CN108761456A - A kind of inversion method of leaf area index of crop - Google Patents
A kind of inversion method of leaf area index of crop Download PDFInfo
- Publication number
- CN108761456A CN108761456A CN201810424632.9A CN201810424632A CN108761456A CN 108761456 A CN108761456 A CN 108761456A CN 201810424632 A CN201810424632 A CN 201810424632A CN 108761456 A CN108761456 A CN 108761456A
- Authority
- CN
- China
- Prior art keywords
- polarization
- area index
- parameter
- leaf area
- data
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
- G01S13/90—Radar or analogous systems specially adapted for specific applications for mapping or imaging using synthetic aperture techniques, e.g. synthetic aperture radar [SAR] techniques
- G01S13/904—SAR modes
- G01S13/9076—Polarimetric features in SAR
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
- G01S13/90—Radar or analogous systems specially adapted for specific applications for mapping or imaging using synthetic aperture techniques, e.g. synthetic aperture radar [SAR] techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
- G01S13/90—Radar or analogous systems specially adapted for specific applications for mapping or imaging using synthetic aperture techniques, e.g. synthetic aperture radar [SAR] techniques
- G01S13/9021—SAR image post-processing techniques
- G01S13/9027—Pattern recognition for feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The present invention discloses a kind of inversion method of leaf area index of crop, including：S1 obtains research area's polarization radar image；S2 obtains polarization data of compacting from the polarization radar image simulation in S1.Using polarization radar figure, simulation obtains polarimetric radar data of compacting；S3 carries out polarization decomposing to the polarization data of compacting in S2, obtains the polarization parameter image that compacts with different physical significances；S6 carries out non-linear heredity-partial least-square regression method modeling, obtains the predicted value of leaves of winter wheat area index.The present invention provides the extraction schemes of the compact polarization SAR parameter highly relevant with Crop leaf area index parameters.GA-PLS methods are introduced into the information analysis for polarimetric radar remote sensing of compacting by the present invention for the first time, avoid the Physical Process Analyses of complexity early period, reduce human error.The present invention provides the technical solutions of the leaf area index inverting of the crop key developmental stages based on novel polarization SAR data of compacting.
Description
Technical field
The present invention relates to remote sensing technologies, more specifically, are related to the leaf area index inversion technique of crop.
Background technology
Leaf area index (Leaf Area Index, LAI) is the closely related basic parameter of Vegetation canopy structure, in agriculture
In industry research, it is directly related to crop growing state, growth period time and yield.It is a good Crop development and health indicator,
Used also as the input variable of many plant growths and Production Forecast Models.It is evaluation Agro-ecological System physiology and ecology life
The important parameter of reason process, monitoring crop growth and forecast production play an important roll on region and country scale.Remote sensing skill
Art has the characteristics that periodically to observe in terms of obtaining terrestrial information and large area covers.It plays and focuses in agricultural resource monitor
It acts on.It can capture the distributed intelligence of land vehicles critical biophysical parameter on room and time.Therefore, it can be with
A practicable method is provided to observe the leaf area index in macro-scale.
Currently, optical remote sensing is the main means of monitoring crop growth parameter(s), Application Optics remotely-sensed data is long into row crop
Gesture monitors oneself through foring the technical method of a set of comparative maturity, precision oneself reach higher level.But in northern China drought
Ground kharif main growing period, sexual intercourse weather are affected, and can not in time, effectively obtain complete, continuous optical remote sensing
Data are observed, therefore very necessary using the study on monitoring of radar remote sensing progress dry crop.Synthetic aperture radar
The appearance of (Synthetic Aperture Radar, SAR) makes crops monitoring not influenced by cloud, mist, rain, ensure that number
According to the independence obtained with local weather, and when microwave remote sensing detection vegetation information, can get with optical sensor completely not
Same information.Based on this, many scholars have carried out a large amount of experimental study, to inquire into sensibility of the SAR to crop LAI.Polarization
It is a kind of Electric Field Characteristics of electromagnetic wave, the radar wave of different scattering volume scatterings contains different polarization informations, describes not
Same physical scatterers process.The development experience of polarimetric radar from single polarization to dual polarization again to the process of complete polarization, and full pole
Change data and provides polarization information the abundantest.Therefore, polarization radar data are frequently used to inverting vegetation and earth's surface
Various parameters.Estimating the algorithm of crop LAI from SAR image at present, there are two main classes：It method based on empirical model and is based on
The method of semiempirical model.Method based on empirical model be mainly using regression analysis method to the LAI parameters of crop into
Row estimation.
