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

Well-to-seismic joint initial lithologic model construction method based on deep learning

A well-seismic combination and deep learning technology, applied in neural learning methods, biological neural network models, seismology, etc., can solve problems such as low logging data frequency, gradient disappearance, and insufficient initial model resolution, and achieve high computational efficiency , reliable results, fast convergence

Active Publication Date: 2020-12-01
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004]In the actual situation, the commonly used method of initial lithology model construction is to filter the logging data, and use the known filtered logging data to perform extrapolation and internal This results in two problems in the initial model: (1) The frequency of the filtered logging data is too low, generally not exceeding 70HZ, resulting in insufficient resolution of the established initial model; (2) Using the logging data for extrapolation and internal During the interpolation process, the well-seismic relationship was not used, and the seismic data did not control the initial model enough, resulting in multiple solutions in the established initial model
[0016]RNN cannot handle long sequences very well, and cannot effectively mine the information contained in long sequences. It is prone to gradient disappearance, which leads to the fact that the gradient cannot be transmitted in a long sequence during training, so that RNN cannot capture the long-distance influence

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
  • Well-to-seismic joint initial lithologic model construction method based on deep learning
  • Well-to-seismic joint initial lithologic model construction method based on deep learning
  • Well-to-seismic joint initial lithologic model construction method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The accuracy of traditional initial lithology model construction directly affects the inversion of lithology parameters, thus determining the final lithology model. At present, the commonly used initial lithology model construction method only uses seismic data, which leads to the lack of high-frequency information and insufficient resolution of the initial model; it does not make full use of logging data, and the information mining of seismic data and logging data is limited, resulting in incomplete initial models. precise. The present invention is based on deep learning, and proposes a new neural network, which uses the convolutional neural network to extract the long and short cycle, that is, the high and low frequency features contained in the data, and uses the long and short time memory network to perform feature selection and classification for different features. Furthermore, the relationship between seismic data and well logging data can be learned accurately 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 well-to-seismic joint initial lithologic model construction method based on deep learning, is applied to the field of three-dimensional geological modeling, and aims to solvethe problems that in the prior art, the frequency of well logging data is too low due to filtering, a lot of high-frequency effective information is lost, and seismic data cannot be effectively controlled in the interpolation process. According to the invention, the convolutional neural network is used to extract characteristics of long and short periods, namely high and low frequencies, contained in data; different features are classified and learned by adopting a long-term and short-term memory network, so that the relationship between seismic data and logging data is learned accurately, accurate prediction of rock attributes is achieved, a lithology initial model is constructed, a basis is provided for inversion of lithology parameters, and exploration and development of oil and gas and reservoir description of oil and gas reservoirs are guided.

Description

technical field [0001] The invention belongs to the field of three-dimensional geological modeling, in particular to an initial lithology model construction technology. Background technique [0002] 3D geological modeling is a new technology emerging from the study of oil and gas reservoirs in recent years, and it is the product of the fusion of computer science, mathematics, geology, geophysics and other disciplines and technologies. Since the technology was proposed in the 1990s, 3D geological modeling technology has been widely used in oil and gas exploration and development, mineral exploitation, hydrogeology and many other fields, and has achieved good application results. At present, in the process of oil and gas exploration and development, the existing geological, geophysical, drilling and other data are mainly used to construct the initial lithology model with the help of relevant algorithms, and provide the initial model for subsequent inversion, thereby revealing ...

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): G06T17/05G06N3/04G06N3/08G06K9/62G01V1/28
CPCG06T17/05G06N3/084G01V1/282G06N3/048G06N3/044G06N3/045G06F18/211G06F18/253
Inventor 陈豪鲁才罗艳阳亓康富唐元培胡光岷梁兼栋
Owner UNIV OF ELECTRONICS SCI & TECH OF 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