CN111912793A - Method for measuring cadmium content in tobacco by hyperspectral and establishment of prediction model - Google Patents
Method for measuring cadmium content in tobacco by hyperspectral and establishment of prediction model Download PDFInfo
- Publication number
- CN111912793A CN111912793A CN202010847800.2A CN202010847800A CN111912793A CN 111912793 A CN111912793 A CN 111912793A CN 202010847800 A CN202010847800 A CN 202010847800A CN 111912793 A CN111912793 A CN 111912793A
- Authority
- CN
- China
- Prior art keywords
- tobacco
- cadmium
- leaf
- spectral
- content
- 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
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
- G01N21/17—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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Mathematical Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides a method for measuring cadmium content in tobacco by utilizing hyperspectrum and establishment of a prediction model, wherein the wavelength of the hyperspectrum is 350-2500nm, the sampling interval of 350-1000nm is 4nm, and the spectral resolution is 3 nm; the sampling interval is 2nm and the resolution is 10nm at the sampling interval of 1000-2500 nm. Adopting a decrement fine sampling method, systematically analyzing the quantitative relation between the normalized vegetation index NDVI and the ratio vegetation index RVI which are constructed by the combination of the spectral reflectances of any two wave bands in the spectral range of 350-2,500nm under different processing conditions and the cadmium content in the tobacco leaves, and obtaining the determining coefficients R of the NDVI and the RVI2And drawing R2Equipotential map of (a). The tobacco leaf of the invention has a certain rule between the cadmium content and the spectral reflectivity,cadmium has a certain effect on the reflectivity of the tobacco lamina. Meanwhile, a BP neural network model is established, and the method has a good prediction effect on cadmium content.
Description
Technical Field
The invention relates to the field of tobacco research, in particular to a method for measuring cadmium content in tobacco by utilizing hyperspectrum and establishment of a prediction model.
Background
The cadmium metal has strong biological toxicity, and after being absorbed by plants, the cadmium metal not only can influence the growth and development of vegetation, but also can harm human health through a food chain. When the cadmium content absorbed by the plants reaches a certain standard, the symptoms of growth retardation, short plants, green leaves and the like can appear, and further, the quality is reduced and the yield of crops is reduced. Excessive cadmium accumulated in the tobacco can reduce the quality of the tobacco and can enter human bodies through smoke, thereby affecting the health of the human bodies.
Tobacco is an important economic crop in China, the tax of the tobacco industry accounts for about 7 percent of the total income of the national economy, and the number of smokers in China is about 3.5 hundred million in 2019. Therefore, the production of tobacco and the control of the quality of tobacco products play an important role in the development of national economy and the physical health condition of people.
The traditional method for measuring the cadmium content in the tobacco leaves needs destructive sampling, is time-consuming and labor-consuming, has hysteresis results, and is difficult to obtain the information of tobacco in a tobacco field of a large area in real time.
In recent years, with the rapid development of remote sensing technology, it has become possible to acquire vegetation information rapidly, nondestructively and in real time. The remote sensing technology is used for analyzing the correlation between the spectral reflectivity of the tobacco canopy and the physicochemical parameters, and various physicochemical parameter spectral characteristic estimation models can be established. The physical and chemical parameters of the vegetation and the spectral reflectivity have a nonlinear relation, and a nonlinear model BP neural network (BP neural network) has good effects on nitrogen, chlorophyll, chlorine, leaf area index and the like in tobacco, and has good application in crops such as rice, wheat, corn, soybean and the like. But the research of predicting the cadmium content of the tobacco by applying the hyperspectral remote sensing technology is not reported.
Disclosure of Invention
The invention provides a method for measuring cadmium content in tobacco by hyperspectrum and establishment of a prediction model, and the cadmium content in tobacco leaves can be quickly and accurately obtained.
The technical scheme for realizing the invention is as follows:
a method for measuring cadmium content in tobacco by utilizing hyperspectrum is characterized in that a leaf holder is adopted, an upper leaf and a lower leaf are selected from each tobacco, and the hyperspectrum is adopted to sample and measure chromium in the tobacco.
The wavelength of the hyperspectral spectrum is 350-; the sampling interval is 2nm and the resolution is 10nm at the sampling interval of 1000-2500 nm.
