Multi-Algorithm Integration Algorithm of Surface Component Temperature Based on Bayesian Model Averaging Method

A Bayesian model and multi-algorithm technology, applied in calculations, complex mathematical operations, computer components, etc., to achieve high-precision results

Active Publication Date: 2021-05-11
AEROSPACE INFORMATION RES INST CAS
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] To sum up, most of the existing research uses the characteristics of thermal infrared observations in a certain dimension (such as angle, band and time, etc.) Capability and applicability to meet the needs of product production

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
  • Multi-Algorithm Integration Algorithm of Surface Component Temperature Based on Bayesian Model Averaging Method
  • Multi-Algorithm Integration Algorithm of Surface Component Temperature Based on Bayesian Model Averaging Method
  • Multi-Algorithm Integration Algorithm of Surface Component Temperature Based on Bayesian Model Averaging Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be described in further detail below with reference to the accompanying drawings and specific embodiments.

[0035] like figure 1 The shown multi-algorithm ensemble algorithm for surface component temperature based on the Bayesian model averaging method includes the following steps:

[0036] I. Integrate the surface composition temperature inversion method into a unified framework, that is, according to the advantages and disadvantages of different algorithms, select the composition temperature inversion algorithm with strong representativeness and complementary relationship M={M i};

[0037] Remote sensing observation data includes visible light observation, thermal infrared observation, cloud mask, surface water vapor products, etc. The present invention mainly uses data from visible light observation, thermal infrared observation, cloud mask, and surface water vapor products.

[0038] II. Perform surface temperature inversion based on spl...

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 multi-algorithm integration algorithm of surface component temperature based on the Bayesian model averaging method, which comprises the following steps: I. performing surface temperature inversion based on split window algorithm or temperature emissivity separation algorithm; II. based on ground measurement and three-dimensional The data set simulated by the model DART, based on the method of Bayesian model averaging, evaluates the algorithm of multi-pixel, multi-angle, multi-temporal and multi-band inversion methods; III. Using multi-pixel, multi-angle, multi-temporal and The multi-band method retrieves the temperature of surface components (ie, vegetation and soil); IV. The weight factor of each sub-algorithm obtained through algorithm evaluation is used for inversion structure fusion, and the component temperature retrieval result of the integrated algorithm is obtained. The invention builds a multi-algorithm integration framework for component temperature inversion, reduces the uncertainty of single algorithm / single data source inversion, and improves the accuracy and stability of surface component temperature inversion.

Description

technical field [0001] The invention relates to an integration algorithm, in particular to a multi-algorithm integration algorithm of surface component temperature based on a Bayesian model averaging method. Background technique [0002] Surface temperature is an important input parameter in the process of energy balance and water cycle on the earth's surface. By means of remote sensing, large-area surface temperature information can be obtained. For stationary and polar orbiting satellites, the spatial resolution of thermal infrared pixels can reach 1 km or even 5 km. Mixed pixels are common, and the temperature difference between components within a pixel can reach 10K. Most of the existing surface temperature inversion algorithms are based on the average temperature of the entire pixel, which is difficult to reflect the temperature difference of the components within the pixel. In contrast, the physical meaning of component temperature inside a pixel is more clear, which...

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 Patents(China)
IPC IPC(8): G06F17/12G06F17/16G06F17/18G06K9/62
CPCG06F17/12G06F17/16G06F17/18G06F18/24155
Inventor 卞尊健历华杜永明曹彪肖青柳钦火
Owner AEROSPACE INFORMATION RES INST CAS
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap