CN107796779A - The near infrared spectrum diagnostic method of rubber tree LTN content - Google Patents
The near infrared spectrum diagnostic method of rubber tree LTN content Download PDFInfo
- Publication number
- CN107796779A CN107796779A CN201711114947.5A CN201711114947A CN107796779A CN 107796779 A CN107796779 A CN 107796779A CN 201711114947 A CN201711114947 A CN 201711114947A CN 107796779 A CN107796779 A CN 107796779A
- Authority
- CN
- China
- Prior art keywords
- rubber tree
- nitrogen content
- near infrared
- tree leaf
- fractional order
- 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.)
- Pending
Links
- 244000043261 Hevea brasiliensis Species 0.000 title claims abstract description 109
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 25
- 238000002405 diagnostic procedure Methods 0.000 title abstract 2
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims abstract description 125
- 229910052757 nitrogen Inorganic materials 0.000 claims abstract description 63
- 238000001228 spectrum Methods 0.000 claims abstract description 40
- 230000003595 spectral effect Effects 0.000 claims abstract description 28
- 230000003044 adaptive effect Effects 0.000 claims abstract description 13
- 230000002860 competitive effect Effects 0.000 claims abstract description 13
- 238000012216 screening Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 39
- 238000003745 diagnosis Methods 0.000 claims description 24
- 238000001035 drying Methods 0.000 claims description 9
- 238000005303 weighing Methods 0.000 claims description 5
- 102000004190 Enzymes Human genes 0.000 claims description 4
- 108090000790 Enzymes Proteins 0.000 claims description 4
- 230000009849 deactivation Effects 0.000 claims description 4
- 241000238631 Hexapoda Species 0.000 claims description 3
- 241000607479 Yersinia pestis Species 0.000 claims description 3
- 201000010099 disease Diseases 0.000 claims description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 3
- 238000010238 partial least squares regression Methods 0.000 claims description 3
- 230000029087 digestion Effects 0.000 claims description 2
- 238000004611 spectroscopical analysis Methods 0.000 abstract 2
- 229920001971 elastomer Polymers 0.000 description 13
- 238000001514 detection method Methods 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 8
- 229920003052 natural elastomer Polymers 0.000 description 5
- 229920001194 natural rubber Polymers 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 235000016709 nutrition Nutrition 0.000 description 3
- 230000035764 nutrition Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 241000196324 Embryophyta Species 0.000 description 2
- 238000004497 NIR spectroscopy Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000000227 grinding Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000009659 non-destructive testing Methods 0.000 description 2
- 235000003715 nutritional status Nutrition 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 208000032544 Cicatrix Diseases 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009614 chemical analysis method Methods 0.000 description 1
- 229920003211 cis-1,4-polyisoprene Polymers 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000004836 empirical method Methods 0.000 description 1
- 230000004720 fertilization Effects 0.000 description 1
- 239000000383 hazardous chemical Substances 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 231100000241 scar Toxicity 0.000 description 1
- 230000037387 scars Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
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
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
-
- 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
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N31/00—Investigating or analysing non-biological materials by the use of the chemical methods specified in the subgroup; Apparatus specially adapted for such methods
- G01N31/002—Determining nitrogen by transformation into ammonia, e.g. KJELDAHL method
-
- 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
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
- G01N2021/3572—Preparation of samples, e.g. salt matrices
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Molecular Biology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides a kind of near infrared spectrum diagnostic method of rubber tree LTN content, including：First step：Choose rubber tree leaf sample；Second step：Gather the spectroscopic data of the near infrared band of rubber tree leaf sample；Third step：Rubber tree leaf sample is pre-processed, then determines the nitrogen content of pretreated rubber tree leaf sample；Four steps：Fractional order spectrum is obtained using the spectroscopic data of the near infrared band of the rubber tree leaf sample of collection；5th step：The foundation of model is carried out as independent variable using the spectral value corresponding to the mostly concerned wave band of the nitrogen content of the rubber tree leaf sample with measure in competitive adaptive weight weighting algorithm screening fractional order spectrum；6th step：The prediction of rubber tree leaf-nitrogen value content is carried out using the model of foundation.
Description
Technical Field
The invention relates to the technical field of near-infrared nondestructive testing; specifically, the invention relates to a near infrared spectrum diagnosis method of the nitrogen content of rubber tree leaves based on a fractional order algorithm, which utilizes a near infrared spectrum technology to carry out nondestructive detection on the nitrogen content of the rubber tree leaves.
Background
The rubber tree is an important economic crop in Hainan province, is also used as an important strategic material natural rubber source in China, and the nutritional status of the rubber tree is directly related to the yield of the natural rubber, the gum production amount, the gum production age of the rubber tree and the like. Therefore, the detection of the vegetative level of rubber trees is extremely important. Nitrogen is one of the most important nutrient elements of rubber trees, and the content of nitrogen is closely related to the growth of the rubber trees and the yield of natural rubber. The nitrogen content of the rubber trees can be timely and effectively mastered, and the method plays an important role in assessing the nutrition condition of the rubber trees, variably fertilizing and estimating the yield of rubber.
The traditional method for diagnosing the nitrogen nutrition of the rubber tree mainly adopts an experience judgment method, the subjective evaluation method is influenced by subjective conditions such as personal experience, emotion and fatigue degree, the error in the operation process is large, most of the subjective conditions stay in qualitative judgment, the subjectivity and the accuracy are poor, the development of the rubber industry in China is limited to a great extent, and the competitiveness is lacked in the international market. Another more accurate method is based on laboratory analysis of leaf tissue. The analysis method is destructive to rubber blade samples, and laboratory analysis methods are subject to sample collection, drying, grinding, weighing, chemical analysis, and the like. These processes are time, labor and material intensive and also require hazardous chemicals and specialized analytical personnel and laboratory facilities. Therefore, the traditional laboratory analysis method cannot meet the detection requirement of the nutrition level of a large number of rubber trees. The spectral analysis method is one of effective alternative means of an empirical method and a traditional laboratory analysis method as a rapid and efficient detection method. The application of the spectrum technology to the diagnosis of the nitrogen level of crops has been deeply researched, but the existing research is mostly focused on annual crops and partial fruit trees, and the obtained result cannot be directly suitable for economic crops, namely rubber trees. The research on the spectral diagnosis model of the nitrogen content of the rubber tree is of great significance.
Integral second order differential is one of the most common processing means in the spectrum data preprocessing, and meanwhile, the spectrum differential technology is an analysis method with high application value in the spectrum data preprocessing. The first order differential has better effect on eliminating the influence of partial linear or nearly linear noise spectrum, background and the like on the target spectrum; the second order differential corresponding to the first order differential is excellent for eliminating the baseline drift and the background noise and improving the analysis accuracy. Fractional calculus has been a classic problem for over 300 years. The occurrence of the method expands calculus from an integer order field to a non-integer order field. Due to the introduction of non-integer order, fractional calculus has better interpretation and extraction capability on spectral features compared with traditional two-order differentiation. The introduction of the fractional order algorithm can facilitate the provision of a spectral diagnostic model more suitable for the leaf nitrogen content of the rubber tree.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a near infrared spectrum diagnosis method for the nitrogen content of rubber tree leaves, which is used for establishing a spectrum diagnosis model of the nitrogen content of the rubber tree leaves, applying a fractional order algorithm to the establishment process of the model and considering the influence of background noise and the difference of the fractional order on the model precision so as to realize the rapid, accurate and real-time nondestructive detection of the nitrogen content of the rubber tree leaves; the method solves the defects that the existing rubber tree nitrogen diagnosis technology is time-consuming, labor-consuming, complex in laboratory operation, environment-friendly, high in cost and the like.
According to the invention, the near infrared spectrum diagnosis method of the nitrogen content of the rubber tree leaves based on the fractional order algorithm is characterized by comprising the following steps:
the first step is as follows: selecting a rubber tree leaf sample;
the second step is as follows: collecting spectral data of a near infrared band of a rubber tree leaf sample;
the third step: pretreating a rubber tree leaf sample, and then determining the nitrogen content of the pretreated rubber tree leaf sample;
the fourth step: acquiring a fractional order spectrum by using the acquired spectral data of the near infrared wave band of the rubber tree leaf sample;
the fifth step: screening a spectrum value corresponding to a wave band most related to the measured nitrogen content of the rubber tree leaf sample in the fractional order spectrum by using a competitive adaptive reweighting algorithm, and taking the spectrum value as an independent variable to establish a model;
a sixth step: and predicting the nitrogen content of the rubber tree leaves by using the established model.
Preferably, the formula of the model is:
y＝α 0 +α 1 λ 1 +α 2 λ 2 ++α n λ n
wherein y is the nitrogen content of the rubber tree leaves; lambda [ alpha ] 1 ～λ n A spectrum value corresponding to the wave band selected by the competitive adaptive reweighting algorithm, n is the number of the characteristic wave bands selected by the competitive adaptive reweighting algorithm, alpha 0 ～α n Is a coefficient value trained by partial least squares regression.
Preferably, the fractional spectrum is calculated by the formula:
wherein x is a band value, v is a fractional order,h is the step size of the solution, where h =1, t and a are the upper and lower limits of the integral, respectively.
Preferably, the middle leaflet is selected from mature leaves which are free of plant diseases and insect pests and well grown as a leaf sample of the rubber tree.
Preferably, the rubber tree leaf samples are randomly selected from the field environment.
Preferably, the near infrared band is a band of 350nm to 2500 nm.
Preferably, when acquiring the spectral data, randomly selecting a predetermined number of points on the blade surface of the rubber tree blade sample to acquire each spectral data, and taking the average value of the acquired spectral data as the value of the final spectral data of the rubber tree blade sample.
Preferably, the pretreatment comprises the steps of carrying out enzyme deactivation, drying, crushing and sample weighing on the rubber tree leaf sample, and stewing.
Preferably, the water-removing temperature of the rubber tree leaf sample is 95-115 ℃, and the water-removing time is 20-40 min. The drying temperature is 70-90 ℃, and the leaves are dried to constant weight.
Preferably, the nitrogen content of the pretreated rubber tree leaf sample is determined by adopting a semi-micro Kjeldahl azotometer.
Drawings
A more complete understanding of the present invention, and the attendant advantages and features thereof, will be more readily understood by reference to the following detailed description when considered in conjunction with the accompanying drawings wherein:
fig. 1 is a 0.6 order fractional order spectral image of the reciprocal spectrum.
FIG. 2 is a graph of scatter distribution of training set sample prediction results in accordance with an embodiment of the present invention;
FIG. 3 is a graph of scatter distribution of test set sample prediction results in accordance with an embodiment of the present invention;
FIG. 4 is a flow chart schematically illustrating a method for near infrared spectroscopy diagnosis of nitrogen content of hevea brasiliensis leaves based on a fractional order algorithm according to a preferred embodiment of the present invention.
It should be noted that the appended drawings illustrate rather than limit the invention. It is noted that the drawings representing structures may not be drawn to scale. Also, in the drawings, the same or similar elements are denoted by the same or similar reference numerals.
Detailed Description
In order that the present disclosure may be more clearly and readily understood, reference will now be made in detail to the present disclosure as illustrated in the accompanying drawings.
The invention considers that a fractional order differential algorithm is introduced into the establishment process of the rubber tree nitrogen content spectrum diagnosis model, and the rubber tree leaf nitrogen content spectrum diagnosis model is established so as to provide reference for rubber management in Hainan province, provide theoretical basis and model reference for variable fertilization and increase of rubber yield.
FIG. 4 is a flow chart schematically illustrating a method for near infrared spectroscopy diagnosis of nitrogen content of hevea brasiliensis leaves based on fractional order algorithm according to a preferred embodiment of the present invention.
As shown in FIG. 4, the method for diagnosing the nitrogen content of the leaf of the rubber tree based on the fractional order algorithm by near infrared spectrum according to the preferred embodiment of the invention comprises the following steps:
first step S1: selecting a rubber tree leaf sample;
preferably, the middle leaflet is selected from mature leaves which are free of plant diseases and insect pests and have good growth vigor as a rubber tree leaf sample.
Preferably, the rubber tree leaf samples are randomly selected from the field environment, more suitable for actual field management.
A second step S2: collecting spectral data of a near infrared band of a rubber tree leaf sample;
specifically, the near infrared band may be a band of 350nm to 2500 nm.
Preferably, when acquiring the spectral data, a predetermined number (e.g. 6) of points are randomly selected on the blade surface of the rubber tree blade sample to acquire each spectral data, and the average value of the acquired spectral data is used as the final spectral data value of the rubber tree blade sample. The method can improve the reliability of obtaining the spectral data and is beneficial to improving the precision of the model.
A third step S3: pretreating a rubber tree leaf sample, and then determining the nitrogen content of the pretreated rubber tree leaf sample;
preferably, the pretreatment comprises the steps of carrying out enzyme deactivation, drying, crushing and sample weighing on the rubber tree leaf sample, and stewing. Preferably, a semi-micro Kjeldahl azotometer is adopted to determine the nitrogen content of the pretreated rubber tree leaf sample.
Preferably, the water-removing temperature of the rubber tree leaf sample is 95-115 ℃, and the water-removing time is 20-40 min. The water-removing temperature is most suitable, so that the main components in the rubber blade can be retained, and the components in the rubber blade can be prevented from reacting and being consumed continuously. Preferably, the drying temperature is 70-90 ℃, the leaves are dried to constant weight, the drying temperature is most suitable, and the situation of scorching the leaves cannot occur. Meanwhile, the dried leaves are convenient to grind into powder.
Fourth step S4: acquiring a fractional order spectrum by using the acquired spectral data of the near infrared wave band of the rubber tree leaf sample;
for example, before obtaining the fractional spectrum, for the convenience of calculation, the acquired spectrum data of the rubber tree leaf sample may be first subjected to inverse transformation, which is expressed by the following formula: y =1/R, wherein R is spectral data of a collected sample of a hevea leaf;
specifically, for example, the calculation formula of the fractional spectrum is preferably as follows:
wherein x is a band value, v is a fractional order,h is the step size of the solution, where h =1, t and a are the upper and lower limits of the integral, respectively.
Fifth step S5: screening a spectrum value corresponding to a wave band most relevant to the nitrogen content of the measured rubber tree leaf sample in the fractional order spectrum by using a competitive adaptive re-weighting algorithm (CARS) to serve as an independent variable to establish a model; wherein the model is preferably as follows:
y＝α 0 +α 1 λ 1 +α 2 λ 2 +…+α n λ n
wherein y is the nitrogen content of the rubber tree leaves; lambda [ alpha ] 1 ～λ n A spectrum value corresponding to the wave band selected by the competitive adaptive reweighting algorithm, n is the number of the characteristic wave bands selected by the competitive adaptive reweighting algorithm, alpha 0 ～α n Is a coefficient value trained by partial least squares regression.
Sixth step S6: and predicting the nitrogen content of the rubber tree leaf by using the established model, and evaluating the prediction result.
When light irradiates the surface of the rubber blade, the rest part except the part which is absorbed is reflected. The amount of light wave absorption is related to the content of chemical substances inside the blade. Wherein the band associated with the nitrogen content in the leaves of the rubber tree is limited. The method can reduce the dimensionality of data and improve the operation speed of the model by finding out the wave bands (186 in total) most relevant to the nitrogen content through a competitive adaptive re-weighting algorithm.
The invention and the modeling method using fractional calculus and partial least square realize the rapid nondestructive detection of the nitrogen content of the rubber tree. Compared with the traditional chemical determination method, the method greatly reduces the detection time, reduces the pollution to the environment, improves the detection efficiency of nitrogen, and can provide reference for the field management of rubber forests.
< specific example >
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention more clear, the invention is further explained by combining with the examples of the specific embodiments. For example, the software and hardware are mainly implemented by a near infrared spectrometer, a chemometric software, a computer and the like. The whole implementation process is described as follows:
1. and (6) obtaining a sample. 177 rubber tree leaf samples are randomly adopted in a test field of tropical agricultural science institute of China, and the sample variety is 7-33-97 of hot grinding. A richer sample range can be selected, so that the model built has better adaptability and robustness.
2. And (4) collecting the spectrum of the sample. After the samples were brought back to the laboratory, reflectance values were measured for the full-band spectrum of the rubber blade samples using a FieldSpec3 spectrometer from ASD, USA. During near infrared spectrum measurement, 6 points are randomly selected on the whole blade, meanwhile, the defects (scratches and scars) in the blade are avoided as much as possible, and the average spectrum of the 6 spectrums is used as the reflectivity value of the sample for modeling.
3. And (4) measuring a sample reference value. And (3) performing enzyme deactivation, drying, crushing, sample weighing and digestion on the rubber tree leaves with the collected spectrums, and finally determining the nitrogen content of the rubber leaves by using a semi-micro Kjeldahl apparatus.
4. And selecting a sample set. 118 samples are selected as modeling set samples according to a concentration gradient method, and the remaining 59 samples are prediction set samples.
5. Preprocessing the spectral data and extracting the characteristics. And performing reciprocal transformation on the original spectrum value to obtain a reciprocal spectrum. Then, fractional calculus processing is performed, and the selected order is 0.6. After obtaining a 0.6 th order spectrum (e.g., as shown in fig. 1), wavelength points with large regression coefficients in the PLS model are screened out by using a competitive adaptive re-weighting algorithm (CARS), wavelength points with small weights are removed, and a subset with the lowest RMSECV index is selected by using cross validation, so that an optimal wavelength combination related to the measured element (nitrogen content) is obtained.
6. And (5) establishing a model. And (3) modeling by using partial least square regression by taking 0.6-order spectral values corresponding to 186 wave bands of a competitive adaptive reweighting algorithm as independent variables and taking nitrogen values of rubber tree leaves obtained by corresponding actual measurement as dependent variables.
And (5) predicting the nitrogen content of the remaining 59 samples by using the model established in the step 6, and evaluating the result. In the evaluation index, the closer the correlation coefficient and the decision coefficient are to 1, the smaller the absolute value of the root mean square error is, the better the prediction performance is. The predicted results are shown in the following table:
7. and predicting the modeling set and the prediction set, wherein the correlation coefficient between the prediction value of the rubber tree nitrogen content and the measured value obtained by using the traditional chemical analysis method is more than 0.9, and the satisfactory prediction precision is obtained. The scatter distribution plots of the prediction results for the modeling set and prediction set samples are shown in fig. 2 and 3. The method can be used for rapidly and accurately predicting the content of the nitrogen of the rubber tree.
Therefore, the invention discloses a rubber tree leaf nitrogen content near infrared spectrum diagnosis method based on a fractional order algorithm. As the rubber tree is used as the source of natural rubber which is an important strategic material in China, the method has important significance for reasonably managing the nutritional status of the rubber tree so as to improve the yield of the natural rubber. According to the invention, mature rubber leaves in a natural environment are randomly collected to serve as samples, and near infrared spectrum information and internal physicochemical component data of the samples are collected. And (3) establishing a near infrared spectrum model of the sample by adopting a partial least square method through the pretreatment of the spectrum data and the characteristic extraction of a fractional order algorithm. And through the correlation analysis of the nitrogen content of the rubber leaves and the spectral data, the nitrogen content change and the interference of the ground background data on the near-infrared nondestructive testing are corrected. Analyzing the influence of different orders on the near infrared spectrum model, and finally determining the optimal order of the rubber tree leaf nitrogen content near infrared spectrum diagnosis model based on fractional order. The introduction of the fractional order algorithm enables more effective information in the near infrared spectrum to be mined and utilized, and the rapid, accurate and real-time nondestructive detection of the nitrogen content of the rubber tree leaves is realized.
It should be noted that the terms "first", "second", "third", etc. in the specification are used only for distinguishing various components, elements, steps, etc. in the specification, and are not used for representing the logical relationship, the sequential relationship, etc. among the various components, elements, steps, etc. unless otherwise specified.
It is to be understood that while the present invention has been described in conjunction with the preferred embodiments thereof, the foregoing description is not intended to limit the invention. It will be apparent to those skilled in the art that many changes and modifications can be made, or equivalents employed, to the presently disclosed embodiments without departing from the intended scope of the invention. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention are still within the scope of the protection of the technical solution of the present invention, unless the contents of the technical solution of the present invention are departed.
Claims (10)
1. A near infrared spectrum diagnosis method of rubber tree leaf nitrogen content based on fractional order algorithm is characterized by comprising the following steps:
the first step is as follows: selecting a rubber tree leaf sample;
the second step is as follows: collecting spectral data of a near-infrared band of a rubber tree leaf sample;
the third step: pretreating a rubber tree leaf sample, and then determining the nitrogen content of the pretreated rubber tree leaf sample;
the fourth step: acquiring a fractional order spectrum by using the acquired spectral data of the near-infrared band of the rubber tree leaf sample;
the fifth step: screening a spectrum value corresponding to a wave band most related to the measured nitrogen content of the rubber tree leaf sample in the fractional order spectrum by using a competitive adaptive reweighting algorithm, and taking the spectrum value as an independent variable to establish a model;
a sixth step: and predicting the nitrogen content of the rubber tree leaves by using the established model.
