CN108007916B - Confocal micro-Raman measurement model for establishing nitrogen content of rice plant by Hilbert-Huang method - Google Patents
Confocal micro-Raman measurement model for establishing nitrogen content of rice plant by Hilbert-Huang method Download PDFInfo
- Publication number
- CN108007916B CN108007916B CN201710156394.3A CN201710156394A CN108007916B CN 108007916 B CN108007916 B CN 108007916B CN 201710156394 A CN201710156394 A CN 201710156394A CN 108007916 B CN108007916 B CN 108007916B
- Authority
- CN
- China
- Prior art keywords
- hilbert
- spectrum
- nitrogen content
- nitrogen
- raman
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/65—Raman scattering
Abstract
The invention discloses a confocal micro-Raman measurement model for establishing the nitrogen content of rice plants by a Hilbert-Huang method, belonging to the technical field of measurement of trace elements in crops. According to the requirement of a measurement target, 5 functional modules are constructed: the system comprises a spectrum acquisition module, a spectrum preprocessing module, a spectrum decomposition and training module, a Hilbert-Huang transform module and a mode recognition module. The main function of the method is to collect the rice plant spectrum by using a confocal micro-Raman spectrometer; denoising and baseline correction are carried out on the spectral data by applying a wavelet decomposition algorithm; decomposing the spectral data by using a global average empirical mode method to obtain characteristic modal components, and obtaining nitrogen element associated components through neural network training and recognition; obtaining nitrogen characteristic frequency from the marginal spectrum by using Hilbert-Huang transform; and establishing a least square measurement model of the characteristic frequency and the nitrogen content. The invention uses nitrogen marginal spectrum frequency to participate in modeling, has clear measurement mechanism, and has the characteristics of high measurement precision and short test time.
Description
Technical Field
The invention relates to a confocal micro-Raman spectrum measurement method for establishing the nitrogen content of a rice plant by a Hilbert-Huang method, belonging to the technical field of measurement of trace elements in crops.
Background
The traditional detection method of nitrogen level comprises a soil index method, a biochemical determination method and an empirical method. The soil index method is to supplement fertilizer to rice according to the nitrogen content in soil, namely a soil testing formula. The biochemical determination method is the main experimental method for detecting the nitrogen of the rice at present, and comprises a formaldehyde method, a Kjeldahl nitrogen determination method, a Dumas combustion nitrogen determination method and the like. The technical means or indexes of the empirical detection are mainly divided into three categories: visual inspection, remote spectrum sensing, and machine vision. The visual inspection method uses the abnormal color of the leaves as an index to diagnose the disease condition according to the production experience, and is a widely adopted detection means at present. The spectrum remote sensing method is characterized in that the spectrum of the rice field canopy is used as an analysis object, and the standard spectrum is compared to realize nitrogen deficiency detection. The machine vision method mainly uses a PC to distinguish the slight color difference between diseased rice and healthy rice plants from images, and is a digital extension of the visual method. In the method, only when rice has diseases, the spectrum remote sensing method and the machine vision method can be used for effective detection, namely, early measurement is difficult. Experience shows that after the rice shows the nitrogen deficiency symptom, the dosage of the additional fertilizer is at least doubled and obviously influences the growth of seedlings, so that the early detection of the nitrogen deficiency disease is very important. The soil index method is predictive, but the nitrogen in the rice seedlings is related to the nitrogen content in the soil, is influenced by illumination, temperature and humidity, soil pH value and the like, is a multi-factor constraint variable, and is an indirect measurement means with low measurement precision. The biochemical determination method is accurate and reliable, but has complex operation and low efficiency, can not carry out scale and rapid measurement and is mainly used in a control experiment. In the current rice nitrogen deficiency detection, although the visual detection method has large error, the operation is simple, and the method is the most widely applied detection means. There are two disadvantages to manual visual inspection: (1) the color of the rice plant needs to be observed according to experience by manual visual observation, and the judgment result is greatly influenced by subjective factors. When two or more nutrient elements are simultaneously deficient, the color of pathological changes is affected in a crossed manner, so that the visual inspection method cannot effectively judge the color. (2) Only serious nitrogen deficiency lesions can be observed by manual visual inspection. The change of rice plant expression is not obvious in early stage or light degree of pathological changes, but the change has serious influence on plant photosynthesis physiology and the like, and visual observation is difficult.
Disclosure of Invention
The invention aims to solve the problems in the prior art, and researches a confocal microscopic Raman spectrum measurement model for analyzing the nitrogen content in rice plants based on a Hilbert-Huang method, and the model can accurately, quickly and early measure the nitrogen level in the rice plants.
