Reservoir prediction method based on bidirectional recurrent neural network

A technology of cyclic neural network and neural network, which is applied in the field of seismic data interpretation of geophysical exploration, and can solve problems such as not considering seismic wave depth (time) information

Active Publication Date: 2019-05-24
CHINA PETROLEUM & CHEM CORP +1
View PDF7 Cites 52 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] To sum up, the previous methods did not consider the depth (time) information of seismic waves in the formation process, failed to take multi-seismic attributes as model input, and used reservoir and non

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
  • Reservoir prediction method based on bidirectional recurrent neural network
  • Reservoir prediction method based on bidirectional recurrent neural network
  • Reservoir prediction method based on bidirectional recurrent neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0115] The technical solution of the present invention will be described in detail below in conjunction with the drawings and embodiments.

[0116] Examples are attached figure 2The API (programming interface) provided by TensorFlow (an open source software library developed by Google using data flow graphs for numerical computing) defines a multi-layer bidirectional recurrent neural network.

[0117] Based on the above-mentioned source program, the process flow of the reservoir prediction method based on the two-way cyclic neural network designed by the present invention is shown in the appendix figure 1 ,

[0118] All steps can be automatically run by those skilled in the art using computer software technology. The specific implementation process of the embodiment is as follows:

[0119] Step 1, generation of well seismic data.

[0120] Step 1.1, generation of seismic data volume. Seismic data volumes include original seismic data and derived data volumes, mainly inclu...

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 relates to a reservoir prediction method based on a bidirectional recurrent neural network. The reservoir prediction method includes: generating well seismic data, generating well markeddata, generating a marked dataset, building and training the bidirectional recurrent neural network, storing a trained model, extracting seismic data corresponding to all geographic positions in a region, and performing prediction on the seismic data to acquire probability distribution of reservoirs below the whole region. A one-to-one corresponding relation between each sampling point and reservoirs and non-reservoirs is established, wherein input of each time step is n-dimension seismic data of each sampling point while output of the same is corresponding reservoir or non-reservoir marks. An optimal model is acquired by training marked samples and adjusting hyper-parameters, in this way, unmarked data can be predicted to finally generate a predicted seismic body of same dimension, and value of each sampling point is prediction probability between 0 and 1, so that the method has good effect on reservoir prediction.

Description

technical field [0001] The invention belongs to the technical field of geophysical exploration seismic data interpretation, and mainly relates to a reservoir prediction method based on a bidirectional cyclic neural network. Background technique [0002] Petroleum exploration methods are mainly divided into geological method, geophysical method, geochemical method and drilling method, among which the seismic physical exploration in the geophysical method is mainly used in each oil and gas field. Seismic exploration method is the application of artificial methods to make the earth's crust vibrate, such as artificial earthquakes produced by explosives. Then use sophisticated instruments to record the vibration of seismic waves at various points on the ground, and analyze these seismic waves and their derived data to determine whether there are oil fields below the formation. [0003] Reservoir seismic description is an important technology in oil and gas exploration and develo...

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): G01V1/48G01V1/50G06F17/16G06N3/04G06N3/08
Inventor 王兴谋冯德永朱剑兵王宝坤池明旻李长红
Owner CHINA PETROLEUM & CHEM CORP
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