And (3) measuring 5 points for each leaf during measurement, and respectively taking the leaf tip part of the tobacco leaf, the two end parts of the middle part of the tobacco leaf and the two end parts of the bottom of the tobacco leaf. And measuring 10 light curves at each point, respectively measuring the light curves of the upper and lower tobacco leaves of each tobacco to be 50, taking the average value as the leaf spectrum of the tobacco, and totaling 72 groups of processed spectrum data, wherein the effective data is 71 groups. Calibration was done with a standard reference white board before each measurement.
The method for establishing the hyperspectral prediction model comprises the following steps: tobacco is divided into 3 categories of low cadmium (<15mg/kg), medium cadmium (15-30 mg/kg) and high cadmium (>30mg/kg) according to different cadmium element contents of leaves, and the reflectivity of the leaves is in direct proportion to the cadmium content in the tobacco within the wavelength range of 930-000 nm; in addition, the reflectance is first decreased and then increased along with the increase of cadmium content in the wavelength range of 350-2,500nm, and the change is more obvious in the green light band, the near infrared (1,000-1,300 nm), the short wave infrared (1,600-1,850 nm, 2,150-2,350 nm), namely 4 wave peaks.
A decrement fine sampling method is adopted, the quantitative relation between the normalized vegetation index NDVI and the ratio vegetation index RVI which are constructed by combining the spectral reflectances of any two wave bands in the 350-2,500nm spectral range under different processing conditions and the cadmium content in the tobacco leaves is systematically analyzed, the decision coefficients R of the NDVI and the RVI are obtained, and an equipotential diagram of the R is drawn.
In the formula, the predicted value is an actual measurement value, and the average value of the actual measurement values is shown.
The NDVI and RVI are calculated as follows:
in the formula (I), the compound is shown in the specification,R λ1 is referred to as wavelengthλ 1 The spectral reflectivity of the blade is measured and,R λ2 is referred to as wavelengthλ 2 The spectral reflectivity of the blade.
The invention has the beneficial effects that:
(1) the content of cadmium in the tobacco leaves and the spectral reflectivity of the tobacco leaves have a certain rule, namely the cadmium can have certain influence on the reflectivity of the tobacco leaves. Specifically, in the range of about 930-.
(2) The BP neural network model is established, and the BP neural network model has a good prediction effect on the cadmium content of the tobacco leaves.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 shows the position of the tobacco leaf spectrum measurement of the present invention.
FIG. 2 shows the spectral reflectance of canopy of flue-cured tobaccos of different chromium contents.
Fig. 3 is an equipotential diagram of determination coefficients (R) of rvi (a) and ndvi (b).
FIG. 4 shows the training results of the BP neural network model.
FIG. 5 shows the test result of BP neural network model.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments of the present invention, and it should be understood 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 obtained by a person skilled in the art without inventive effort based on the embodiments of the present invention, are within the scope of the present invention.
1. Materials and methods
1.1 design of the experiment
4 treatments are set up in the test, each treatment is measured for 3 periods, each period is measured for 6 plants repeatedly, and 4 equal concentration gradients are set in the simulated cadmium pollution environment and are respectively 0, 5, 10 and 20 mg/kg. The test soil was dried and passed through a 2mm mesh screen, each pot containing 1.2kg of soil, for a total of 72 pots. Prepared CdSO4Pouring the solution into a basin, and stirring and mixing uniformly. Tobacco seedlings with consistent growth vigor and good growth conditions are selected from a field to be transplanted, and then watering is carried out regularly. The soil fertilizer dosage is tobacco compound fertilizer (N: P)2O2:K2O =10:10:20)0.01kg, potassium sulfate 0.01kg, calcium superphosphate 0.005 kg. And (3) after fully and uniformly mixing the fertilizers, selecting healthy seedlings with consistent seedling age and growth vigor for transplanting, wherein one seedling is used in each pot. The physiological and biochemical indexes and the spectral data of the tobacco plants are measured every 15 days from 30 days of transplantation for 3 times.
1.2 determination of cadmium content in tobacco leaves
Collecting leaves of tobacco plants as samples in three periods of 30d, 45d and 60d after the tobacco is transplanted, putting the collected tobacco leaves in an oven for deactivating enzymes at 105 ℃, drying at 65 ℃, grinding the tobacco leaves and sieving with a 40-mesh sieve after drying. Then HNO is added3And H2O2. Placing in an automatic digestion instrument for digestion, placing the digested solution in an inductive couplerAnd measuring the cadmium content in the tobacco by using a plasma atomic emission spectrometer (ICP-0 ES).
