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

Spatial data random simulation method based on deep learning

A technology of stochastic simulation and deep learning, applied in the field of stochastic simulation of spatial data based on deep learning, can solve the problems of poor ability to extract structural features of MPS method and affect the quality of simulation, and achieve the effect of improving the quality of stochastic simulation of MPS.

Inactive Publication Date: 2018-03-20
SHANGHAI UNIVERSITY OF ELECTRIC POWER
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] An important branch of the uncertainty interpolation method is the MPS method (Multipoint Geostatistics Method). The MPS method can extract complex (non-linear) feature patterns from the training image and copy them to the interpolated image by reproducing high-order statistics. In order to obtain the final simulation results, but the structural feature extraction ability of the MPS method is poor, which affects the final simulation quality

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
  • Spatial data random simulation method based on deep learning
  • Spatial data random simulation method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The embodiments of the present invention are described in further detail below in conjunction with the accompanying drawings, but the present embodiments are not intended to limit the present invention. All similar structures and similar changes of the present invention should be included in the scope of protection of the present invention. The commas in all indicate the relationship between and.

[0022] like figure 2 As shown, a method for random simulation of spatial data based on deep learning provided by the embodiment of the present invention is characterized in that the specific steps are as follows:

[0023] 1) Construct a deep belief network, and set a data simulation path for MPS random simulation, and a data scanning path for scanning training data;

[0024] If there is conditional data in the training image, distribute the conditional data in the training image to each grid point of the deep belief network;

[0025] The method of constructing a deep belie...

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 spatial data random simulation method based on deep learning, and relates to the technical field of image processing. A technical problem to be solved is to improve the random simulation quality. The method comprises the steps: building a training image mode library through a data template method, extracting image essence structural features in the training image mode library through a deep learning method of a deep belief network; carrying out the classification of the image essence structural features through a clustering algorithm; and carrying out the MPS simulation of a simulation target area of a training image. The method provided by the invention can be widely used for the fields of environment monitoring, exploration and development of oil and gas, geological analysis and weather forecast.

Description

technical field [0001] The invention relates to image processing technology, in particular to a technology based on a deep learning-based random simulation method for spatial data. Background technique [0002] Uncertainty in spatial data generally exists in nature and human society, and plays a vital role at the same time. Uncertainty spatial data in real life come from both scientific experiments and production practices, and their formats and characteristics are all-encompassing. [0003] At present, data interpolation has become an effective means to obtain uncertain spatial data. Data interpolation is to use the scattered sampling information in the studied data to estimate the attribute values ​​at the unsampled points with certain physical and mathematical effective and reasonable rules, in order to form a complete data model of continuous distribution of attributes. Interpolation methods can be roughly divided into "deterministic" interpolation methods and "uncerta...

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): G06K9/62
CPCG06F18/232G06F18/24G06F18/214
Inventor 张挺
Owner SHANGHAI UNIVERSITY OF ELECTRIC POWER
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com