Although full-polarization SAR has good performance in LAI invertings, its known limitation is to utilize the pulse weight repeated
Complex frequency scans the strip width of the reduction caused by the polarized all combinations of transmission/reception.In order to overcome such limitation,
Compact polarization SAR, and the imaging pattern for only sending circular polarisation two orthogonal linear polarizations of reception has been suggested.Compact polarization SAR
(Compact Synthetic Aperture Radar, CP SAR), also referred to as condenses or tightens polarization SAR, be it is a kind of it is novel at
As radar system, it emits a kind of polarized wave, receives two kinds of orthogonally polarized waves, effectively reduces SAR system complexity and energy consumption,
Reduce sensor bulk, it has also become one of the important trend of earth observation SAR system of new generation.It polarizes in imaging radar
In level, polarization is compacted between complete polarization and dual polarization.Compared with full-polarization SAR, the polarization SAR that compacts can not only be one
Determine to keep polarization information in degree, moreover it is possible to which the breadth and ranges of incidence angles for realizing bigger meet some special application demands.This
Outside, the polarization SAR that compacts also has the advantages such as self calibration, cross validation.April first in 2012 has polarization measurement ability of compacting
Earth observation radar satellite RISAT-1 (Radar Imaging Satellite 1) successful launch.The Japan of transmitting in 2014
ALOS-2 (Advanced Land Observation Satellite 2) satellite is also using polarization of compacting as experimental data mould
Formula.The coming years, Canadian RCM (Radar Constellation Mission), Argentinian SAOCOM (Satelite
Argentino de Observacion Con Microondas), the U.S. DESDynI (Deformation, Ecosystem
Structure and Dynamics of Ice) also by SAR satellite of the transmitting with the polarization observation mode that compacts.With over the ground
Becoming increasingly abundant for polarization SAR system of compacting is observed, carrying out the key application technical research based on polarization SAR data of compacting seems outstanding
It is urgent.Meanwhile using novel polarization SAR data of compacting, carrying out typical feature target response signature analysis, development has higher
The information extraction algorithm of robustness leads the development and radar remote sensing technology that push China's future SAR sensor in correlation
The application in domain is of great significance.Technology based on polarimetric radar data inversion crops parameter of compacting on condition that must find and
The mostly concerned polarization parameter of the biophysical chemistry parameter of crop, could establish accurate inverse model in this way.Therefore, it faces
The a large amount of polarization information that polarization data of compacting is brought, it is most important for the screening for the polarization information that compacts.
The existing crops parametric inversion technology based on radar mostly uses greatly full polarimetric SAR data, and is mostly using single
The method of polarization parameter inverting, is as follows：
1. according to studying the existing cognition in area, artificially judge that goal in research is any scattering mechanism.
2. field measurement takes several samples in research area, using field test or the method for laboratory sample measurement,
Obtain the characteristic parameter data of goal in research.
3. under the premise of known to the physical scatterers mechanism to certain polarization parameters, finds one and dissipated with the goal in research
The polarization parameter that mechanism is most consistent is penetrated, the polarization parameter data are obtained using technologies such as polarization decomposings.
4. the characteristic parameter data of the polarization parameter data and goal in research are established simply by way of data training
Linear relationship.
5. according to the correlativity, polarization parameter image is inputted, is finally inversed by the characteristic parameter image in research area.
The prior art has the following defects and deficiency：
1. the prior art is mainly both for polarization radar data, the limited coverage area of full polarimetric SAR data, big
It can be limited by many in terms of the popularization and application of range.