1.3 acquisition of spectral data of the blades
And respectively carrying out leaf spectrum measurement 30d after the tobacco plants are transplanted, 45d after the tobacco plants are transplanted and 55d after the tobacco plants are transplanted. 6 tobacco plants with normal and consistent growth vigor are selected for each treatment. Measuring hyperspectrum by using a field Spec3 portable type surface texture spectrometer (ASD company in America), wherein the wavelength is 350-; the sampling interval is 2nm and the resolution is 10nm at the sampling interval of 1000-2500 nm. Using a leaf holder, the spectrum was measured on 2 leaves, one for each tobacco, and 5 points were measured on each leaf, as shown in FIG. 1. And measuring 10 light curves at each point, respectively measuring the light curves of the upper and lower tobacco leaves of each tobacco to be 50, taking the average value as the leaf spectrum of the tobacco, and totaling 72 groups of processed spectrum data, wherein the effective data is 71 groups. Calibration was done with a standard reference white board before each measurement.
1.4 index of vegetation
The vegetation index is a spectral parameter which is formed by linear and nonlinear combination of spectral data and has a certain indication meaning for vegetation. RVI is a sensitive indicating parameter of green plants and can be used for detecting and estimating plant biomass, and NDVI is an important parameter reflecting crop growth and nutrition information and has an important guiding function for obtaining crop information.
Wherein RVI is a ratio vegetation index, NDVI is a normalized vegetation index,R λ1 is referred to as wavelengthλ 1 The spectral reflectivity of the blade is measured and,R λ2 is referred to as wavelengthλ 2 The spectral reflectivity of the blade.
2. Results and analysis
2.1 spectral reflectance of tobacco leaves with different chlorine content
As shown in the figure, the tobacco is divided into 3 categories of low cadmium (<15mg/kg), medium cadmium (15-30 mg/kg) and high cadmium (>30mg/kg) according to the different cadmium element contents in the leaves. In the range of about 930-; in addition, in the range of 350-2,500nm, the reflectance is first decreased and then increased along with the increase of the cadmium content, and the change is more obvious in the green light band, the near infrared (1,000-1,300 nm), the short wave infrared (1,600-1,850 nm, 2,150-2,350 nm), namely 4 wave peaks. The result shows that the tobacco leaf spectral reflectivity with different cadmium contents has certain regular difference, and can be used for monitoring the cadmium content of the tobacco by remote sensing.
2.1 screening of sensitive bands
Based on the relation between the cadmium content in the tobacco leaves and the spectral reflectivity, a decrement fine sampling method is adopted, the quantitative relation between the normalized vegetation index (NDVI) and the Ratio Vegetation Index (RVI) which are constructed by combining the spectral reflectivities of any two wave bands in the spectral range of 350-2,500nm under different processing conditions and the cadmium content in the tobacco leaves is systematically analyzed, and the decision coefficients R of the NDVI and the RVI are obtained2And draw R2Equipotential map (fig. 3).
As shown in fig. 3a, R of RVI has been replaced>The band combination range of 0.6 is about (510-. R of NDVI2>The band combination range of 0.6 is about (510-.
2.3 cadmium content monitoring model
Randomly selected 50 samples were used to build the model and the remaining 21 samples were used to verify the model. And selecting the first 20 RVI values and the first 20 NDVI values with the largest determining coefficients as independent variables to establish a BP neural network model for predicting the cadmium content of the tobacco leaves.
The screened vegetation index is used as an input factor of a BP neural network, an S-shaped tangent transfer function (Tansig) is used as an input layer transfer function, an L-M optimization algorithm function (Trainlm) is used as a training function, and a linear transfer function (Purelin) is used as an output layer transfer function. Comparing values of different node numbers by adopting a trial and error method, obtaining the optimal hidden node number of 13, setting the target precision of 0.01 and the iteration number of 5,000, and automatically stopping training by the neural network when the fitting precision reaches the target precision. The prediction result of the BP neural network is shown in fig. 4, R of the prediction model is 0.681, RMSE is 8.001, and the prediction effect of the BP neural network on the cadmium content of the tobacco leaves is good.