To achieve the above object, the present invention is achieved by the following steps:
(1) firstly, acquiring a confocal microscopic Raman spectrum of a rice plant;
(2) then preprocessing the confocal micro-Raman spectrum data;
(3) then, carrying out self-adaptive decomposition on the confocal micro-Raman spectrum signal, and carrying out correlation identification on each decomposition component and nitrogen to obtain a correlation signal;
(4) then performing Hilbert-Huang transformation on the correlation signals to obtain nitrogen characteristic frequency;
(5) and establishing a correlation characteristic frequency and nitrogen content chemometric measurement model.
[ detailed description ] embodiments
The following provides a specific implementation mode of the method for measuring the nitrogen content in the rice plant based on the confocal micro-Raman spectrum frequency method.
In a laboratory, under the constant temperature environment of 25 ℃, the rice leaves are pressed for 1 hour by a pressing glass sheet, and 0.5 × 0.5cm is cut from the middle part of the position 1cm away from the leaf apex2Leaf sample, placing the leaf sample between a glass slide and a cover glass, placing the leaf sample on an objective table below an objective lens of a micro-Raman spectrometer, scanning the sample with the horizontal and vertical step lengths of 1.2 mu m to obtain a spatial micro-Raman spectrum image of the sample, and expressing a standard image of the rice leaf sample by using average values of a plurality of images; denoising and baseline drift removal processing are carried out on the confocal micro-Raman spectrum by using a wavelet decomposition method; performing ensemble average empirical mode decomposition on the confocal micro-Raman spectrum signal, and applying neural network training and identification to obtain a nitrogen correlation signal; performing Hilbert-Huang transform on the correlation signals, and obtaining nitrogen characteristic frequency through marginal spectrum; and finally, establishing a least square measurement model of the characteristic frequency and the nitrogen content.
The method has the advantages that the spectrum characteristic modal component obtained by overall average empirical mode decomposition is subjected to neural network identification, irrelevant or weakly relevant components are removed, a nitrogen related characteristic modal component is obtained, further Hilbert-Huang transformation is carried out, the inherent characteristic modal component in the spectrum is obtained, the characteristic modal component is nitrogen covalent bond vibration single-frequency direct expression, and the frequency component obtained by comparing the Hilbert-Huang transformation has practical significance, so that the frequency characteristic index is not influenced by superposition of characteristic peaks of other trace elements, and the method has specificity and high identification precision and is suitable for trace element measurement in plants.
Drawings
FIG. 1 is a functional block diagram of a method.
Detailed Description
The embodiments of the present invention will be described in detail below with reference to the accompanying drawings:
1. functional block diagram of method
The method is designed in a modularized mode so as to be convenient to adjust, reusable, easy to modify and easy to expand. According to the measurement target requirement, namely the rice plant leaf confocal micro-Raman spectrum processing and modeling process, 5 functional modules are constructed: the system comprises a spectrum acquisition module, a spectrum preprocessing module, a spectrum decomposition and training module, a Hilbert-Huang transform module and a mode identification module, as shown in figure 1.
The spectrum acquisition module realizes parameter adjustment, state setting, sample preparation, spectrum acquisition and data storage of the spectrum instrument; the spectrum preprocessing module provides a spectrum preprocessing algorithm, including denoising and baseline correction; the spectrum decomposition and training module is used for decomposing the Raman spectrum, training and identifying to obtain the related components of the nitrogen; the Hilbert-Huang transform module converts the wavelength characteristic modal component into a frequency characteristic index; the mode identification module adopts a least square method to establish a nitrogen content measurement model.
2. Key technology
2.1 wavelet decomposition denoising and de-baseline Drift
There are two types of noise in confocal micro-raman spectroscopy, electronic thermal motion noise from the instrument and external communication system interference. The existence of noise greatly affects the interpretation of the true information of the spectrum, so the signal noise reduction plays a significant role in spectrum analysis.
Signal reconstruction is performed by using sym1, sym2, sym3, sym4, sym5, sym6, sym7, sym8, db1, db2, db3, db4, db5, db6, db7, db8, db9, coif1, coif2, coif3, coif4 and coif5 wavelet basis functions respectively, and different threshold estimation methods Hcursucurc, Sqtwolog, Rigrsucrc, Minimaxi and n (1-10) are used for signal reconstruction, and in the present invention, for the confocal microscopy baseline Raman spectrum of rice leaves, the denoising and denoising parameters are preferably set as: basis functions sym5, sym6, sym7, db6, db 7; threshold estimation methods hcursrc, Sqtwolog; the number of decomposition layers was 5.
2.2 ensemble averaged empirical mode decomposition confocal microscopy Raman Spectroscopy
The empirical mode decomposition method can decompose signals in a self-adaptive mode according to different frequencies, but the problem of mode aliasing occurs in the process of decomposing the confocal micro-Raman spectrum.
And (3) ensemble average empirical mode decomposition:
step 1: adding equal-length unequal-amplitude Gaussian white noise into the confocal micro-Raman spectrum to be processed, carrying out empirical mode decomposition on the composite signal, and repeating the operation k times to obtain characteristic modal componentsAnd remainder。
Empirical mode decomposition:
step a: obtaining a maximum envelope u (t) and a minimum envelope v (t) of the confocal microscopic Raman spectrum x (t) through a cubic spline function, wherein the mean value is recorded as m (t):
step b: let r (t) = x (t) -m (t), if r (t) does not satisfy the characteristic modal component condition, assign it to x (t). Returning to the step 1, circularly calculating
Step d: returning to the step 1 to continue screeningIn turn obtain,,…,. Judge the remainderThe screening process stops when there is little or substantially a monotonic trend.
Step 2: the ensemble average of the characteristic modal components is taken,
Identification of characteristic modal components by neural network trainingThe degree of association with nitrogen element, and the threshold value is set to screen out the associated characteristic frequency component. The neural network in the invention adopts a BP type structure, and the parameters are set as follows: the number of input layer neurons is determined by the characteristic modal components, in this example, the input feature vector isData; the output layer adopts 1 node, and 0 and 1 respectively represent that the nitrogen characteristic modal component is false and true; the selection of the number of nodes of the hidden layer has great influence on the performance of the network, the number of nodes is too small, the nodes are easy to fall into local minimum values, the number of the hidden nodes is too large, a fitting function is complex, the generalization capability of the network is poor, and test results show that the number of the nodes of the optimal hidden layer ranges from 8 to 12 (according to different values of n and m); selecting a logsig () function as an activation function of a neuron in a hidden layer, and selecting a pureline () function as an activation function of an output layer; the number of iterations is set to 1000, the network is trained 1 time every 10 steps, the target value is 0.01, the learning rate is 0.1, and the function of rainlm () is used as the training network.
2.3 Hilbert-Huang transform and model building
Correlating characteristic modal components withPerforming convolution integral operation on the signal to obtain the Hilbert-Huang instantaneous frequency of the associated characteristic modal componentThe marginal spectrum of each hilbert instantaneous frequency is calculated according to equation (6).
In the formulaIs the marginal spectrum of the kth component of the confocal micro-raman spectrum. And (3) establishing a partial least square fitting model by taking each frequency amplitude in the marginal spectrum as an input variable and the nitrogen content as an output variable, so as to realize the measurement of the nitrogen content in the rice.
Therefore, the method disclosed by the embodiment of the invention establishes the nitrogen content measurement model in the rice by using the Hilbert-Huang method, is different from a black box modeling method, directly participates in modeling by using the marginal spectrum frequency of nitrogen element, has a clear model measurement mechanism, and has the characteristics of high measurement precision and short test time. The invention is suitable for early detection of nitrogen deficiency diseases of crops such as rice and the like and can provide scientific basis for precision agriculture.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (5)
1. The Hilbert-Huang method is used for establishing a confocal microscopic Raman measurement model of the nitrogen content of the rice plant, and is characterized by being realized by the following steps:
(1) firstly, acquiring a confocal microscopic Raman spectrum of a rice plant;
(2) then preprocessing the confocal micro-Raman spectrum data;
(3) then, carrying out self-adaptive decomposition on the confocal micro-Raman spectrum signal by using a global average empirical mode method to obtain characteristic modal components, and identifying each decomposition component by using neural network training to obtain a nitrogen correlation signal;
(4) then performing Hilbert-Huang transformation on the correlation signals to obtain nitrogen characteristic frequency;
(5) and establishing a correlation characteristic frequency and nitrogen content chemometric measurement model.
2. The hilbert yellow method of claim 1, wherein the model is a confocal micro-raman measurement model for nitrogen content of rice plants, and is characterized in that:
in a laboratory, under the constant temperature environment of 25 ℃;
pressing the rice leaf for 1 hour by using a press glass sheet, and cutting 0.5 × 0.5.5 cm from the middle part of the position 1cm away from the leaf tip2Leaf samples;
placing the leaf sample between a glass slide and a cover glass, placing the leaf sample on an objective table below an objective lens of a micro-Raman spectrometer, and scanning the sample in transverse and longitudinal steps of 1.2 mu m to obtain a spatial micro-Raman spectrum image of the sample;
the rice leaf-like standard image is represented by the average value of a plurality of images.
3. The hilbert yellow method of claim 1, wherein the model is a confocal micro-raman measurement model for nitrogen content of rice plants, and is characterized in that:
denoising the confocal micro-Raman spectrum by using a wavelet decomposition method;
and removing the base line drift of the confocal micro-Raman spectrum by using a wavelet decomposition method.
4. The hilbert yellow method of claim 1, wherein the model is a confocal micro-raman measurement model for nitrogen content of rice plants, and is characterized in that:
and performing Hilbert-Huang transform on the correlation signals, and obtaining the nitrogen characteristic frequency through marginal spectrum.
5. The hilbert yellow method of claim 1, wherein the model is a confocal micro-raman measurement model for nitrogen content of rice plants, and is characterized in that:
and establishing a characteristic frequency and nitrogen content measurement model by using a least square method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710156394.3A CN108007916B (en) | 2017-03-16 | 2017-03-16 | Confocal micro-Raman measurement model for establishing nitrogen content of rice plant by Hilbert-Huang method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710156394.3A CN108007916B (en) | 2017-03-16 | 2017-03-16 | Confocal micro-Raman measurement model for establishing nitrogen content of rice plant by Hilbert-Huang method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108007916A CN108007916A (en) | 2018-05-08 |
CN108007916B true CN108007916B (en) | 2020-08-04 |
Family
ID=62048653
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710156394.3A Expired - Fee Related CN108007916B (en) | 2017-03-16 | 2017-03-16 | Confocal micro-Raman measurement model for establishing nitrogen content of rice plant by Hilbert-Huang method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108007916B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20230184684A1 (en) * | 2020-05-21 | 2023-06-15 | Temasek Life Sciences Laboratory Limited | Early diagnosis and management of nitrogen deficiency in plants utilizing raman spectroscopy |
CN113049500B (en) * | 2021-03-19 | 2022-12-06 | 杭州海康威视数字技术股份有限公司 | Water quality detection model training and water quality detection method, electronic equipment and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101382488A (en) * | 2008-10-14 | 2009-03-11 | 江苏吟春碧芽茶叶研究所有限公司 | Method for detecting nitrogen content in fresh tea by visible light-near infrared diffuse reflection spectrum technology |
CN101424637A (en) * | 2008-12-04 | 2009-05-06 | 浙江大学 | Remote sensing appraising model method for leave nitrogen content of rapes |
CN103674929A (en) * | 2013-12-25 | 2014-03-26 | 黑龙江八一农垦大学 | Health examination method for plant seedlings by using spectral analysis |
KR20140038213A (en) * | 2012-09-20 | 2014-03-28 | 주식회사 스마테움 | Methods for assessing virus infections against a plant using raman spectroscopy and chemometrics |
CN103729688A (en) * | 2013-12-18 | 2014-04-16 | 北京交通大学 | Section traffic neural network prediction method based on EMD |
CN105203495A (en) * | 2015-09-11 | 2015-12-30 | 天津工业大学 | Spectrum signal denoising method based on Hilbert-Huang transformation |
US9403833B2 (en) * | 2014-05-14 | 2016-08-02 | Novartis Ag | Carboxamide derivatives |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8326404B2 (en) * | 2003-11-28 | 2012-12-04 | British Columbia Cancer Agency Branch | Multimodal detection of tissue abnormalities based on raman and background fluorescence spectroscopy |
CN102374971A (en) * | 2010-08-09 | 2012-03-14 | 中国农业大学 | Method for estimating LNC (leaf nitrogen content) of corns based on hyperspectral technique |
US20120092663A1 (en) * | 2010-10-14 | 2012-04-19 | Kull Linda S | Transmission raman spectroscopy analysis of seed composition |
CN102788752B (en) * | 2012-08-08 | 2015-02-04 | 江苏大学 | Non-destructive detection device and method of internal information of crops based on spectrum technology |
CN106290292B (en) * | 2016-07-25 | 2018-12-28 | 浙江大学 | A method of carotenoid content in tealeaves is detected using burnt microscopic Raman is copolymerized |
-
2017
- 2017-03-16 CN CN201710156394.3A patent/CN108007916B/en not_active Expired - Fee Related
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101382488A (en) * | 2008-10-14 | 2009-03-11 | 江苏吟春碧芽茶叶研究所有限公司 | Method for detecting nitrogen content in fresh tea by visible light-near infrared diffuse reflection spectrum technology |
CN101424637A (en) * | 2008-12-04 | 2009-05-06 | 浙江大学 | Remote sensing appraising model method for leave nitrogen content of rapes |
KR20140038213A (en) * | 2012-09-20 | 2014-03-28 | 주식회사 스마테움 | Methods for assessing virus infections against a plant using raman spectroscopy and chemometrics |
CN103729688A (en) * | 2013-12-18 | 2014-04-16 | 北京交通大学 | Section traffic neural network prediction method based on EMD |
CN103674929A (en) * | 2013-12-25 | 2014-03-26 | 黑龙江八一农垦大学 | Health examination method for plant seedlings by using spectral analysis |
US9403833B2 (en) * | 2014-05-14 | 2016-08-02 | Novartis Ag | Carboxamide derivatives |
CN105203495A (en) * | 2015-09-11 | 2015-12-30 | 天津工业大学 | Spectrum signal denoising method based on Hilbert-Huang transformation |
Non-Patent Citations (4)
Title |
---|
Elastic properties and surface damage resistance of nitrogen-rich;Pathikumar Sellappan;《Journal of Non-Crystalline Solids》;20100930;第356卷(第41期);全文 * |
Estimation of sugarcane leaf nitrogen concentration using in situ spectroscopy;Elfatih M;《International Journal of Applied Earth Observation and》;20101231;第12S卷;全文 * |
基于希尔伯特解调的LFM信号调频斜率的识别;高洪青;《计算机测量与控制》;20161231;第24卷(第9期);全文 * |
基于拉曼光谱分析寒地水稻叶瘟病害植株特征;谭峰;《农业工程学报》;20150228;第31卷(第4期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN108007916A (en) | 2018-05-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102879353B (en) | The method of content of protein components near infrared detection peanut | |
CN102721651B (en) | Detection method and system of water content in plant leaf based on multispectral image | |
CN107796764B (en) | Method for constructing wheat leaf area index estimation model based on three-band vegetation index | |
CN103940748B (en) | Based on the prediction of oranges and tangerines canopy nitrogen content and the visualization method of hyperspectral technique | |
CN101915738A (en) | Method and device for rapidly detecting nutritional information of tea tree based on hyperspectral imaging technique | |
CN101210875A (en) | Damage-free measurement method for soil nutrient content based on near infrared spectra technology | |
CN107271382A (en) | A kind of different growing rape leaf SPAD value remote sensing estimation methods | |
CN107607486B (en) | Soil total nitrogen detection method and device | |
CN108007917B (en) | Method for establishing Raman spectrum measurement model of nitrogen content in rice plant by Hilbert method | |
CN104778349B (en) | One kind is used for rice table soil nitrogen application Classified Protection | |
CN108007916B (en) | Confocal micro-Raman measurement model for establishing nitrogen content of rice plant by Hilbert-Huang method | |
CN111855593A (en) | Remote sensing inversion model and method for starch content of rice leaf | |
CN110333195A (en) | Water content in plant leaf detection method and device | |
CN110363119A (en) | Based on wavelet transformation-random forests algorithm tobacco mildew method for quickly identifying | |
Wu et al. | Study on the optimal algorithm prediction of corn leaf component information based on hyperspectral imaging | |
CN107202784B (en) | Method for detecting process nodes in rice seed soaking and germination accelerating process | |
CN109142238B (en) | Cotton phosphorus nutrition rapid diagnosis method | |
Wang et al. | Intelligent detection of hard seeds of snap bean based on hyperspectral imaging | |
Peng et al. | Estimating total leaf chlorophyll content of gannan navel orange leaves using hyperspectral data based on partial least squares regression | |
CN110596048A (en) | Method for quickly measuring potassium content in tobacco leaves by spectrum | |
CN114676636A (en) | Grassland area soil moisture rapid inversion method integrating vegetation and habitat characteristics | |
Yang et al. | Classification of sugar beets based on hyperspectral and extreme learning machine methods | |
CN113065230B (en) | High-spectrum inversion model for establishing rice leaf SPAD based on optimized spectral index | |
CN112651173B (en) | Agricultural product quality nondestructive testing method based on cross-domain spectral information and generalizable system | |
Liu et al. | Estimation of chlorophyll content in maize canopy using wavelet denoising and SVR method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200804 |