2. in polarization radar application aspect, the prior art is joined only with the complete polarization of those known physics scattering mechanisms
Number, the novel polarization information for not making full use of polarization data of compacting to bring.It polarizes in the various dimensions of crop parameter sensitivity
In terms of the selection of characteristic parameter, current main technical method is all the side using the artificial scattering mechanism for judging goal in research
Formula, for precision dependent on researcher to the degree of understanding of goal in research, the interference of human error is larger.
3. existing many technologies only simulate the physical scatterers process for approaching goal in research with a polarization parameter.And from
The scattering mechanism of right atural object is extremely complex, in most cases it is difficult to be expressed with a significant physical process, but it is multiple
The general performance of physical process.
Invention content
Although the dimension for the polarization SAR observation space that compacts decreases relative to full-polarization SAR, it has been proved in water
With huge potentiality and with the performance similar with full-polarization SAR in terms of rice drawing.It is few at present to be based on the polarization thunder that compacts
The research of inverting is carried out to leaves of winter wheat area index up to data.Also less someone is using non-linear hereditary offset minimum binary (GA-
PLS) algorithm carries out selection and the dimensionality reduction of SAR characteristic parameters.The purpose of the present invention is utilize polarimetric radar data inversion of compacting
The leaf area index of crop is obtained, and expands application potential of the polarimetric radar data in crops parametric inversion that compact.
For this purpose, the present invention proposes a kind of inversion method of leaf area index of crop, including：
S1 obtains research area's polarization radar image；
S2 obtains polarization data of compacting from the polarization radar image simulation in S1.Utilize polarization radar figure, simulation
Obtain polarimetric radar data of compacting；
S3 carries out polarization decomposing to the polarization data of compacting in S2, obtains the polarization ginseng of compacting with different physical significances
Number image；
S5 is measured and is obtained the parameter value of the leaf area index of winter wheat in selected research area；
S6 carries out non-linear heredity-partial least-square regression method modeling, obtains the prediction of leaves of winter wheat area index
Value.
Beneficial effects of the present invention include：
1) the present invention provides the extraction sides of the compact polarization SAR parameter highly relevant with Crop leaf area index parameters
Case.
2) GA-PLS methods are introduced into the information analysis for polarimetric radar remote sensing of compacting by the present invention for the first time, and it is multiple to avoid early period
Miscellaneous the Physical Process Analyses reduce human error, do not do any quantification it is assumed that from data level screening polarization information channel；?
In terms of the dimensionality reduction of various dimensions polarization characteristic parameter, the present invention proposes the dynamical multi-parameter for polarimetric radar data of compacting
Dimension-reduction algorithm.
3) the present invention provides the leaf area index invertings of the crop key developmental stages based on novel polarization SAR data of compacting
A full set of technical solution.
Description of the drawings
Fig. 1 is the Technology Roadmap of an embodiment of the method for the present invention.
The flow chart of one embodiment of the method for Fig. 2 present invention.
Fig. 3 is to be compacted the obtained composite diagram of polarization decomposing three-component by Renny.
Fig. 4 be compact polarization parameter importance selection schematic diagram.
Fig. 5 is the scatter plot of the LAI values of actual measurement and inverting.
Specific implementation mode
Embodiments of the present invention are described with reference to the accompanying drawings, wherein identical component is presented with like reference characters.
In the absence of conflict, the technical characteristic in following embodiment and embodiment can be combined with each other.
Below by taking winter wheat as an example for what the present invention method technical solution, with this, those skilled in the art can
To expand to other kinds of crop with not making the creative labor.
The present invention is deeply excavated by compact polarization SAR response pattern and the mechanism in research winter wheat crucial phenological period time
Application potential of the polarization SAR data of compacting in winter wheat LAI invertings establishes the winter wheat LAI based on polarization SAR data of compacting
Inversion method, improve compact polarization SAR dry land crop monitoring in application level, be winter wheat Growing state survey with the yield by estimation,
Field management, resource distribution and decision provide basic information.
