CN113065230A - High-spectrum inversion model for establishing rice leaf SPAD based on optimized spectral index - Google Patents
High-spectrum inversion model for establishing rice leaf SPAD based on optimized spectral index Download PDFInfo
- Publication number
- CN113065230A CN113065230A CN202110279004.8A CN202110279004A CN113065230A CN 113065230 A CN113065230 A CN 113065230A CN 202110279004 A CN202110279004 A CN 202110279004A CN 113065230 A CN113065230 A CN 113065230A
- Authority
- CN
- China
- Prior art keywords
- spectral
- index
- spectrum
- rice leaf
- optimized
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
-
- 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
- G01N21/55—Specular reflectivity
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Immunology (AREA)
- Theoretical Computer Science (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Health & Medical Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides a rice leaf SPAD hyperspectral inversion model established based on an optimized spectral index, which comprises the following steps: s1, collecting the spectrum and chlorophyll content data of the target rice leaf: s2, preprocessing the spectral data: noise elimination and signal local characteristic refinement are realized by scaling translation operation of wavelet mother functions, and spike signals and mutation signals in original signals are effectively protected. The invention optimizes the integral calculation defined by the NAOC spectral index by simplifying the integral calculation based on integral limits (a, b), namely a mode of dual-wavelength combined operation, and screens out characteristic band combinations with higher correlation coefficients with rice leaf SPAD in the original spectrum and three mathematical transformation spectra by utilizing a correlation analysis method.
Description
Technical Field
The invention relates to the technical field of a hyperspectral inversion model of rice leaf SPAD, in particular to a hyperspectral inversion model of rice leaf SPAD established based on optimized spectral indexes.
Background
Chlorophyll is an important pigment for plant photosynthesis, and the content, distribution and change of the chlorophyll can directly or indirectly reflect the photosynthetic capacity, nutrient condition and growth health condition of plants. The accurate diagnosis of the chlorophyll content has important significance on scientific management means such as growth monitoring, nutrition diagnosis, crop yield estimation, pest and disease early warning and the like of crops. The rice is an important grain crop in China, the gold belt is produced in the rice in Jilin province, the main variety is japonica rice, the tillering period of the rice is ended in one season of one year and in the middle of 7 months, and the rice is successively put into the stage of jointing and booting, the growth period is a key turning period of the rice from the vegetative growth period with tillering as the center, such as long root, long leaf, long tiller and the like, to the reproductive growth period with young ear development as the center, and the chlorophyll content in the rice leaf directly influences the photosynthetic strength and the accumulation amount of organic matters, so that the growth of the young ear and the yield of the rice are influenced. Therefore, the method has certain practical significance for researching the chlorophyll content of the rice in the jointing and booting stage.
At present, the inversion of the chlorophyll content of vegetation by using the spectral index is a very effective method. The spectral index is constructed to extract information that can form a high correlation with the chlorophyll content in the spectrum, and generally, the reflectance corresponding to a specific wavelength band is combined and calculated, and the selection of the specific wavelength band generally needs to refer to a certain physical basis. Initially, Horler et al defined the maximum value of the first derivative of a characteristic curve in the range of 670-780 nm of green vegetation as the "red edge", and the corresponding physical meaning is the peak position of the strong absorption of chlorophyll by the red light band, and thought that there may be a close relationship between the "red edge" position of the spectrum of the vegetation canopy and the content of chlorophyll. Curran et al, corroborated this conclusion by studying the "red edge" position and the sensitivity of the total chlorophyll content in the canopy, and then some scholars established a series of spectral indices such as Ratio Vegetation Index (RVI), Difference Vegetation Index (DVI), Normalized Vegetation Index (NDVI), etc. using the combined operation of some key bands within this band range, and amplified the relationship between spectral reflectance and chlorophyll content of the Vegetation. With the progress of the inversion research on the chlorophyll content, some researchers find that the spectral index obtained based on the key waveband combination in the 'red edge' position range only contains two or three wavelengths of operation, and the effective information contained in the spectral index is very limited relative to a complete spectral reflectivity characteristic curve, so that when the spectral index is applied to crops under the influence of factors such as different varieties, growth periods, places and the like, the calculated result may have a large deviation from the real situation. Therefore, some scholars propose the concept of integral index, integrating more sensitive wavelengths to increase the applicability of spectral index. The method comprises the steps that Oppelt, Mauser and the like calculate the ratio of the area of two-point integral operation in the range of 600-735 nm of a corn reflectivity spectrum to an envelope line, namely a Chlorophyll Absorption integral index (CAI), the prediction capability of the index on the corn leaf area index and the canopy Chlorophyll density is researched, and the sensitivity of the index on a canopy structure, illumination geometry, soil background reflectivity and atmospheric conditions is analyzed; delegido et al established a reflectance Curve Normalized Area index (NAOC) for studying the spatial distribution of chlorophyll of urban vegetation in a complex environment, and used the index to invert the chlorophyll content of various green vegetation such as phoenix tree, date palm and the like, and found that the NAOC index has strong inversion capability for the chlorophyll content of the green vegetation, and provided a simple and convenient method for remote sensing estimation of chlorophyll of vegetation through linear fitting between the NAOC index and the chlorophyll content of the chlorophyll.
However, the strong prediction capability of the spectral index on the chlorophyll content of the rice in the jointing and booting stage under the farmland environment is still to be researched.
Disclosure of Invention
The invention aims to provide a rice leaf SPAD hyperspectral inversion model established based on an optimized spectral index so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
the method for establishing the rice leaf SPAD hyperspectral inversion model based on the optimized spectral index comprises the following steps:
s1, collecting the spectrum and chlorophyll content data of the target rice leaf:
s2, preprocessing the spectral data: noise elimination and signal local characteristic refinement are realized by scaling translation operation of wavelet mother functions, and spike signals and mutation signals in original signals are effectively protected;
s3, optimized spectral index NAOC: the NAOC index is an integrated spectral index comprising a plurality of spectral bands, the NAOC index being defined as:
simplifying the spectral index NAOC based on integral operation to obtain the optimized spectral index based on dual-wavelength simplified operation, which is defined as:
s4, performing hyperspectral pretreatment on the rice leaves based on wavelet analysis: selecting 4-order Daubechies wavelets, namely db4 wavelets, to perform 1-6 layers of wavelet decomposition on the original reflectivity spectrum, and determining L4 layers of decomposed and reconstructed spectra as a result of wavelet analysis denoising processing of the original spectral reflectivity curve;
s5, optimizing the spectral index and waterCorrelation analysis of rice leaf SPAD: respectively carrying out three mathematical transformation processes of logarithm, reciprocal and square opening on the denoised L4 layer spectral reflectivity curve R to obtain transformed spectra LgR, 1/R and
and are respectively substituted into
Obtaining four groups of optimized spectrums and conversion spectrum indexes;
s6, performing statistical analysis on correlation coefficients corresponding to the optimized spectrum and the transformed spectrum index in the four forms, wherein 3 integral wave bands with the correlation coefficients higher than 0.87 are combined and are respectively R (641, 790) (0.8726),
(653, 767) (0.8717) and R (644, 774) (0.8716), calculating 60 optimized spectral index values corresponding to 3 integration band combinations with correlation coefficients higher than 0.87 in 20 original samples, according to a ratio of 2: 1 into a modeling set and a verification set, and determining samples by adopting an equal-interval sampling method.
Preferably, the data acquisition of the target blade spectrum is carried out by using a Hand-Held type ground object spectrometer of Hand Held 2 produced by analytical spectroscopy instrument company, the spectral band range of the instrument is 325-1075nm, the sampling interval is 1.4nm, the resolution is 3nm @700nm, the instrument is preheated for 20min before use, each blade acquires 3 spectral curves, and a white board is used for correction after each measurement.
Preferably, the collection of the chlorophyll content selects a Japanese SPAD-502 chlorophyll meter to synchronously obtain the relative chlorophyll content of the corresponding rice leaf, the SPAD value is used for replacing the chlorophyll content of the rice leaf, a main leaf vein is avoided during measurement, five points are marked at intervals from the leaf tip to the leaf tail, each point is measured once, and the average value of the points is taken as the measurement result of the chlorophyll content of the leaf after 5 times of repeated measurement.
Preferably, in S6, 40 modeling set samples and 20 validation set samples are determined by equal-interval sampling, and partial least squares regression is usedThree rice leaf SPAD inversion models are established by a regression model (PLSR), a Support Vector Machine (SVM) and a BP neural network so as to determine a Coefficient (R)2) And Root Mean Square Error (RMSE) as a model evaluation index.
Compared with the prior art, the invention has the beneficial effects that
The method optimizes integration calculation defined by the NAOC spectral index by simplifying the integration calculation based on integration limits (a, b), namely a dual-wavelength combined operation mode, screens out characteristic band combinations with higher correlation coefficients with rice leaf SPAD in an original spectrum and three mathematical transformation spectrums by using a correlation analysis method, uses the optimized spectrum and the transformation spectrum index obtained by calculation to construct an inversion model of the rice leaf SPAD in the heading and booting stage, and finally contrasts and analyzes the precision and stability of the three modeling methods to determine the optimal rice leaf SPAD inversion model established based on the optimized spectrum and the transformation spectrum index.
Drawings
FIG. 1 is a schematic of the spectra of the present invention;
FIG. 2 is a decomposition reconstruction spectrum of the L4 layer according to the present invention;
FIG. 3 is a scatter plot of the prediction of PLSR;
FIG. 4 is a scatter plot of the predicted results of the SVM;
FIG. 5 is a scatter plot of the prediction results of the BP neural network.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-5, in the embodiment of the present invention, the method for establishing a hyperspectral inversion model of rice leaf SPAD based on an optimized spectral index includes the following steps:
s1, collecting the spectrum and chlorophyll content data of the target rice leaf:
s2, preprocessing the spectral data: noise elimination and signal local characteristic refinement are realized by scaling translation operation of wavelet mother functions, and spike signals and mutation signals in original signals are effectively protected;
s3, optimized spectral index NAOC: the NAOC index is an integrated spectral index comprising a plurality of spectral bands, the NAOC index being defined as:
simplifying the spectral index NAOC based on integral operation to obtain the optimized spectral index based on dual-wavelength simplified operation, which is defined as:
s4, performing hyperspectral pretreatment on the rice leaves based on wavelet analysis: selecting 4-order Daubechies wavelets, namely db4 wavelets, to perform 1-6 layers of wavelet decomposition on the original reflectivity spectrum, and determining L4 layers of decomposed and reconstructed spectra as a result of wavelet analysis denoising processing of the original spectral reflectivity curve;
s5, optimizing the correlation analysis of the spectral index and rice leaf SPAD: respectively carrying out three mathematical transformation processes of logarithm, reciprocal and square opening on the denoised L4 layer spectral reflectivity curve R to obtain transformed spectra LgR, 1/R and
and are respectively substituted into
Obtaining four groups of optimized spectrums and conversion spectrum indexes;
s6, performing statistical analysis on correlation coefficients corresponding to the optimized spectrum and the transformed spectrum index in the four forms, wherein 3 integral wave bands with the correlation coefficients higher than 0.87 are combined and are respectively R (641, 790) (0.8726),
(653, 767) (0.8717) and R (644, 774) (0.8716), calculating 60 optimized spectral index values corresponding to 3 integration band combinations with correlation coefficients higher than 0.87 in 20 original samples, according to a ratio of 2: 1 into a modeling set and a verification set, and determining samples by adopting an equal-interval sampling method.
Respectively carrying out three mathematical transformation processes of logarithm, reciprocal and square opening on the denoised L4 layer spectral reflectivity curve R to obtain transformed spectra LgR, 1/R and
and are respectively substituted into
And obtaining four groups of optimized spectrums and conversion spectrum indexes. As the effective range defined by the NAOC index is 600-800 nm, 201 effective wave bands are respectively intercepted from an original spectrum curve and three transformed spectrum curves, correlation analysis is carried out on four groups of optimized spectra and transformed spectrum indexes and rice leaf SPAD by a correlation analysis method in the form of (a, b) two-wave band combination, the wavelength positions of the integration limits (a, b) corresponding to four groups of maximum correlation coefficients are respectively R (641, 790), LgR (628, 722), 1/R (620, 736),
(653, 767), the optimized spectral index based on the original spectral curve R has the maximum correlation coefficient with rice leaf SPAD, and reaches 0.8726; secondly, the
Transformed spectral curve of the form with maximum correlation coefficient 0.8717; the maximum correlation coefficient of the transformation spectrum curves in the logarithmic form and the reciprocal form and the rice leaf SPAD is less than 0.8, and is 0.5426 and 0.7165 respectively. The wavelength positions (641, 628, 620 and 653nm) of the lower integration limit a corresponding to the maximum correlation coefficients of the four groups of spectral indexes are all positioned on the left side of 670nm, and the wavelength positions (790, 722 and 736) of the upper integration limit b767nm) is located to the right of 670nm, which is consistent with the explanation of Delegido et al for the upper and lower limits of the integral of the NAOC spectral indices, indicating that the wavelength combinations corresponding to the four sets of maximum correlation coefficients all have corresponding physical meanings.
The data acquisition of the target blade spectrum of the embodiment adopts a Hand-Held type ground object spectrometer of Hand Held 2 produced by analytical spectroscopy instrument company to carry out measurement, the spectral band range of the instrument is 325-plus 1075nm, the sampling interval is 1.4nm, the resolution is 3nm @700nm, the instrument is preheated for 20min before use, each blade acquires 3 spectral curves, and a white board is used for correction after each measurement.
The collection of the chlorophyll content in the embodiment selects a Japanese SPAD-502 chlorophyll meter to synchronously obtain the relative chlorophyll content of the corresponding rice leaf, the SPAD value is used for replacing the chlorophyll content of the rice leaf, a main leaf vein needs to be avoided during measurement, five points are marked at intervals from the leaf tip to the leaf tail, each point is measured once, and the average value of the points is taken as the measurement result of the chlorophyll content of the leaf after 5 times of repeated measurement.
In S6 of this embodiment, 40 modeling set samples and 20 verification set samples are determined by an equidistant sampling method, three rice leaf SPAD inversion models are established by a partial least squares regression model (PLSR), a Support Vector Machine (SVM), and a BP neural network, and a decision coefficient and a root mean square error are used as model evaluation indexes.
Table 13 inversion results of modeling method
Table 1 shows the results of the SPAD inversion of rice leaves by 3 modeling methods. It can be seen that no matter the modeling set or the verification set, the decision coefficients of the 3 inversion models established by utilizing the optimized spectrum and the transformed spectrum index are all larger than 0.79, and the root mean square error is smaller than 1.9, which shows that the three inversion models can realize the function of accurately predicting the rice leaf SPAD. In the three inversion models, the verification set of the model established by the BP neural network method has a relatively high determination coefficient of 0.857, and the model fitting degree is relatively good; the prediction accuracy is also relatively high, and the root mean square error is only 1.7221. Through continuous attempts in the modeling test process, the optimal neural network model structure is determined to be 3 layers, the number of nodes of a hidden layer is 6, the learning rate is set to be 0.1, when the iteration times reach 900 times, the accuracy of the neural network model tends to be stable, and the model has the optimal inversion effect on rice leaf SPAD.
