Supercharge Your Innovation With Domain-Expert AI Agents!

Sand body prediction method and system based on seismic attributes of target layer and adjacent layer

A technology of seismic attributes and prediction methods, applied in the direction of seismic signal processing, etc., can solve the problem of inability to accurately predict the distribution of sand bodies in the target layer, and achieve the effects of reducing the impact, improving the interpretation progress, and high fitting of logging parameters.

Inactive Publication Date: 2019-05-17
CHINA UNIV OF PETROLEUM (BEIJING)
View PDF9 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, only based on the amplitude attribute of the target layer, there are obvious multi-solutions, and it is impossible to accurately predict the sand body distribution of the target layer

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
  • Sand body prediction method and system based on seismic attributes of target layer and adjacent layer
  • Sand body prediction method and system based on seismic attributes of target layer and adjacent layer
  • Sand body prediction method and system based on seismic attributes of target layer and adjacent layer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] Since the seismic attribute anomaly difference formed by the sand body in the target layer and the adjacent strata is relatively complicated, the present invention is based on well logging data (the reliability of the well logging data is high), and adopts machine learning (intelligent algorithm including support vector machine, genetic neural network, etc.) Network, deep learning) method, to establish a nonlinear mapping relationship between the thickness of the sand body interpreted by logging and the target layer and the upper and lower adjacent layers; and then according to the mapping relationship after training, the seismic attributes of the target layer and adjacent layers Fusion becomes a new attribute, which is also the predicted sand body thickness. The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0025] The present invention provides a sand body prediction method based on the seismic attr...

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 sand body prediction method and system based on seismic attributes of a target layer and an adjacent layer. The method comprises the following steps of extracting the thickness of a sand body at a well point of the target layer, and carrying out fine horizon interpretation on seismic horizons of the target layer and the adjacent layer; extracting a seismic attribute value near the well point, and selecting the seismic attributes capable of reflecting target parameters through analysis of the correlation between the seismic attributes near the well point and the thickness of the sand body of well logging interpretation; taking the thickness of the sand body of well logging interpretation of the target layer as a target data set, taking the seismic attribute valuesnear the well points of the target layer and the upper and lower adjacent stratums as a training sample data set, taking all of target data and training data as input data, and carrying out nonlinearmapping to obtain a trained multiple regression model; and fusing seismic attribute layer slices of the target layer and the upper and lower adjacent stratums according to the trained multiple regression model in order to obtain a fused seismic attribute graph capable of reflecting the thickness distribution of the sand body of the target layer, thereby completing the sand body distribution prediction.

Description

technical field [0001] The invention relates to the technical field of seismic attribute analysis and prediction, in particular to a sand body prediction method and system based on the seismic attributes of a target layer and an adjacent layer. Background technique [0002] With the improvement of the quality of 3D seismic data, seismic attribute analysis technology has achieved rapid development and is widely used in reservoir prediction. However, in the actual production process, how to use seismic attribute analysis technology to improve the interpretation accuracy of reservoirs has always been the direction of continuous efforts of geological interpreters. At present, in improving the reservoir prediction accuracy of seismic attributes, many scholars are mainly working on the following two aspects: one is to explore new seismic attributes, in order to better identify the distribution of reservoirs through more reasonable mathematical algorithms; The second is to make re...

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): G01V1/28G01V1/30
Inventor 李伟岳大力王文枫吴胜和王武荣
Owner CHINA UNIV OF PETROLEUM (BEIJING)
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More