Referring to Fig.1, technical principle of the invention is, first with RADARSAT-2 full-polarization SAR digital simulation CP SAR
Data.On this basis, the extraction based on compact polarization scattering matrix and polarization decomposing method of compacting obtains having certain physics
The CP SAR parameters of meaning.Then, some most sensitive CP SAR parameters have been selected using feature selecting algorithm, are based on mathematics
Regression modeling algorithm builds the inverse model of winter wheat LAI.Finally, the field period synchronous with satellite transit time is utilized
Interior, the LAI data measured carry out comprehensive, system verification to inversion accuracy.
More specifically, with reference to Fig. 2, the method for the present invention includes：
S1 obtains research area's polarization radar image.
Polarization radar image contains most comprehensive polarization information, and the scattering that scatterer can be described more fully with is special
Sign.
In one embodiment, RADARSAT-2 data may be used.By RADARSAT-2 polarization radar initial data
By pretreatments such as radiation calibration, filtering, geometric calibrations, polarization radar image, the radiation calibration, filtering, geometry are obtained
Method generally in the art may be used in calibration processing.
S2 obtains polarization data of compacting from the polarization radar image simulation in S1.Utilize polarization radar figure, simulation
Obtain polarimetric radar data of compacting used in later process.
More specifically, using RADARSAT-2 full polarimetric SAR datas (S2 matrixes), covariance matrix C3 is generated.It is then based on line
Transformational relation between polarization and right-handed circular polarization is established the polarization SAR data Stokes vectors that compact and is assisted with full-polarization SAR data
Relationship between variance matrix C3 matrixes realizes the polarization SAR digital simulation that compacts.Analogue data is deposited in the form of Stokes vectors
Storage.
S3 carries out polarization decomposing to the polarization data of compacting in S2, obtains the polarization ginseng of compacting with different physical significances
Number, and then obtain the polarization parameter image that compacts.Decomposition technique is the main means of polarographic analysis, passes through decomposition technique
Different polarization parameters can be obtained, the scattering properties of scatterer is described from different physics aspects.By to the polarization number that compacts
According to the extraction and decomposition of (CP SAR matrixes), 19 relevant polarization parameters that compact (CP parameters), respectively Raney_ have been obtained
Rnd,Raney_Dbl,RV,RR,RL,RH,Raney_Odd,p2,p1,l2,l1,Contrast,LPR,H,DoLP,DoCP,CPR,
A and Raney_m, these polarization parameters that compact can combine, and GA-PLS modelings are carried out as input variable.
Fig. 3 is the polarization data of compacting simulated by full polarimetric SAR data, extracts the composograph of three obtained component.
Fig. 3 show by Renny compact the obtained composite diagram of polarization decomposing three-component (including:Raney_ dihedral angle scattering components；
Raney_ volume scattering components；Raney_ area scatterings component).
S4 pre-processes the polarization parameter image that compacts obtained in S3.It compacts the pretreatment point of polarization parameter image
For two parts：
S41 carries out geometric correction to all polarization parameter images that compact.
S42 reads the polarization of compacting of each sampled point on the image based on the polarization parameter image that compacts obtained in S41
Parameter value.In one embodiment, since there are the interference effects of speckle noise and electromagnetic wave for radar image, in sampled point
A zonule nearby delimited, the region is taken to compact compact polarization parameter value of the average value as the sampled point of polarization parameter.
S5 is measured and is obtained the parameter value of the leaf area index of winter wheat in selected research area.Can using measuring instrument come
Obtain the parameter value of the leaf area index of winter wheat in selected research area.It is planted for example, by using the LAI-2200 of LI.COR companies production
By Canopy Analyzer.LAI-2200 need not contact crop, directly observe the upper and lower diffusing scattering variation of wheat canopy and ask indirectly
Effective LAI of winter wheat, effective LAI is taken to be equivalent to practical LAI in practical applications, their light all having the same intercept and capture energy
Power.In one embodiment, several trial zones can be uniformly chosen in research area, measures the number of the leaf area index of sample
Value.
