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

Lithology prediction method based on residual network

A prediction method and lithology technology, applied in the field of geophysical exploration, to achieve the effect of improving recognition accuracy, high accuracy, and precise representation

Active Publication Date: 2019-04-12
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The invention introduces deep learning into the field of geological exploration, which can effectively solve the problem of lithology identification and classification and improve identification accuracy

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
  • Lithology prediction method based on residual network
  • Lithology prediction method based on residual network
  • Lithology prediction method based on residual network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The scheme in the specific embodiment of the present invention will be described in detail below in conjunction with the accompanying drawings of the specification of the present invention:

[0015] figure 1 It is a flow chart of the lithology prediction method based on the residual network. This prediction method is divided into four stages, including:

[0016] A. Input feature map formation 11: Before training, the residual network of the present invention filters the seismic attributes at the seismic grid corresponding to the uphole position to form a matrix of N*N size to form a single-channel feature map as the input of the network , the lithology marker on the well is used as the output label.

[0017] B. Design of residual block 12: The difference between the residual network used in the present invention and the ordinary convolutional neural network lies in the existence of the residual block, which can make the network reach a very deep depth. The change of t...

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 lithology prediction method based on the residual network. Lithology qualitative analysis is achieved, the internal relation between the seismic attribute and the lithology is sought by utilizing the characteristic that the residual network can build a deeper convolutional network, after a prediction model is trained, corresponding lithology categories can be obtained according to a seismic attribute forming characteristic pattern, the quantity of output labels, that is, the quantity of output layer neurons is determined according to the quantity of the lithology categories in data, the output value of each neuron represents the probability that the group of data belongs to the corresponding lithology category, and the lithology characteristics of the neurons canbe expressed more precisely.

Description

technical field [0001] The invention belongs to the field of geophysical exploration and the field of deep learning, and specifically relates to the research and application of residual neural network in lithology prediction. Background technique [0002] Searching for lithologic reservoirs is an important research topic, and lithology prediction is of great significance to the discovery of lithologic reservoirs. Although there are many methods for lithology prediction, due to the different geological conditions in each area, each method can only achieve better application results in specific areas and under specific conditions. [0003] Logging data and seismic data are the most commonly used data, relying on mathematical models or inversion techniques established by geologists through experience is a common technique for qualitative prediction of lithology in unknown areas. Empirical formulas or the establishment of geological models have certain guiding significance for ...

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): G01V11/00G06N3/08
CPCG01V11/00G06N3/08
Inventor 李克文苏兆鑫刘文英周广悦
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
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