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

Method for inverting arctic melting pool distribution by using artificial neural network

An artificial neural network and inversion technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems affecting the accuracy of fusion pool distribution, and achieve the effect of improving the monitoring level.

Active Publication Date: 2020-03-06
NANJING UNIV OF INFORMATION SCI & TECH
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Modeling with fixed or insufficient prior conditions can lead to large errors, and using it as an input to the model can even affect the accuracy of the melt pool distribution

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
  • Method for inverting arctic melting pool distribution by using artificial neural network
  • Method for inverting arctic melting pool distribution by using artificial neural network
  • Method for inverting arctic melting pool distribution by using artificial neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

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

[0025] The present invention proposes a new method for remote sensing monitoring through the relationship between the reflectance of the 500m-resolution medium-resolution imaging spectrometer (MODIS) daily surface reflectance product (MOD09GA) from bands 1 to 7 and melting pools, sea ice and seawater , and can be applied to the 8-day 500m resolution MODIS surface reflectance product (MOD09A1), successfully inverting the distribution characteristics of the Arctic melting pool. It makes up for the defects in the time and space distribution and accuracy of the remote sensing monitoring fusion pool, and improves the application level of my country's polar monitoring business.

[0026] Such as figure 1 As shown, the research area is from 60° north latitude to 90° north latitude, and the specific steps are as follows:

[0027] 1. Collect the high-resolution melti...

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 method for inverting arctic melting pool distribution by using an artificial neural network. The method comprises the following steps: firstly, collecting a high-resolution melting pool image and a medium-resolution imaging spectrometer MOD09GA at the same time period, and re-projecting the high-resolution melting pool image and the medium-resolution imaging spectrometerMOD09GA into sine projection; then, constructing a grid consistent with the MOD09GA; calculating the proportion of a melting pool, the proportion of sea ice and the proportion of open water in each grid, and deleting pixels covered by cloud in MOD09GA; forming a data set by the obtained data, the corresponding sun-chasing surface reflectance and the MOD09GA 1-7 waveband reflectance; finally, constructing a melting pool model, taking the matched MOD09GA 1-7 waveband reflectivity as an input set, taking the corresponding sea ice proportion, melting pool proportion and open water proportion as anoutput sample set to train an artificial neural network, and finding an optimal solution. The method overcomes the defects of field observation and underway observation in time and space, has the characteristics of rapidness and simplicity, improves the remote sensing monitoring level of polar regions in China, and can better reflect the real melting pool condition of the north pole.

Description

technical field [0001] The invention in this paper belongs to the technical field of polar remote sensing, and relates to a method for retrieving the distribution of melting pools in the Arctic by using artificial neural networks. Background technique [0002] Summer melt pools in the Arctic can cover 50%-60% of the Arctic sea ice extent. The formation of melting pools on the sea ice surface due to short-wave insolation in summer and above-freezing surface air temperatures reduces the albedo of the sea ice surface, thereby causing the sea ice to absorb more additional heat. The melting pool is the most important parameter for the change of Arctic sea ice albedo in spring and summer. A low albedo melting pool will accelerate the melting of sea ice and lead to an earlier ice-free season in the Arctic. Therefore, it is of great practical significance to monitor changes in the Arctic melt pool. [0003] Conventional monitoring methods include navigation observation and field m...

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): G06F30/27G06N3/04G06N3/08
CPCG06N3/084G06N3/048G06N3/045
Inventor 张渊智冯佳俊何宜军
Owner NANJING UNIV OF INFORMATION SCI & TECH
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