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

Multi-time sequence image rice yield estimation method based on crop phenological period

A multi-time series and phenological period technology, applied in neural learning methods, biological neural network models, instruments, etc., can solve problems such as lack of consideration, inaccurate inversion result accuracy, and unstable models, so as to achieve accurate models and avoid cost investment oversized, cost-reducing effect

Pending Publication Date: 2021-05-25
哈尔滨航天恒星数据系统科技有限公司
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to solve the problems of inaccurate accuracy of inversion results, unstable models and failure to consider the influence of growth, disasters and soil moisture, the present invention proposes a multi-time-series image rice yield estimation method based on crop phenology, and the specific scheme of the method For: the method steps are as follows:

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-time sequence image rice yield estimation method based on crop phenological period
  • Multi-time sequence image rice yield estimation method based on crop phenological period
  • Multi-time sequence image rice yield estimation method based on crop phenological period

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0045] Specific embodiment one: the present embodiment uses the vegetation index (NDVI, GNDVI, EVI, VCI) of rice phenology stage (tillering stage, heading stage, filling stage, maturity stage), rice growth grade data (1-11 grade), rice Disaster grade data (level 1-5), soil moisture data (soil moisture content) and field yield measurement data, conduct model training, establish the optimal model, use the optimal model combined with the image of the target area to estimate the rice yield, and obtain the yield level of the target area Distribute raster data. This method fully considers the monitoring of rice growth status, disasters affecting rice growth, water content, phenological period and other factors, and uses multi-time series images to estimate yield, which provides a new idea and method for accurate crop yield estimation. The specific features are as follows :

[0046] Feature 1: Use ENVI5.3 software to complete satellite image preprocessing to obtain reflectivity data...

specific Embodiment approach 2

[0066] Specific implementation mode two: adopt the BP neural network algorithm, use matlab2019a software programming, GUI design to establish the rice yield estimation model, the present embodiment provides a kind of multi-time series image rice yield estimation method based on the crop phenology period, use the rice phenology period (tillering stage, Heading stage, filling stage, maturity stage) vegetation index (NDVI, GNDVI, EVI, VCI), rice growth grade data (1-11 grade), rice disaster grade data (1-5 grade), soil moisture data (soil moisture content ) and field yield measurement data, conduct model training, establish the optimal model, use the optimal model combined with the image of the target area to estimate the rice yield, and obtain the raster data of the yield grade distribution in the target area. This method fully considers the monitoring of rice growth status, disasters affecting rice growth, water content, and phenological period, and uses multi-time series images...

specific Embodiment approach 3

[0070] Specific implementation method three: In addition to the yield estimation method described in Embodiment 1 or 2, the yield estimation process can also be subdivided into 7 stages: the raw data acquisition and processing stage, the rice distribution extraction stage in the target area, the vegetation index extraction stage, and the growing condition / disaster / soil moisture data extraction stage, BP neural network method production estimation model construction stage, model training input and target parameter extraction stage, model training and verification stage, the following is the specific implementation process of each stage:

[0071] 1. Raw data acquisition and processing stage:

[0072] On-site sample collection is carried out according to the requirements of on-site yield measurement, and the on-site yield measurement data is sent to the laboratory to measure the dry grain weight to obtain on-site yield data.

[0073] Obtain the image data of the tillering stage,...

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-time sequence image rice yield estimation method based on a crop phenological period, belongs to the technical field of remote sensing technology and crop yield estimation, and aims to solve the problems that the precision of an inversion result is inaccurate, a model is unstable, and the influence of growth vigor, disasters and soil moisture content is not considered. According to the method, a BP neural network algorithm is adopted, matlab2019b programming and GUI design are applied to establish a rice yield estimation model, model training is performed by applying a vegetation index of a rice phenological period, rice growth trend grade data, rice disaster grade data, soil moisture content data and field yield estimation data, an optimal model is established, the optimal model is combined with a target area image to perform rice yield estimation, and the output grade distribution grid number of the target area is obtained. The remote sensing technology is used for processing satellite image data and extracting vegetation indexes, growth vigor, disasters and soil moisture content, the yield of a target area is inversed, the production cost is saved, the production efficiency is improved, and meanwhile the purpose of accurately estimating the yield is achieved.

Description

technical field [0001] The invention relates to a method for estimating rice yield based on multi-time series images of crop phenology, in particular to a method for estimating rice yield based on multi-time series images, and belongs to the technical fields of remote sensing technology and crop yield estimation. Background technique [0002] In recent years, with the development of space technologies such as satellite remote sensing and UAV remote sensing, digital agricultural technology has been greatly improved, and the application of remote sensing technology to precision agriculture has gradually emerged. The method in the article "Rice Remote Sensing Yield Estimation Method Based on Relative Remote Sensing Variables and Relative Yield Information" is based on a well-planted and well-growing field in the study area as the reference field, using three stages of gestation, heading, and milk maturity. Based on the relative remote sensing variables and relative production o...

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): G06K9/00G06K9/20G06N3/04G06N3/08
CPCG06N3/084G06V20/188G06V10/143G06N3/044Y02A40/10
Inventor 宋振强王众娇高磊翟建宝刘彤赵博文潘拓
Owner 哈尔滨航天恒星数据系统科技有限公司
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