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

Composite vortex recognition model construction method based on Helmholtz decomposition and deep learning

A deep learning and recognition model technology, applied in the field of compound vortex recognition, can solve the problems of low accuracy and low recognition efficiency, and achieve the effect of improving the recognition accuracy

Pending Publication Date: 2022-05-24
SHANGHAI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the methods for identifying compound vortices are mainly physical methods, such as the improved HD method, which is based on the original satellite altimeter data, but using this unprocessed data to identify compound vortices makes the identification efficiency low , and the accuracy is not high

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
  • Composite vortex recognition model construction method based on Helmholtz decomposition and deep learning
  • Composite vortex recognition model construction method based on Helmholtz decomposition and deep learning
  • Composite vortex recognition model construction method based on Helmholtz decomposition and deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be further described in detail below with reference to the accompanying drawings, so that those skilled in the art can implement it with reference to the description.

[0041] It should be understood that terms such as "having", "comprising" and "including" as used herein do not assign the presence or addition of one or more other elements or combinations thereof.

[0042] Mesoscale eddies refer to eddies with a radius of 10-100 km in the ocean, and their survival cycle, that is, the time from birth to decay, is as long as tens of days or even years. According to the shape of the mesoscale vortex, the mesoscale vortex is divided into single vortex and compound vortex. The single vortex refers to the vortex composed of closed streamlines in the ocean with one vortex center, and the compound vortex refers to the existence of 2 to 3 single vortices in the vortex composed of closed streamlines. According to the different rotation directions of me...

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 composite vortex recognition model construction method based on Helmholtz decomposition and deep learning, and the method comprises the following steps: obtaining data of a flow velocity U in the east-west direction and a flow velocity V in the south-north direction of seawater, and constructing a velocity vector field image; performing Helmholtz decomposition on the velocity vector field image to obtain an image with a potential field Fd and an image with a rotation field Fc; according to a potential function and UV data in the rotation field Fc, labeling a single-vortex air vortex, a single-vortex anti-cyclone vortex, a compound-vortex air vortex and a compound-vortex anti-cyclone vortex, and taking rotation field images before and after labeling as a deep learning data set; and training the deep learning data set by using a neural network to obtain a composite vortex recognition model. The Helmholtz decomposition method is used for processing derivative data of the satellite altimeter, the recognition accuracy of the compound vortex is improved, the deep learning method is adopted, the recognition efficiency of the compound vortex is improved, and finally application of the model to the whole sea area is achieved.

Description

technical field [0001] The invention belongs to the field of compound vortex identification, in particular to a method for constructing a compound vortex identification model based on Helmholtz decomposition and deep learning. Background technique [0002] A mesoscale eddy is a type of eddy in the ocean that is widespread in the global ocean. Ocean eddies themselves carry great kinetic energy, which plays a key role in global ocean material transport and energy transfer. We have often identified single vortices before, but little attention has been paid to compound vortices. The composite vortex is a combination of single vortices. After two single vortices meet together to form a composite vortex, it will affect the trajectory of the original single vortex. In addition, the form of energy exchange between two independent single vortices is also different from that of the two single vortices in the composite vortex, so our identification of the composite vortex has very im...

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): G06V20/05G06V20/13G06V10/26G06V10/774G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/04G06N3/08G06F18/24G06F18/214Y02T90/00
Inventor 张丹宋晶晶吴昊李孝伟彭艳谢少荣
Owner SHANGHAI UNIV
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