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

Identification method for rice leaves contaminated by heavy metals based on near infrared spectroscopy

A near-infrared spectroscopy and heavy metal technology is applied in the field of heavy metal pollution detection of plants, which can solve the problems of high instrument requirements, high detection cost, cumbersome preprocessing operation, etc., and achieves the effects of high identification accuracy, low cost, and non-destructive detection.

Inactive Publication Date: 2012-12-19
CHINA JILIANG UNIV +1
View PDF6 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of these methods have high requirements for instruments, and there are disadvantages such as cumbersome pretreatment operations and high detection costs.

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
  • Identification method for rice leaves contaminated by heavy metals based on near infrared spectroscopy
  • Identification method for rice leaves contaminated by heavy metals based on near infrared spectroscopy
  • Identification method for rice leaves contaminated by heavy metals based on near infrared spectroscopy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] 1. Build a model

[0037] (1) Set the mercury content to 1.5mg·Kg respectively -1 , containing cadmium 1.0mg·Kg -1 , lead 500mg·Kg -1 1. Four soils that do not contain heavy metals, and rice is planted on the four soils; rice is selected from 11 seeds of Zhonghua, and after 15 days of raising seedlings, transplant the seedlings in the three soils with heavy metal content, apply enough base fertilizer, irrigate in time, and regularly Apply nitrogen and compound fertilizers.

[0038] (2) When the rice is at the five-leaf stage, 20 rice leaf samples are collected from four soils as a calibration set, and the Nicolet Nexus870 (Thermo Corporation USA) Fourier transform near-infrared spectrometer is used to transmit to the back of the rice leaf samples The range of wave number is 4000~12000cm -1 near-infrared spectrum, and collect the diffuse reflectance spectrum information of all rice leaf samples; the near-infrared spectrometer sets the number of scans to 32 times, and...

Embodiment 2

[0059] 1. Model establishment

[0060] (1)~(2) are with embodiment 1;

[0061] (3) Use the wavelet function Daubechies 2 (Db2), set the decomposition level to 2, process the diffuse reflectance spectra of all the collected rice samples, and obtain the corresponding 1039 wavelet features. The wavelet eigenvalues ​​of the rice samples are shown in Table 4; The original diffuse reflectance spectra and wavelet reconstructed diffuse reflectance spectra of all rice sample leaves are as follows: image 3 , Figure 4 It can be seen from the figure that the processed spectrogram retains the basic spectral information.

[0062] (4) Take the wavelet feature of the rice leaf sample obtained in step (3) as input, and take the leaf pollution type setting value corresponding to the rice leaf sample as the output, and set four pollution types: mercury pollution, cadmium pollution, lead pollution and normal The set values ​​of output are 1, 2, 3, 4 respectively, and the BP neural network mo...

Embodiment 3

[0079] 1. Build a model

[0080] (1)~(2) steps are with embodiment 1;

[0081] (3) Use the wavelet function Daubechies 2 (Db2), set the decomposition level to 4, process the diffuse reflectance spectrum information of all collected rice leaf samples, and obtain the corresponding 262 wavelet features; the original diffuse reflectance spectra of all rice leaf samples Figure and wavelet reconstructed diffuse reflectance spectrum as shown in Figure 5 , Image 6 As shown in the figure, it can be seen from the figure that the processed spectrogram retains the basic spectral information;

[0082] (4) Take the wavelet feature of the rice leaf sample obtained in step (3) as input, and take the leaf pollution type setting value corresponding to the rice leaf sample as the output, and set four pollution types: mercury pollution, cadmium pollution, lead pollution and normal The set values ​​of output are 1, 2, 3, 4 respectively, and the RBF neural network model is established.

[008...

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 an identification method for rice leaves contaminated by heavy metals based on near infrared spectroscopy. The method comprises the following steps: (1) collecting four kinds of rice leaf samples, emitting a near infrared spectrum with a wave number in a range of 4000 to 12000 / cm to back sides of the rice leaf samples and collecting diffuse reflection spectrum information of all the rice leaf samples; (2) respectively processing the diffuse reflection spectrum information of all the rice leaf samples by using a wavelet transformation method so as obtain corresponding wavelet features; (3) establishing a neural network model with the wavelet features of the rice leaf samples as input and set values of pollution types corresponding to the rice leaf samples as output; and (4) substituting the wavelet features obtained after the step (1) and step (2) into the neural network model obtained in step (3) so as to obtain pollution types of rice to be identified. The identification method provided by the invention has the advantages of high precision, simple operation, low cost and capacity of realizing rapid and nondestructive identification of heavy metal pollution in rice.

Description

technical field [0001] The invention belongs to the field of heavy metal pollution detection of plants, and in particular relates to a method for identifying rice leaves polluted by heavy metals based on near-infrared spectroscopy. Background technique [0002] Due to the progress of industrial society, mining and industrial "three wastes", large-scale application of chemical fertilizers and pesticides have increased the content of heavy metals in farmland soil, seriously threatening plant growth and environmental quality. Rice is an important food crop in my country, and the safety of rice production is related to the national economy and people's livelihood. [0003] At present, a large number of rice fields in my country have been polluted by toxic heavy metals, which not only affects the growth and development of rice, reduces yield and quality, but also heavy metals absorbed by rice enter the human body from the food chain, seriously affecting human health. Lead, cadmi...

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): G01N21/25
Inventor 朱诚张龙潘家荣赵鹂
Owner CHINA JILIANG 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