S6 carries out GA-PLS modelings.Modeling process is divided into two large divisions：
S61 filters out several the compact polarization parameters mostly concerned with area's characteristic parameter is studied using genetic algorithm (GA).
Overall parameter before screening is respectively Raney_Rnd, Raney_Dbl, RV, RR, RL, RH, Raney_Odd, p2,
P1, l2, l1, Contrast, LPR, H, DoLP, DoCP, CPR, A and Raney_m.Mostly concerned criterion is to pass through something lost
Propagation algorithm come the polarization parameter importance that judges to compact, i.e., with wait for inverting parameter between correlation degree of correlation size.
Genetic algorithm is exactly that all independents variable, dependent variable are encoded into binary code, is based on genetics principle, selects
The mostly concerned independent variable with dependent variable.By the screening for the polarization parameter that compacts, final inversion accuracy can be effectively improved.
S62 establishes inverting mould based on the polarization parameter data selected in S61 with offset minimum binary (PLS) homing method
Type obtains the predicted value of leaves of winter wheat area index.GA-PLS is the mathematical algorithm of a relative maturity, is widely used in various
In multiple regression analysis, but do not apply also in the field for compacting polarimetric radar Remote sensing parameters inverting.The present invention introduces it into
In crops parametric inversion technology based on the polarization parameter that compacts, this is unexistent in the prior art.
It obtains the principle of the predicted value of leaves of winter wheat area index and steps are as follows：
Partial least-square regression method principle is as follows：
Assuming that sample size is N, the data matrix of independent variable is X, and the data matrix of dependent variable is y.
First, principal component analysis is carried out to X and y：
X=TP '+E
Y=UQ '+F
Wherein, T and U is score matrix (i.e. principal component matrix), represents the main information of X and y, and P and Q are load moments
Battle array, E and F are residual matrixes.
Secondly, the regression equation of principal component T and U is established
U=BT
Finally, final inverse model is calculated
Y=Xb+c
Wherein, b is regression coefficient vector, and c is residual vector.
Based on above-mentioned GA-PLS principles, code is write, by the polarization parameter data of all samples and actual measurement characteristic parameter number
It is tables of data according to arranging, reads in the program finished and run, obtain last equation of linear regression, sieved from the equation
The polarization parameter elected and corresponding weight.Equation of linear regression is as follows：
Y=a × X1+b×X2+c×X3+…
Wherein Xi(i=1,2,3 ...) is the polarization parameter screened, and coefficient a, b, c are corresponding weights, represent phase
The size of closing property, y is characteristic parameter.
S7, the predicted value obtained in measured value and S6 based on the leaves of winter wheat area index obtained in S5 carry out precision and comment
Valence obtains the precision evaluation result of leaves of winter wheat area index inversion result.
Calculate the root-mean-square error (RMSE) of all samples, the precision of prediction of evaluation model.It is examined by precision evaluation
With the accuracy for judging arithmetic result.
Wherein, yi' and yiIt is the predicted value and measured value of sample i respectively.
S8 generates inversion chart according to the inverse model established in S6.Based on the inversion formula calculated, input in S4
The polarization parameter image that compacts screened using remote sensing software or writes the last research area leaves of winter wheat area of code building
The remote-sensing inversion figure of index.
For on the whole, by CP SAR emulation and CP decomposition methods, it can be generated from original SAR image with difference
The CP parameters of physical significance.There are correlativities with leaves of winter wheat area index for these CP parameters.Feature selecting algorithm is drawn
Enter the parameter that can be selected and can preferably characterize leaves of winter wheat area index.Utilize the algorithm of regression modeling just on this basis
The accurate mathematical relationship between filtered out CP parameters and leaf area index variable can be established.I.e. first with complete polarization number
According to the collision matrix S and complex covariance matrix C for simulating the polarization data that obtains compacting.Then, many polarization parameters that compacts can
It is obtained with being extracted from these matrixes.Being decomposed by Cloude for CP polarization decomposing parameters is obtained with Renny decomposition computations.