2. The method for near infrared spectrum diagnosis of nitrogen content in rubber tree leaves based on fractional order algorithm as claimed in claim 1, wherein the formula of the model is as follows:
y＝α 0 +α 1 λ 1 +α 2 λ 2 +…+α n λ n
wherein y is the nitrogen content of the rubber tree leaves; lambda [ alpha ] 1 ～λ n A spectrum value corresponding to the wave band selected by the competitive adaptive reweighting algorithm, n is the number of the characteristic wave bands selected by the competitive adaptive reweighting algorithm, alpha 0 ～α n Is a coefficient value trained by partial least squares regression.
3. The method for near infrared spectrum diagnosis of nitrogen content in rubber tree leaves based on fractional order algorithm as claimed in claim 1 or 2, wherein the fractional order spectrum has the formula:
wherein x is a band value, v is a fractional order,h is the step size of the solution, where h =1, t and a are the upper and lower limits of the integral, respectively.
4. The near infrared spectrum diagnosis method for the nitrogen content of the rubber tree leaves based on the fractional order algorithm as claimed in claim 1 or 2, characterized in that the middle leaflet is selected from mature leaves without diseases and insect pests and with good growth vigor as a rubber tree leaf sample.
5. The method for near infrared spectrum diagnosis of nitrogen content in rubber tree leaves based on fractional order algorithm as claimed in claim 1 or 2, characterized in that the rubber tree leaf samples are randomly selected from field environment.
6. The method for near infrared spectrum diagnosis of nitrogen content in hevea brasiliensis leaves based on fractional order algorithm as claimed in claim 1 or 2, wherein the near infrared band is a band of 350nm to 2500 nm.
7. The method for near infrared spectrum diagnosis of nitrogen content in rubber tree leaves based on fractional order algorithm as claimed in claim 1 or 2, wherein when the spectral data is collected, a predetermined number of points are randomly selected on the leaf surface of the rubber tree leaf sample to obtain each spectral data, and the average value of each obtained spectral data is used as the final spectral data value of the rubber tree leaf sample.
8. The method for near infrared spectrum diagnosis of nitrogen content in rubber tree leaves based on fractional order algorithm as claimed in claim 1 or 2, wherein the pretreatment comprises the steps of enzyme deactivation, drying, crushing and sample weighing, and digestion of rubber tree leaf samples.
9. The method for near infrared spectrum diagnosis of nitrogen content in rubber tree leaves based on fractional order algorithm as claimed in claim 8, wherein the de-enzyming temperature of the rubber tree leaf sample is 95-115 ℃ and the de-enzyming time is 20-40 min. The drying temperature is 70-90 ℃, and the leaves are dried to constant weight.
10. The near infrared spectrum diagnosis method for the nitrogen content of the rubber tree leaves based on the fractional order algorithm as claimed in claim 1 or 2, characterized in that a semi-micro Kjeldahl apparatus is adopted to measure the nitrogen content of the pretreated rubber tree leaf samples.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711114947.5A CN107796779A (en) | 2017-11-13 | 2017-11-13 | The near infrared spectrum diagnostic method of rubber tree LTN content |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711114947.5A CN107796779A (en) | 2017-11-13 | 2017-11-13 | The near infrared spectrum diagnostic method of rubber tree LTN content |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107796779A true CN107796779A (en) | 2018-03-13 |
Family
ID=61534908
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711114947.5A Pending CN107796779A (en) | 2017-11-13 | 2017-11-13 | The near infrared spectrum diagnostic method of rubber tree LTN content |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107796779A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109115704A (en) * | 2018-08-29 | 2019-01-01 | 中南大学 | The more metal ion detection Spectroscopy differential preprocess methods of trace under a kind of high zinc background |
| CN110082310A (en) * | 2019-05-30 | 2019-08-02 | 海南大学 | A kind of near infrared band EO-1 hyperion diagnostic method of rubber tree LTN content |
| CN110455722A (en) * | 2019-08-20 | 2019-11-15 | 中国热带农业科学院橡胶研究所 | Rubber tree blade phosphorus content EO-1 hyperion inversion method and system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106404699A (en) * | 2016-12-02 | 2017-02-15 | 南京农业大学 | Nondestructive measurement method for contents of nitrogen elements of pear tree leaf blades |