2.4 model checking
The remaining 21 samples were selected for validation of the model built. As shown in fig. 5, a 1:1 relationship between the predicted value and the measured value of the BP neural network model is plotted. Solid line (y = x), the closer the data is to this line indicates the better the prediction; the dashed line represents the BP neural network. The more the points in the graph are distributed around the diagonal line, the higher the prediction accuracy of the model is, the better the effect is. R of predicted value and measured value of BP neural network model20.801, RMSE 4.430 respectively, and the test result shows that the BP neural network model has good prediction effect on the cadmium content of the tobacco leaves.
3. Conclusion
(1) Researches find that a certain rule exists between the cadmium content of the tobacco leaves and the spectral reflectivity of the tobacco leaves, namely, the cadmium can have certain influence on the reflectivity of the tobacco leaves. Specifically, in the range of about 930-.
(2) R of RVI and NDVI is drawn by adopting a decrement fine sampling method2Equipotential diagrams. The screened RVI spectral index is RVI (520, 710) and the screened NDVI spectral index is NDVI (530, 710).
(3) Randomly selecting 50 samples to establish a BP neural network model, R20.681, RMSE 8.001, and the model was examined for R20.801 for RMSE 4.430 for each. The BP neural network model has a good prediction effect on the cadmium content of the tobacco leaves.
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, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (6)
1. The method for measuring the cadmium content in the tobacco by utilizing the hyperspectrum is characterized by comprising the following steps of: a leaf holder is adopted, an upper leaf and a lower leaf are selected for each tobacco, and hyperspectrum is adopted to sample and measure chromium in the tobacco.
2. The method for measuring cadmium content in tobacco by using hyperspectrum according to claim 1, which is characterized in that: the wavelength of the hyperspectral spectrum is 350-; the sampling interval is 2nm and the resolution is 10nm at the sampling interval of 1000-2500 nm.
3. The method for measuring cadmium content in tobacco by using hyperspectrum according to claim 1, which is characterized in that: and (3) measuring 5 points for each leaf during measurement, and respectively taking the leaf tip part of the tobacco leaf, the two end parts of the middle part of the tobacco leaf and the two end parts of the bottom of the tobacco leaf.
4. A hyperspectral predictive model built using the method of any of claims 1-3, characterized in that: tobacco is divided into 3 categories of low cadmium, medium cadmium and high cadmium according to the content of cadmium elements in the leaves, and the reflectivity of the leaves is in direct proportion to the content of cadmium in the tobacco leaves within the wavelength range of 930-000 nm; in addition, in the wavelength range of 350-2,500nm, the reflectance is increased after being decreased as the content of cadmium is increased.
5. The hyperspectral prediction model of claim 4, wherein: adopting a decrement fine sampling method, systematically analyzing the quantitative relation between the normalized vegetation index NDVI and the ratio vegetation index RVI which are constructed by the combination of the spectral reflectances of any two wave bands in the spectral range of 350-2,500nm under different processing conditions and the cadmium content in the tobacco leaves, and obtaining the determining coefficients R of the NDVI and the RVI2And drawing R2Equipotential map of (a).
