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

Oil and gas layer prediction method based on LSTM

A prediction method and technology for oil and gas formation, applied in the field of petroleum exploration, can solve the problems of not conforming to the geological thought, ignoring the vertical correlation of logging sequence data, etc., and achieve the effect of using continuity

Pending Publication Date: 2020-11-06
太仓中科信息技术研究院
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current layering methods based on machine learning mainly consider the one-to-one mapping relationship, that is, analyze for a single sampling point, while ignoring the longitudinal correlation of the logging sequence data, which is not in line with the actual geological thinking and traditional logic of geological analysis

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
  • Oil and gas layer prediction method based on LSTM
  • Oil and gas layer prediction method based on LSTM
  • Oil and gas layer prediction method based on LSTM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described The embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0029] Such as figure 1 As shown, the present invention discloses a method for predicting oil and gas reservoirs based on LSTM, comprising the following steps:

[0030] Step S1: Divide multiple different prediction stages;

[0031] Step S2: Screening the logging attributes in the logging data of a plurality of different prediction sta...

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 an oil and gas layer prediction method based on LSTM. The oil and gas layer prediction method based on LSTM comprises the following steps of: dividing into a plurality of different prediction stages; respectively screening logging attributes in logging data of the multiple different prediction stages; respectively carrying out LSTM model training on the multiple different prediction stages by using the logging attributes screened in the step S2; and combining the trained multiple models into a final model to obtain a final prediction result. According to the method, thetraining process is divided into three stages, different horizons can be distinguished in a targeted mode, training data are trained in a segment mode, the continuity of geological information can beeffectively utilized, the horizons can be accurately identified, accurate and reliable layering results can be quickly obtained, time and labor are saved, and the method has important value.

Description

technical field [0001] The invention relates to the technical field of petroleum exploration, in particular to an LSTM-based oil and gas reservoir prediction method. Background technique [0002] Petroleum is a very important strategic resource. However, the exploitation of petroleum is often accompanied by high costs. Therefore, it is usually necessary to use well logging information to predict geological structure information and judge the location of oil and gas layers. However, the traditional identification of oil and water layers mainly depends on the experience of experts, and experts obtain layered interpretation conclusions through the analysis of well logging curves. This method is not only time-consuming and laborious, but also not necessarily accurate, and the geological differences in different regions will also bring huge troubles to human prediction. Therefore, how to use well logging information to quickly obtain accurate stratification interpretation conclu...

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): E21B47/00E21B49/00
CPCE21B47/00E21B49/00
Inventor 朱登明石敏金相臣
Owner 太仓中科信息技术研究院
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