-
2017
- 2017-11-13 CN CN201711114947.5A patent/CN107796779A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106404699A (en) * | 2016-12-02 | 2017-02-15 | 南京农业大学 | Nondestructive measurement method for contents of nitrogen elements of pear tree leaf blades |
Non-Patent Citations (3)
| Title |
|---|
| KAI CHEN ET AL.: "Estimation of the nitrogen concentration of rubber tree using fractional calculus augmented NIR spectra", 《INDUSTRIAL CROPS & PRODUCTS》 * |
| 张文文等: "光谱分数阶微分与玉米叶片重金属铜含量的相关性分析", 《科学技术与工程》 * |
| 杨宝华等: "基于敏感波段的小麦冠层氮含量估测模型", 《农业工程学报》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109115704A (en) * | 2018-08-29 | 2019-01-01 | 中南大学 | The more metal ion detection Spectroscopy differential preprocess methods of trace under a kind of high zinc background |
| CN110082310A (en) * | 2019-05-30 | 2019-08-02 | 海南大学 | A kind of near infrared band EO-1 hyperion diagnostic method of rubber tree LTN content |
| CN110455722A (en) * | 2019-08-20 | 2019-11-15 | 中国热带农业科学院橡胶研究所 | Rubber tree blade phosphorus content EO-1 hyperion inversion method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chandrasekaran et al. | Potential of near-infrared (NIR) spectroscopy and hyperspectral imaging for quality and safety assessment of fruits: An overview | |
| Zhu et al. | Predicting bruise susceptibility of ‘Golden Delicious’ apples using hyperspectral scattering technique | |
| Xu et al. | Determination of rice root density from Vis–NIR spectroscopy by support vector machine regression and spectral variable selection techniques | |
| Hadiwijaya et al. | Multi-product calibration model for soluble solids and water content quantification in Cucurbitaceae family, using visible/near-infrared spectroscopy | |
| Zhang et al. | Spectral technology and multispectral imaging for estimating the photosynthetic pigments and SPAD of the Chinese cabbage based on machine learning | |
| Kanchanomai et al. | Non-destructive analysis of Japanese table grape qualities using near-infrared spectroscopy | |
| CN107796779A (en) | The near infrared spectrum diagnostic method of rubber tree LTN content | |
| CN104255118B (en) | Rapid lossless testing method based on near infrared spectroscopy technology for paddy rice seed germination percentage | |
| Jin et al. | Predicting the nutrition deficiency of fresh pear leaves with a miniature near-infrared spectrometer in the laboratory | |
| CN111912793A (en) | Method for measuring cadmium content in tobacco by hyperspectral and establishment of prediction model | |
| CN111562235A (en) | Method for rapidly identifying black-leaf outbreak disease and infection degree of tobacco leaves based on near infrared spectrum | |
| Xie et al. | Spectral reflectance response to nitrogen fertilization in field grown corn | |
| Van Wyngaard et al. | Infrared spectroscopy and chemometric applications for the qualitative and quantitative investigation of grapevine organs | |
| Sun et al. | Water content detection of potato leaves based on hyperspectral image | |
| Rathna Priya et al. | Characterising corn grain using infrared imaging and spectroscopic techniques: a review | |
| Wang Xue et al. | Monitoring model for predicting maize grain moisture at the filling stage using NIRS and a small sample size. | |
| CN113049526B (en) | Corn seed moisture content determination method based on terahertz attenuated total reflection | |
| Vallone et al. | Quality evaluation of grapes for mechanical harvest using vis NIR spectroscopy | |
| CN102519903A (en) | Method for measuring whiteness value of Agaricus bisporus by using near infrared spectrum | |
| Wu et al. | Nitrogen status assessment for multiple cultivars of strawberries using portable FT-NIR spectrometers combined with cultivar recognition and multivariate analysis | |
| Amirul et al. | Estimation of harumanis (Mangifera Indica L.) sweetness using near-infrared (NIR) spectroscopy | |
| Li et al. | Chlorophyll assessment and sensitive wavelength exploration for tea (Camellia sinensis) based on reflectance spectral characteristics | |
| CN112763448A (en) | ATR-FTIR technology-based method for rapidly detecting content of polysaccharides in rice bran | |
| CN102636455A (en) | Method for measuring hardness of agaricus bisporus by using near infrared spectrum | |
| Luo et al. | Prediction of the Harvest Time of Cabernet Sauvignon Grapes Using Near-Infrared Spectroscopy |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180313 |