6. The hyperspectral predictive model of claim 5, wherein the NDVI and the RVI are calculated as follows:
in the formula (I), the compound is shown in the specification,R λ1 is referred to as wavelengthλ 1 The spectral reflectivity of the blade is measured and,R λ2 is referred to as wavelengthλ 2 The spectral reflectivity of the blade.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010847800.2A CN111912793A (en) | 2020-08-21 | 2020-08-21 | Method for measuring cadmium content in tobacco by hyperspectral and establishment of prediction model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010847800.2A CN111912793A (en) | 2020-08-21 | 2020-08-21 | Method for measuring cadmium content in tobacco by hyperspectral and establishment of prediction model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111912793A true CN111912793A (en) | 2020-11-10 |
Family
ID=73278536
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010847800.2A Pending CN111912793A (en) | 2020-08-21 | 2020-08-21 | Method for measuring cadmium content in tobacco by hyperspectral and establishment of prediction model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111912793A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112697726A (en) * | 2020-12-09 | 2021-04-23 | 云南省烟草农业科学研究院 | Hyperspectral field tobacco nicotine content prediction method and system based on unmanned aerial vehicle |
CN112697724A (en) * | 2020-12-09 | 2021-04-23 | 云南省烟草农业科学研究院 | Hyperspectral field tobacco leaf potassium oxide content prediction method and system based on unmanned aerial vehicle |
CN112697725A (en) * | 2020-12-09 | 2021-04-23 | 云南省烟草农业科学研究院 | Method and system for predicting total sugar content of tobacco leaves in field based on hyperspectrum of unmanned aerial vehicle |
CN112697723A (en) * | 2020-12-09 | 2021-04-23 | 云南省烟草农业科学研究院 | Hyperspectral field tobacco yield prediction method and system based on unmanned aerial vehicle |
CN118209502A (en) * | 2024-05-22 | 2024-06-18 | 北京市农林科学院信息技术研究中心 | Method and device for estimating potassium content of flue-cured tobacco leaves, electronic equipment and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102109462A (en) * | 2009-12-23 | 2011-06-29 | 中国科学院沈阳应用生态研究所 | Method for extracting characteristic spectrum information of Cd polluted rice leaf |
CN104089926A (en) * | 2014-07-18 | 2014-10-08 | 湖南省食品测试分析中心 | NIR (Near Infrared Ray) spectral analysis model and method for identifying excessive content of cadmium in rice |
US20160252458A1 (en) * | 2015-02-28 | 2016-09-01 | Board Of Supervisors Of Louisiana State University And Agricultural And Mechanical College | Quantum dot light emitting diodes for multiplex gas sensing |
EP3306289A1 (en) * | 2015-06-07 | 2018-04-11 | Yoon, Hojun | Portable hyperspectral camera device using plurality of semiconductor light sources |
CN108519339A (en) * | 2018-03-26 | 2018-09-11 | 江苏大学 | A kind of blade cadmium content Vis-NIR spectral signature modeling methods based on WT-LSSVR |
CN110133027A (en) * | 2019-05-14 | 2019-08-16 | 江苏省地质调查研究院 | A kind of method of Accurate Determining arable land Heavy Metal Pollution |
CN110376167A (en) * | 2019-07-29 | 2019-10-25 | 北京麦飞科技有限公司 | Rice leaf nitrogen content monitoring method based on unmanned plane EO-1 hyperion |
-
2020
- 2020-08-21 CN CN202010847800.2A patent/CN111912793A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102109462A (en) * | 2009-12-23 | 2011-06-29 | 中国科学院沈阳应用生态研究所 | Method for extracting characteristic spectrum information of Cd polluted rice leaf |
CN104089926A (en) * | 2014-07-18 | 2014-10-08 | 湖南省食品测试分析中心 | NIR (Near Infrared Ray) spectral analysis model and method for identifying excessive content of cadmium in rice |
US20160252458A1 (en) * | 2015-02-28 | 2016-09-01 | Board Of Supervisors Of Louisiana State University And Agricultural And Mechanical College | Quantum dot light emitting diodes for multiplex gas sensing |
EP3306289A1 (en) * | 2015-06-07 | 2018-04-11 | Yoon, Hojun | Portable hyperspectral camera device using plurality of semiconductor light sources |
CN108519339A (en) * | 2018-03-26 | 2018-09-11 | 江苏大学 | A kind of blade cadmium content Vis-NIR spectral signature modeling methods based on WT-LSSVR |
CN110133027A (en) * | 2019-05-14 | 2019-08-16 | 江苏省地质调查研究院 | A kind of method of Accurate Determining arable land Heavy Metal Pollution |
CN110376167A (en) * | 2019-07-29 | 2019-10-25 | 北京麦飞科技有限公司 | Rice leaf nitrogen content monitoring method based on unmanned plane EO-1 hyperion |
Non-Patent Citations (3)
Title |
---|
姚霞等: "基于减量精细采样法估算小麦叶片氮积累量的最佳归一化光谱指数", 《应用生态学报》 * |
杨艳东等: "烤烟叶片氯密度高光谱预测模型的建立", 《河南农业科学》 * |
顾艳文等: "基于光谱参数对小白菜叶片镉含量的高光谱估算", 《生态学报》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112697726A (en) * | 2020-12-09 | 2021-04-23 | 云南省烟草农业科学研究院 | Hyperspectral field tobacco nicotine content prediction method and system based on unmanned aerial vehicle |
CN112697724A (en) * | 2020-12-09 | 2021-04-23 | 云南省烟草农业科学研究院 | Hyperspectral field tobacco leaf potassium oxide content prediction method and system based on unmanned aerial vehicle |
CN112697725A (en) * | 2020-12-09 | 2021-04-23 | 云南省烟草农业科学研究院 | Method and system for predicting total sugar content of tobacco leaves in field based on hyperspectrum of unmanned aerial vehicle |
CN112697723A (en) * | 2020-12-09 | 2021-04-23 | 云南省烟草农业科学研究院 | Hyperspectral field tobacco yield prediction method and system based on unmanned aerial vehicle |
CN118209502A (en) * | 2024-05-22 | 2024-06-18 | 北京市农林科学院信息技术研究中心 | Method and device for estimating potassium content of flue-cured tobacco leaves, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111912793A (en) | Method for measuring cadmium content in tobacco by hyperspectral and establishment of prediction model | |
CN109187441B (en) | Method for constructing summer corn nitrogen content monitoring model based on canopy spectral information | |
Zhang et al. | High throughput analysis of leaf chlorophyll content in sorghum using RGB, hyperspectral, and fluorescence imaging and sensor fusion | |
Neto et al. | Vis/NIR spectroscopy and chemometrics for non-destructive estimation of water and chlorophyll status in sunflower leaves | |
Sunoj et al. | Nondestructive determination of cocoa bean quality using FT-NIR spectroscopy | |
Xu et al. | Determination of rice root density from Vis–NIR spectroscopy by support vector machine regression and spectral variable selection techniques | |
Chen et al. | Hyperspectral characteristics and quantitative analysis of leaf chlorophyll by reflectance spectroscopy based on a genetic algorithm in combination with partial least squares regression | |
Xiaobo et al. | Genetic algorithm interval partial least squares regression combined successive projections algorithm for variable selection in near-infrared quantitative analysis of pigment in cucumber leaves | |
CN108680515B (en) | Single-grain rice amylose quantitative analysis model construction and detection method thereof | |
Martín-Tornero et al. | Comparative quantification of chlorophyll and polyphenol levels in grapevine leaves sampled from different geographical locations | |
Jin et al. | Predicting the nutrition deficiency of fresh pear leaves with a miniature near-infrared spectrometer in the laboratory | |
Prananto et al. | Rapid and cost-effective nutrient content analysis of cotton leaves using near-infrared spectroscopy (NIRS) | |
Yang et al. | High-resolution and non-destructive evaluation of the spatial distribution of nitrate and its dynamics in spinach (Spinacia oleracea L.) leaves by near-infrared hyperspectral imaging | |
CN111426645A (en) | Method for rapidly determining nitrogen content of different organs of plant | |
Guo et al. | Estimation of foliar nitrogen of rubber trees using hyperspectral reflectance with feature bands | |
Lee et al. | Field assessment of macronutrients and nitrogen in apple leaves using a chlorophyll meter | |
CN110596048A (en) | Method for quickly measuring potassium content in tobacco leaves by spectrum | |
Yang et al. | Retrieving potassium levels in wheat blades using normalised spectra | |
Anthony et al. | Robust non-destructive individual cultivar models allow for accurate peach fruit quality and maturity assessment following customization in phenotypically similar cultivars | |
Yang | Nondestructive prediction of optimal harvest time of cherry tomatoes using VIS-NIR spectroscopy and PLSR calibration | |
Song et al. | Fractional-order derivative spectral transformations improved partial least squares regression estimation of photosynthetic capacity from hyperspectral reflectance | |
Ong et al. | Visible and near-infrared spectroscopic determination of sugarcane chlorophyll content using a modified wavelength selection method for multivariate calibration | |
CN107796779A (en) | The near infrared spectrum diagnostic method of rubber tree LTN content | |
Zhang et al. | Detection of tomato water stress based on terahertz spectroscopy | |
CN106404699A (en) | Nondestructive measurement method for contents of nitrogen elements of pear tree leaf blades |
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 |
Application publication date: 20201110 |
|
RJ01 | Rejection of invention patent application after publication |