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

Machine learning constraint-based density mutation interface inversion method and system

A machine learning, mutation interface technology, applied in the field of survey, can solve problems such as poor pertinence and affect the interpretability of the deep learning optimization process, and achieve the effect of enhancing accuracy and improving interpretability

Active Publication Date: 2022-06-28
CHENGDU UNIVERSITY OF TECHNOLOGY
View PDF8 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the limitations of traditional gravity data sets that are not well targeted and the input terminal and training mode are single, the interpretability of the deep learning optimization process is affected. influences

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
  • Machine learning constraint-based density mutation interface inversion method and system
  • Machine learning constraint-based density mutation interface inversion method and system
  • Machine learning constraint-based density mutation interface inversion method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] In the first embodiment, as figure 1 As shown, a method for inversion of density mutation interface based on machine learning constraints includes the following steps:

[0054] S1. According to the measured gravity data of the basin in the target area, the initial basin interface is determined by the Bouguer plate model. The calculation formula is as follows:

[0055]

[0056] in, is the initial depth of the basement of the basin model, For the measured gravity data, is the density difference between the surface and surrounding rock, is the gradient of density difference with depth; based on the initial basin interface, a variety of random transformation methods of probability distribution are used to generate multiple sets of basin disturbance interfaces.

[0057] S2. Perform a Hadamard product operation between the initial basin interface and the random basin disturbance interface data set to quickly generate a basin interface data set.

[0058] S3. Fill i...

Embodiment 2

[0076] In the second embodiment, a density mutation interface inversion system based on machine learning constraints includes: an interface generation module, a Hadamard product operation module, a function filling module, a forward modeling module, a migration imaging module, and a migration model optimization module Deep Learning Module and Gravity Multivariate Density Constrained Regular Inversion Module.

[0077] The interface generation module is used to construct an initial basin interface based on the measured gravity data, and randomly generate a perturbed basin interface dataset based on the initial basin interface.

[0078] The Hadamard product operation module is used to perform the Hadamard product operation based on the initial basin interface and disturbed basin interface data sets to obtain the basin interface data set.

[0079] The function filling module is used to fill in the density of the overlying strata based on the basin interface dataset to obtain a hig...

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 a density abrupt change interface inversion method and system based on machine learning constraints. The method comprises the following steps: constructing an initial basin interface, randomly generating a disturbance basin interface data set, and carrying out Hadamard product operation on the initial basin interface and the disturbance basin interface data set to obtain a basin interface data set; performing higher function filling on the basin interface data set to obtain a high-resolution density interface model data set, performing forward modeling calculation to obtain a simulated gravity data set, and performing transformation and weighting on the simulated gravity data set to obtain a low-resolution offset density interface model data set; and optimizing an offset model deep learning network and mapping to obtain a high-resolution constraint density interface prior model, constructing a stable nonlinear loss function and carrying out regularization inversion to obtain a high-resolution density interface model. By exploring the input mode and the learning mode of deep learning, research on the density mutation interface inversion method based on machine learning constraint is carried out, and the precision of interface inversion imaging is enhanced.

Description

technical field [0001] The present application relates to the field of surveying, and in particular to a method and system for inversion of density mutation interface based on machine learning constraints. Background technique [0002] The observed gravity anomaly is a comprehensive reflection of the fluctuation and lithology of the underground density interfaces. Therefore, the inversion of the fluctuation shape of the density interface through the gravity anomaly has always been an important content in the processing and interpretation of potential field data. At present, the main density imaging methods include: (1) regularized inversion imaging; (2) gravity migration imaging; (3) deep learning imaging. [0003] The regularized inversion method strengthens the geological significance of the inversion results and improves the stability of the inversion by dynamically assigning the weights between the data metric space and the model metric space with the help of prior infor...

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): G06F30/27G06N20/00G06F111/04
CPCG06F30/27G06N20/00G06F2111/04
Inventor 徐铮伟王绪本王睿梁生贤
Owner CHENGDU UNIVERSITY OF TECHNOLOGY
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