Unlock instant, AI-driven research and patent intelligence for your innovation.

A segmentation and extraction method of three-dimensional geological anomaly based on convolution neural network

A convolutional neural network and three-dimensional geological technology, which is applied in the field of segmentation and extraction of three-dimensional geological anomalies, and can solve the problems of difficulty in fine description of fluvial facies reservoirs, etc.

Active Publication Date: 2019-01-15
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF8 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the frequent changes of channel, severe superimposition, limitation of signal-to-noise ratio and limitation of resolution of seismic data itself, there are certain difficulties in finely describing fluvial reservoirs

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
  • A segmentation and extraction method of three-dimensional geological anomaly based on convolution neural network
  • A segmentation and extraction method of three-dimensional geological anomaly based on convolution neural network
  • A segmentation and extraction method of three-dimensional geological anomaly based on convolution neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] Embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0025] see figure 1 , the present invention provides a method for segmenting and extracting three-dimensional geological anomalies based on a convolutional neural network, which is specifically implemented through the following steps:

[0026] Step 1: Divide the input 3D data cube into several 3D river data of the same size, and label the 3D river data to obtain a label vector.

[0027] In this embodiment, the input data is a three-dimensional data cube. Firstly, the input data is divided into multiple three-dimensional river channel data of the same size, and whether the three-dimensional river channel data has a channel is detected and marked. The labeling rules are: if the center point of the 3D river data belongs to the river part, it is marked as 1; if the center point of the 3D river data does not belong to the river part, it is marked as 0. In 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 provides a method for segmenting and extracting three-dimensional geological abnormal bodies based on a convolution neural network, belonging to the field of river channel geology extraction. The invention extracts the three-dimensional geological anomaly body finely through the training and prediction of the convolution neural network, which plays a great role in the future petroleum exploitation; the invention slices the three-dimensional geological abnormal body data from different axes, identifies and segments the three-dimensional data through the two-dimensional data, not only trains the data through a single dimension, but also makes full use of the spatial attribute of the three-dimensional data, and can better identify the relationship of the river channel data points.

Description

technical field [0001] The invention belongs to the field of channel geological bodies, in particular to a method for segmenting and extracting three-dimensional geological anomalies based on a convolutional neural network. Background technique [0002] Sandstone reservoirs are the most important places for oil and gas accumulation, and fluvial facies reservoirs are one of the most important types of reservoirs. Due to the complicated superimposition and transition of river channels, large vertical and lateral changes in reservoir lithology and poor continuity, and the constraints of signal-to-noise ratio and resolution of seismic data, there are still many difficulties in identifying and describing fluvial reservoirs. [0003] Geological anomaly channel sand bodies have good physical characteristics such as porosity and permeability, and are good places for oil and gas accumulation. If the paleo-river sand body is close to the oil source, it can become a reservoir of oil a...

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): G06T7/10G06K9/00G06K9/62G06N3/04
CPCG06T7/10G06V20/647G06N3/045G06F18/214
Inventor 鲁才陈家相胡光岷
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA