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

Soil organic carbon predication method based on geographically weighted regression

A technique of geographical weighting and regression method, applied in soil material testing, material inspection products, etc.

Active Publication Date: 2015-07-08
INST OF SOIL SCI CHINESE ACAD OF SCI
View PDF0 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In view of the above-mentioned technical problems, the technical problem to be solved by the present invention is to provide a method covering two key technical links of local regression multicollinearity diagnosis technology and multicollinearity comprehensive processing, which can solve the problem of independent variable collinearity in existing local regression predictive analysis. A Geographically Weighted Regression-Based Soil Organic Carbon Prediction Method for the Problem

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
  • Soil organic carbon predication method based on geographically weighted regression
  • Soil organic carbon predication method based on geographically weighted regression
  • Soil organic carbon predication method based on geographically weighted regression

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070]The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0071] The basic idea of ​​designing the soil organic carbon prediction method based on geographically weighted regression in the present invention is to complete the diagnosis and treatment of the collinearity problem between independent variable sets in the process of independent variable selection, processing and local regression, so as to realize the localization of different types of independent variables. In the regression process, the non-stationarity of the spatial relationship is detected and the target variable is predicted more efficiently and accurately; while ensuring the diagnosis of the local regression collinearity problem, by comparing a variety of local regression techniques, the trend term is analyzed based on the trend surface equation to eliminate the non-stationary Therefore, the spatial prediction accuracy of tar...

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 soil organic carbon predication method based on geographically weighted regression. The soil organic carbon predication method contains a multicollinearity diagnosis technology and a comprehensive processing method in local regression. The main method comprises the following steps: (a) integrating a pre-processing technology for independent variables in global regression and local regression predication methods; (b) performing comprehensive diagnosis and processing mechanism on the collinearity problem of the independent variables in the universal geographically weighted regression; (c) carrying out applicability analysis on the geographically weighted regression method in a specific data set; (d) selecting the optimal independent variable set by adopting a method; and (e) comprehensively considering the spatial trends of the residual errors of the different regression methods. The calculation efficiency and accuracy of spatial attribute predication are improved by the comprehensive consideration for the spatial trends of the residual errors through contrastive analysis for the different independent variable sets and the collinearity degrees of the different independent variable sets in the local regression.

Description

technical field [0001] The invention belongs to a spatial analysis method oriented to spatial attribute prediction, in particular to a soil organic carbon prediction method based on geographic weighted regression. Background technique [0002] In the field of spatial analysis research, observations of variables are usually sampled by specific geographic units. Therefore, this value usually changes with the change of geographic spatial location, and the relationship between independent variables also changes significantly. This change in the relationship or structure between variables caused by changes in geographic location is called spatial non-stationarity. In geographic statistics and economic statistics, spatial non-stationarity is mainly attributed to three reasons: (1) caused by random sampling errors; (2) caused by differences in natural geographical environment, social management systems, and human habits in different regions; ( 3) The model used to analyze the spat...

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): G01N33/24
Inventor 宋效东刘峰张甘霖赵玉国李德成杨金玲吴华勇
Owner INST OF SOIL SCI CHINESE ACAD OF SCI
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