Method for predicting nitrogen, phosphorus and potassium contents of black soil by using aviation hyperspectral data

A black soil nitrogen, phosphorus and potassium, data prediction technology, applied in the measurement of color/spectral characteristics, etc., can solve the problems of secondary error of extraction results, excessive interference of final extraction results, low reliability, etc.

Active Publication Date: 2019-06-11
BEIJING RES INST OF URANIUM GEOLOGY
View PDF10 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that, on the one hand, the content of nitrogen, phosphorus and potassium is often very weak, and the characteristics on the spectrum are easily obliterated by other information, so the reliability of "spectrum or its transform

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 predicting nitrogen, phosphorus and potassium contents of black soil by using aviation hyperspectral data
  • Method for predicting nitrogen, phosphorus and potassium contents of black soil by using aviation hyperspectral data
  • Method for predicting nitrogen, phosphorus and potassium contents of black soil by using aviation hyperspectral data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0099] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0100] Such as figure 1 As shown, a method using aerial hyperspectral data to predict the content of nitrogen, phosphorus and potassium in black soil obtains the complete spectral data of black soil through normalized preprocessing of the original aerial hyperspectral data, and does not directly model the spectral data, but separately Calculate the statistics, eigenvalues ​​and information values ​​of spectra, and collect 18 parameter values ​​of spectral data. These parameter values ​​are modeled with the known test values ​​of nitrogen, phosphorus and potassium content in black soil, and after principal component analysis, least square regression, root mean square error evaluation and other processes, a model of nitrogen, phosphorus and potassium content is established to achieve fast, efficient and accurate Calculation results of ...

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 belongs to the technical field of information extraction methods, and particularly relates to a method for predicting nitrogen, phosphorus and potassium contents of black soil by using aviation hyperspectral data. The method includes the following steps of: step 1, data preprocessing, namely, preprocessing the hyperspectral data by using an FLAASH algorithm based on an MODTRAN4+ radiation transfer model, and performing abnormal band removal and normalization processing on the spectral data subjected to radiation correction and geometric correction; step 2, spectral parameter calculation, namely, calculating spectral parameter values of 3 categories including 18 subclasses, taking the calculated spectral parameter values as training data, and carrying out modeling with the assay content; and step 3, establishing a model, adopting a principal component analysis method, extracting factors with the maximum correlation between the soil nutrient content and the spectral parameters, establishing a regression equation by using a least square method, finally evaluating root-mean-square errors of a model prediction result, and analyzing the regression effect.

Description

technical field [0001] The invention belongs to the technical field of information extraction methods, and in particular relates to a method for predicting the content of nitrogen, phosphorus and potassium in black soil by using aerial hyperspectral data. Background technique [0002] The black soil in Northeast my country is rich in nutrients. With the deepening of soil digital mapping, precision agriculture and soil resource investigation, the introduction of aerial hyperspectral data and the provision of scientific prediction results have become a research hotspot. In recent years, hyperspectral remote sensing technology has played an increasingly important role in the quantitative remote sensing monitoring of soil composition due to its high spectral resolution, strong band continuity and high spatial resolution. Nitrogen, phosphorus, and potassium are mineral nutrients in soil that can be absorbed by plant roots directly or after transformation, and are important indica...

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): G01N21/31
Inventor 张东辉赵英俊秦凯赵宁博裴承凯张玉燕
Owner BEIJING RES INST OF URANIUM GEOLOGY
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