(1) Performing correlation analysis on the four groups of optimized spectra and transformed spectral indexes and rice leaf SPAD by using a correlation analysis method to obtain wavelength positions of integration limits (a, b) corresponding to four maximum correlation coefficients, which are respectively R (641, 790), LgR (628, 722) and 1/R (620, 736),
(653, 767), the optimized spectral index based on the original spectral curve R has the maximum correlation coefficient with rice leaf SPAD, and reaches 0.8726; secondly, the
Transformed spectral curve of the form with maximum correlation coefficient 0.8717; the maximum correlation coefficients of the transformation spectrum curves in the logarithmic and reciprocal forms and the rice leaf SPAD are both less than 0.8 and are 0.5426 and 0.7165 respectively; compared with the other 8 common spectral indexes based on dual-wavelength or three-wavelength operation, the optimized spectrum and the transformed spectral index provided by the method have obviously better effect;
(2) the combination of 3 integration bands above 0.87 in the correlation coefficient for the four forms of optimized spectra and transformed spectral indices is R (641, 790) (0.8726),
(653, 767) (0.8717) and R (644, 774) (0.8716), calculating 60 optimized spectral index values corresponding to the 3 integration band combinations in the 20 original samples, according to 2: 1, dividing the ratio into a modeling set and a verification set, and establishing a SPAD inversion model of the rice leaves of PLSR, SVM and BP neural network. The determination coefficients of the three inversion models are all larger than 0.79, the root mean square error is smaller than 1.9, and the results show that the three inversion models can accurately predict rice leaf SPADAnd (4) performing functions. In the three inversion models, the BP neural network has the highest validation set decision coefficient of 0.857, and the root mean square error is 1.7221. At the moment, the number of the structural layers of the neural network is 3, the number of nodes of the hidden layer is 6, the learning rate is 0.1, when the iteration times reach 900, the accuracy of the neural network model tends to be stable, and the model is determined to be the optimal model for rice leaf SPAD inversion by utilizing an optimized spectrum and a transformation spectrum index.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the embodiments are described herein in terms of separate embodiments, not every embodiment may comprise a single embodiment, and such descriptions are provided for clarity only, and one skilled in the art should consider the embodiments herein as a whole, and the embodiments herein may be appropriately combined to form other embodiments as will be appreciated by one skilled in the art.
Claims (4)
1. The method is characterized by comprising the following steps of:
s1, collecting the spectrum and chlorophyll content data of the target rice leaf:
s2, preprocessing the spectral data: noise elimination and signal local characteristic refinement are realized by scaling translation operation of wavelet mother functions, and spike signals and mutation signals in original signals are effectively protected;
s3, optimized spectral index NAOC: the NAOC index is an integrated spectral index comprising a plurality of spectral bands, the NAOC index being defined as:
simplifying the spectral index NAOC based on integral operation to obtain the optimized spectral index based on dual-wavelength simplified operation, which is defined as:
s4, performing hyperspectral pretreatment on the rice leaves based on wavelet analysis: selecting 4-order Daubechies wavelets, namely db4 wavelets, to perform 1-6 layers of wavelet decomposition on the original reflectivity spectrum, and determining L4 layers of decomposed and reconstructed spectra as a result of wavelet analysis denoising processing of the original spectral reflectivity curve;
s5, optimizing the correlation analysis of the spectral index and rice leaf SPAD: respectively carrying out three mathematical transformation processes of logarithm, reciprocal and square opening on the denoised L4 layer spectral reflectivity curve R to obtain transformed spectra LgR, 1/R and
and are respectively substituted into
Obtaining four groups of optimized spectrums and conversion spectrum indexes;
s6, performing statistical analysis on correlation coefficients corresponding to the optimized spectrum and the transformed spectrum index in the four forms, wherein 3 integral wave bands with the correlation coefficients higher than 0.87 are combined and are respectively R (641, 790) (0.8726),
(0.8717) and R (644, 774) (0.8716), calculating 60 optimized spectral index values corresponding to 3 integration band combinations with correlation coefficients higher than 0.87 in 20 original samples, according to the ratio of 2: 1 into a modeling set and a verification set, and determining samples by adopting an equal-interval sampling method.
2. The rice leaf SPAD high spectrum inversion model based on the optimized spectral index as claimed in claim 1, wherein the data collection of the target leaf spectrum is measured by Hand Held type ground object spectrometer of Hand Held 2 produced by analytical spectroscopy instrument company, the spectral band range of the instrument is 325-1075nm, the sampling interval is 1.4nm, the resolution is 3nm @700nm, the pre-heating is carried out for 20min before use, each leaf obtains 3 spectral curves, and a white board is used for correction after each measurement.
