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

Reservoir detection method based on depth learning of seismic data

A technology of deep learning and detection methods, applied in the field of petroleum geophysical exploration, to achieve the effect of flexible and diverse calculation methods

Active Publication Date: 2017-06-23
CHENGDU UNIVERSITY OF TECHNOLOGY
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, deep learning is rarely applied to the field of seismic exploration

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 detection method based on depth learning of seismic data
  • Reservoir detection method based on depth learning of seismic data
  • Reservoir detection method based on depth learning of seismic data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the embodiments and accompanying drawings;

[0025] Such as figure 1 As shown, it is a deep learning reservoir detection method process based on seismic data, and the method includes the following steps:

[0026] Step 10 uses well logging, mud logging and synthetic seismic records to accurately demarcate the target layer;

[0027] Step 20 extract well side channel seismic data along the specified time window width of the target layer as the training data of the deep learning model. For the extraction method, see figure 2 ;

[0028] figure 2 Taking a certain point as the origin, the adjacent 9 channels are taken as a whole, and the time window for each channel is 20ms. According to the sampling interval of 2ms, a training sample is 90 sampling points. The space sliding distance is 1 int...

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 embodiment of the invention provides a reservoir detection method, belonging to the technical field of petroleum geophysical exploration. The method comprises a step of obtaining well side seismic channel data corresponding to a target position according to the calibrated target position, a step of establishing a reservoir detection depth learning model based on the well side seismic channel data, a step of obtaining the high level characteristic of the target position based on the reservoir detection depth learning model and the target position, a step of obtaining the reservoir characteristic of a specified reference position on the target position, and a step of determining the reservoir characteristic of an area same with the high level characteristic of the reference position on the target position based on the reservoir characteristic of the reference position. According to the method, through establishing a reservoir characteristic detection depth learning model to extract a reservoir weak earthquake response characteristic, the reservoir characteristic can be simply and efficiently determined, and the detection precision of reservoir such as oil and gas and hydrocarbon of seismic exploration data is improved.

Description

technical field [0001] The invention relates to the technical field of petroleum geophysical exploration, in particular to a deep learning-based reservoir detection method. Background technique [0002] The targets of geophysical exploration are becoming deeper and smaller, and the exploration environment is becoming more complex. Some gas-bearing detection methods and technologies that are effective in shallow conditions, such as "bright spot" technology, AVO effect, high-frequency shadow, etc., cannot meet the requirements. Exploration requirements. The essence of reservoir oil and gas prediction is the identification and evaluation of rock pore fluid properties and saturation. The volume and quality of reservoir pore fluid only account for a very small part of the reservoir rock, and it is filled in the solid rock framework. In pores, the seismic response is very weak. If the seismic record responds to changes in rock pore fluid, it can only be reflected in the fine str...

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): G01V1/28G01V1/30
CPCG01V1/282G01V1/30G01V2210/6226G01V2210/66
Inventor 曹俊兴吴施楷何晓燕
Owner CHENGDU UNIVERSITY OF TECHNOLOGY