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

BPNN-based NDVI prediction method for the grassland area of northern China

A forecasting method, a technology from northern China, applied in forecasting, neural learning methods, biological neural network models, etc., can solve problems such as the inability to accurately characterize the nonlinear variation characteristics of NDVI, and avoid ecological damage and economic losses, major environmental and economic losses. The effect of strategic value and academic significance

Active Publication Date: 2019-01-25
TIANJIN UNIV
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current prediction research on NDVI mainly uses the traditional linear statistical model, which cannot accurately characterize the nonlinear change characteristics of NDVI

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
  • BPNN-based NDVI prediction method for the grassland area of northern China
  • BPNN-based NDVI prediction method for the grassland area of northern China
  • BPNN-based NDVI prediction method for the grassland area of northern China

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0059] Based on the monthly average rainfall in the growing season from 1961 to 2015 and the monthly average NDVI in the growing season from 2000 to 2015 in the Hulunbuir Ewenki region, combined with the establishment method of the NDVI prediction model, the BPNN-based NDVI prediction method of the northern China grassland area proposed by the present invention Give a detailed explanation.

[0060] 1. Select the input variables of the prediction model, perform correlation analysis based on SPSS statistical software, and finally determine the input sequence P(t-1), P(t-2), P(t-3) corresponding to P(t);

[0061] 2. Obtain the training data and test data of the rainfall BPNN prediction model, according to figure 1 The process of importing the training data into the rainfall BPNN prediction model to train the rainfall BPNN prediction model;

[0062] 3. Determine the structure of the optimal model, figure 2 As shown, the input variables are determined to be P(t-1), P(t-2), P(t-3), that ...

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 BPNN-based NDVI prediction method for the grassland area of northern China, including: a BPNN prediction model of monthly average rainfall in the future annual growth seasonis established; the monthly average rainfall-NDVI mapping model for future growing seasons is established; The monthly average rainfall forecast value of the future growing season generated by the rainfall BPNN forecast model is substituted into the rainfall-NDVI mapping model, the NDVI monthly average forecast value in the future growth season is obtained. The invention can accurately predict theaverage value of the NDVI in the growing season (June to August), thereby realizing the evaluation of the number of grazable livestock (carrying capacity) in the future years according to the predicted value of the NDVI. The method is conducive to realizing the dynamic grazing strategy based on the predictable climatic conditions, so as to avoid the occurrence of overgrazing in the disaster years.

Description

Technical field [0001] The invention relates to the field of rainfall and NDVI prediction modeling, and more specifically, to a BPNN-based NDVI prediction method in the grassland areas of northern China. Background technique [0002] In the past 30 years, the grassland area in northern China has been degraded seriously. On the one hand, it is attributed to the rapid development of animal husbandry in the grassland area, that is, the continuous increase in overgrazing, resulting in a relatively obvious imbalance between grass yield and the number of livestock, and ultimately resulting in differences in grassland areas Degree of degradation and desertification. On the other hand, due to the abnormal annual changes in rainfall in the region, severe droughts (such as 2016) or floods (such as 2013) occurred in very few years, which seriously threatened the restoration and protection of the grassland ecological environment in the region, as well as grassland animal husbandry. Sustaina...

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): G06Q10/04G06N3/04G06N3/08
CPCG06N3/084G06Q10/04G06N3/044
Inventor 马建国吴淘锁傅海鹏白红梅
Owner TIANJIN 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