These polarization parameters that compact are modeled as input variable.According to the position of SAR image and leaf area index sample
It sets, selects correction of a part of sample point for model, remaining sample is for verifying.Based on CP synthetic aperture radar theory and
The CP parameters that CP decomposition methods are calculated are as independent variable matrix x, while the leaf area index value measured in each sampled point
Group dependent variable vector.By mathematical modeling, equation of linear regression form that final inverse model can be expressed as：
Y=a1x1+a2x2+a3x3+… (1)
Wherein xiIt is the polarization parameter filtered out by feature selecting while aiBe corresponding regression coefficient (i=1,2,
3…).The schematic diagram of the process of parameter importance selection is as shown in Figure 4.
When genetic algorithm is applied to feature selecting, function is selection and the closely related independent variable of independent variable.Definition
The independent variable closely related with correlated variables, by Partial Least Squares establishes a specific mathematics multivariate regression models.
The scatter plot of modeling result is as shown in Figure 4.Dot represents calibration sample, and triangle represents verification sample (Fig. 4).Blue solid lines are
1:1 normal line.During this investigation it turned out, the coefficient of determination (R2, no unit) and root-mean-square error (RMSE, square metre/square metre),
It is used to the estimation precision of relationship and this method that assessment measures between estimation LAI.The numerical value of the R2 of this research reaches
0.70, root-mean-square error deviation is 0.40 square metre/square metre, this shows to obtain with inverting based on CP SAR parameters higher
The winter wheat LAI inversion results of precision.From the point of view of the distribution of dispersal point shown in Fig. 4, it is selected go out CP parameters and winter wheat
It is in near-linear dependency between LAI.
Embodiment described above, the only present invention more preferably specific implementation mode, those skilled in the art is at this
The usual variations and alternatives carried out within the scope of inventive technique scheme should be all included within the scope of the present invention.
Claims (10)
1. a kind of inversion method of leaf area index of crop, which is characterized in that including：
S1 obtains research area's polarization radar image；
S2 obtains polarization data of compacting from the polarization radar image simulation in S1.Using polarization radar figure, simulation obtains
Polarimetric radar of compacting data；
S3 carries out polarization decomposing to the polarization data of compacting in S2, obtains the polarization parameter figure that compacts with different physical significances
Picture；
S6 carries out non-linear heredity-partial least-square regression method modeling, obtains the predicted value of leaves of winter wheat area index.
2. the inversion method of leaf area index of crop according to claim 1, which is characterized in that in step s3, described
The polarization parameter that compacts includes：Raney_Rnd,Raney_Dbl,RV,RR,RL,RH,Raney_Odd,p2,p1,l2,l1,
Contrast, LPR, H, DoLP, DoCP, CPR, A and Raney_m.
3. the inversion method of leaf area index of crop according to claim 1, which is characterized in that between step S3 and S5
Further include：
S4, pre-processes the polarization parameter image that compacts obtained in S3, and the pretreatment for the polarization parameter image that compacts includes：
S41 carries out geometric correction to all polarization parameter images that compact；And
S42 reads the polarization parameter that compacts of each sampled point on the image based on the polarization parameter image that compacts obtained in S41
Value.
4. the inversion method of leaf area index of crop according to claim 3, which is characterized in that
In S42, near sampled point delimit a zonule, take the region compact polarization parameter average value as the sampling
The polarization parameter value of compacting of point.
5. the inversion method of leaf area index of crop according to claim 1, which is characterized in that step S6 includes：
S61 filters out several the compact polarization parameters mostly concerned with area's characteristic parameter is studied using nonlinear genetic algorithm；
S62 is established inverse model with partial least-square regression method, it is small to be obtained the winter based on the polarization parameter data selected in S61
The predicted value of wheat leaf area index.