3. The rice leaf SPAD high spectrum inversion model established based on the optimized spectral index according to claim 1, characterized in that the collection of the chlorophyll content selects a Japanese SPAD-502 chlorophyll meter to synchronously obtain the relative chlorophyll content of the corresponding rice leaf, the SPAD value is used for replacing the chlorophyll content of the rice leaf, a main vein needs to be avoided during measurement, five points are marked at intervals from the leaf tip to the leaf tail, each point is measured once, and the average value of the points is taken as the measurement result of the chlorophyll content of the leaf after 5 times of repeated measurement.
4. The rice leaf SPAD high spectrum inversion model based on optimized spectral index as claimed in claim 1, wherein said S6 adopts equal interval sampling method to determine 40 modeling set samples and 20 validation set samples, and adopts partial least squares regression model (PLSR), Support Vector Machine (SVM) and BP neural network to establish three rice leaf SPAD inversion models for Coefficient of determination (R)2) And Root Mean Square Error (RMSE) as a model evaluation index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110279004.8A CN113065230B (en) | 2021-03-16 | 2021-03-16 | High-spectrum inversion model for establishing rice leaf SPAD based on optimized spectral index |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110279004.8A CN113065230B (en) | 2021-03-16 | 2021-03-16 | High-spectrum inversion model for establishing rice leaf SPAD based on optimized spectral index |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113065230A true CN113065230A (en) | 2021-07-02 |
| CN113065230B CN113065230B (en) | 2022-12-13 |
Family
ID=76561245
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110279004.8A Active CN113065230B (en) | 2021-03-16 | 2021-03-16 | High-spectrum inversion model for establishing rice leaf SPAD based on optimized spectral index |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113065230B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114128568A (en) * | 2021-11-26 | 2022-03-04 | 泉州市金草生物技术有限公司 | Wild-imitating planting method for under-forest anoectochilus roxburghii |
| CN114965884A (en) * | 2022-05-17 | 2022-08-30 | 南京农业大学 | Method for monitoring size of brown planthopper population in rice field indoors |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101413893A (en) * | 2008-11-27 | 2009-04-22 | 吉林大学 | Plant chlorophyll measuring instrument and chlorophyll measuring method |
| CN103868880A (en) * | 2014-01-24 | 2014-06-18 | 河南农业大学 | Wheat leaf nitrogen content monitoring method based on spectrum double-peak index and method for establishing monitoring model |
| CN106442338A (en) * | 2016-09-06 | 2017-02-22 | 西北农林科技大学 | Hyperspectral inversion method for content of chlorophyll in apple leaves based on SVR (support vector regression) algorithm |
| CN107024439A (en) * | 2017-03-23 | 2017-08-08 | 西北农林科技大学 | A kind of paddy rice different growing chlorophyll content EO-1 hyperion estimating and measuring method |
| CN110702628A (en) * | 2019-10-26 | 2020-01-17 | 山东科技大学 | Spectral index model of chlorophyll content of vegetation leaf based on continuous wavelet analysis |
-
2021
- 2021-03-16 CN CN202110279004.8A patent/CN113065230B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101413893A (en) * | 2008-11-27 | 2009-04-22 | 吉林大学 | Plant chlorophyll measuring instrument and chlorophyll measuring method |
| CN103868880A (en) * | 2014-01-24 | 2014-06-18 | 河南农业大学 | Wheat leaf nitrogen content monitoring method based on spectrum double-peak index and method for establishing monitoring model |
| CN106442338A (en) * | 2016-09-06 | 2017-02-22 | 西北农林科技大学 | Hyperspectral inversion method for content of chlorophyll in apple leaves based on SVR (support vector regression) algorithm |
| CN107024439A (en) * | 2017-03-23 | 2017-08-08 | 西北农林科技大学 | A kind of paddy rice different growing chlorophyll content EO-1 hyperion estimating and measuring method |
| CN110702628A (en) * | 2019-10-26 | 2020-01-17 | 山东科技大学 | Spectral index model of chlorophyll content of vegetation leaf based on continuous wavelet analysis |
Non-Patent Citations (5)
| Title |
|---|
| JESÚS DELEGIDO等: "Chlorophyll content mapping of urban vegetation in the city of Valencia based on the hyperspectral NAOC index", 《ECOLOGICAL INDICATORS 》 * |
| 于海业等: "植物叶绿素荧光光谱的研究进展", 《北方园艺》 * |
| 余蛟洋等: "基于高光谱和BP神经网络模型苹果叶片SPAD值遥感估算", 《西北林学院学报》 * |
| 方圣辉等: "基于连续小波分析的混合植被叶绿素反演", 《武汉大学学报(信息科学版)》 * |
| 雷祥祥等: "基于PROSPECT模型的蔬菜叶片叶绿素含量和SPAD值反演", 《光谱学与光谱分析》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114128568A (en) * | 2021-11-26 | 2022-03-04 | 泉州市金草生物技术有限公司 | Wild-imitating planting method for under-forest anoectochilus roxburghii |
| CN114965884A (en) * | 2022-05-17 | 2022-08-30 | 南京农业大学 | Method for monitoring size of brown planthopper population in rice field indoors |
| CN114965884B (en) * | 2022-05-17 | 2023-07-18 | 南京农业大学 | Method for indoor monitoring of brown planthopper population size in rice field |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113065230B (en) | 2022-12-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107796764B (en) | Method for constructing wheat leaf area index estimation model based on three-band vegetation index | |
| CN110376167A (en) | Rice leaf nitrogen content monitoring method based on unmanned plane EO-1 hyperion | |
| Neto et al. | Vis/NIR spectroscopy and chemometrics for non-destructive estimation of water and chlorophyll status in sunflower leaves | |
| CN103940748B (en) | Based on the prediction of oranges and tangerines canopy nitrogen content and the visualization method of hyperspectral technique | |
| Sharabian et al. | Significant wavelengths for prediction of winter wheat growth status and grain yield using multivariate analysis | |
| CN111855589A (en) | Remote sensing inversion model and method for rice leaf nitrogen accumulation | |
| CN113065230B (en) | High-spectrum inversion model for establishing rice leaf SPAD based on optimized spectral index | |
| CN111855590A (en) | Remote sensing inversion model and method for rice leaf starch accumulation | |
| CN111855591A (en) | Rice overground part carbon-nitrogen ratio remote sensing inversion model and method | |
| CN111044516B (en) | Remote sensing estimation method for chlorophyll content of rice | |
| CN112881327B (en) | Tobacco leaf SPAD value estimation method based on novel vegetation index | |
| CN114676636A (en) | Grassland area soil moisture rapid inversion method integrating vegetation and habitat characteristics | |
| Liu et al. | Detection of chlorophyll content in growth potato based on spectral variable analysis | |
| CN112129709A (en) | Apple tree canopy scale nitrogen content diagnosis method | |
| Jin et al. | Hyperspectral indices developed from the low order fractional derivative spectra can capture leaf dry matter content across a variety of species better | |
| Zhang et al. | Hyperspectral model based on genetic algorithm and SA-1DCNN for predicting Chinese cabbage chlorophyll content | |
| CN114460015A (en) | Method and model for predicting chlorophyll content of canopy of rice in cold region | |
| Qiong et al. | Field monitoring of wheat seedling stage with hyperspectral imaging | |
| Bai et al. | Hyperspectral estimation of apple canopy chlorophyll content using an ensemble learning approach | |
| CN106124447A (en) | A kind of based on the method for soluble solid content in near-infrared spectral analysis technology detection Fructus Fragariae Ananssae | |
| CN116151454A (en) | Method and system for predicting yield of short-forest linalool essential oil by multispectral unmanned aerial vehicle | |
| Li et al. | Optimizing spectral index to estimate the relative chlorophyll content of the forest under the damage of Erannis jacobsoni Djak in Mongolia | |
| CN112782103B (en) | Method and system for monitoring early damage of cotton aphids on cotton seedling stage leaves | |
| Huang et al. | Estimation of chlorophyll content in pepper leaves using spectral transmittance red-edge parameters | |
| CN113340815A (en) | Crown scale wheat scab disease index evaluation method based on two-waveband combination index |
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 |