and use it for various processing and interpretation

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 inversion big data generation method based on convolutional neural network
  • Seismic inversion big data generation method based on convolutional neural network
  • Seismic inversion big data generation method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The generation method of seismic inversion big data based on convolutional neural network includes the following detailed steps in turn:

[0015] Step 1: Perform probability density function statistics on each group of logging wave impedance data in the target work area, and select two groups of data that meet the screening conditions.

[0016] Step 2: Select one set of the above two sets of wave impedance data as the initial well data A, and the other set as the target well data B, randomly select a point i in A according to formula 1 and perform disturbance drift based on the greedy algorithm. The wave impedance data with a probability of 0 in the histogram of the geological model of the work area migrated to the non-zero probability category ( figure 1 ), based on formula 3 to get the final disturbance result V new_ And combined into data C.

[0017] i=N*random(0~1)+0.5 (1)

[0018]

[0019]

[0020] Among them, N is the total sample points of a group of wel...

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 inversion big data generation method based on a convolutional neural network. The method is characterized in that a big data set is generated based on data statistical feature migration for realizing seismic inversion for the convolutional neural network. Artificial intelligence, geophysics, spatial statistics, information science and other multiple disciplines are integrated, a deep learning technology, a big data technology, a seismic inversion technology and the like are organically combined, big data are generated by small data for a data set required by seismic inversion, so that the problem of low quality of field exploration data is solved, the data collection cost and theexploration risk are reduced, and the defects in the prior art are overcome.

Description

technical field [0001] The invention relates to the technical field of petroleum and natural gas geophysical exploration, and the specific field is a method for generating large data of seismic inversion based on a convolutional neural network. Background technique [0002] With the continuous improvement and development of oil and gas exploration technology, the degree of development of natural resources such as oil and gas has gradually increased. Limited resources make efficient exploration and production more difficult. In geophysical exploration, seismic inversion is an inverse problem of inferring the real situation of subsurface geology and various properties of geological models based on the seismic data obtained from actual observations; different from forward modeling, inversion usually has multiple solutions and ill-posed properties. The results obtained are often influenced by factors such as the data and processing methods used. The data used in seismic inversi...

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): G01V1/28G01V1/30G01V1/40G06N3/04G06N3/08
CPCG01V1/28G01V1/306G01V1/40G06N3/08G01V2210/6226G06N3/045
Inventor 黄旭日代月徐云贵胡叶正曹卫平唐静
Owner SOUTHWEST PETROLEUM UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com