6. the inversion method of leaf area index of crop according to claim 5, which is characterized in that
In S61, the overall parameter before screening is respectively Raney_Rnd, Raney_Dbl, RV, RR, RL, RH, Raney_
Odd, p2, p1, l2, l1, Contrast, LPR, H, DoLP, DoCP, CPR, A and Raney_m, mostly concerned criterion be,
By genetic algorithm come the polarization parameter importance that judges to compact, i.e., with wait for inverting parameter between correlation degree of correlation it is big
It is small.
7. the inversion method of leaf area index of crop according to claim 6, which is characterized in that in step S62, obtain
The step of predicted value of leaves of winter wheat area index includes：
1) it is based on non-linear heredity-partial least-square regression method principle, the polarization parameter data of all samples and actual measurement are special
It is tables of data to levy supplemental characteristic and arrange, and obtains last equation of linear regression；
2) polarization parameter screened from the equation and corresponding weight；
Eggplant river, equation of linear regression are as follows：
Y=a × X1+b×X2+c×X3+…
Wherein Xi(i=1,2,3 ...) is the polarization parameter screened, and coefficient a, b, c are corresponding weights, represent correlation
Size, y is characteristic parameter.
8. the inversion method of leaf area index of crop according to claim 1, which is characterized in that including：
S5 is measured and is obtained the parameter value of the leaf area index of winter wheat in selected research area；
S7, the predicted value obtained in measured value and S6 based on the leaves of winter wheat area index obtained in S5 carry out precision evaluation,
Obtain the precision evaluation result of leaves of winter wheat area index inversion result.
9. the inversion method of leaf area index of crop according to claim 8, which is characterized in that
By calculating the root-mean-square error of all samples, carry out the precision of prediction of evaluation model.
10. the inversion method of leaf area index of crop according to claim 8, which is characterized in that include after S7：
S8 generates inversion chart according to the inverse model established in S6, based on the inversion formula calculated, inputs in S4 and screens
The polarization parameter image that compacts out generates the remote-sensing inversion figure of last research area's leaves of winter wheat area index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810424632.9A CN108761456A (en) | 2018-05-07 | 2018-05-07 | A kind of inversion method of leaf area index of crop |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810424632.9A CN108761456A (en) | 2018-05-07 | 2018-05-07 | A kind of inversion method of leaf area index of crop |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108761456A true CN108761456A (en) | 2018-11-06 |
Family
ID=64010033
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810424632.9A Pending CN108761456A (en) | 2018-05-07 | 2018-05-07 | A kind of inversion method of leaf area index of crop |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108761456A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109615551A (en) * | 2018-11-15 | 2019-04-12 | 中国农业科学院农业资源与农业区划研究所 | The wheat crops inversion method of leaf area index simulated based on microwave scattering and canopy |
| CN109992863A (en) * | 2019-03-22 | 2019-07-09 | 北京师范大学 | A kind of LAI inversion method and device |
| CN110378896A (en) * | 2019-07-25 | 2019-10-25 | 内蒙古工业大学 | TomoSAR vegetation pest and disease monitoring method and device based on polarization coherence |
| CN111723328A (en) * | 2020-06-18 | 2020-09-29 | 中国科学院空天信息创新研究院 | Leaf area index time series reconstruction method, device, equipment and storage medium |
| CN115372970A (en) * | 2022-08-19 | 2022-11-22 | 陕西省土地工程建设集团有限责任公司 | Remote sensing extraction method for crops SAR in mountainous and hilly areas |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104199027A (en) * | 2014-08-29 | 2014-12-10 | 中国科学院遥感与数字地球研究所 | Method for realizing large-area near real-time monitoring on phenological period of rice based on compactly polarimetric radar |
| CN105372631A (en) * | 2015-10-29 | 2016-03-02 | 中国科学院遥感与数字地球研究所 | Polarizing radar inversion method based on genetic-partial least square algorithm, and application of polarizing radar inversion method |
-
2018
- 2018-05-07 CN CN201810424632.9A patent/CN108761456A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104199027A (en) * | 2014-08-29 | 2014-12-10 | 中国科学院遥感与数字地球研究所 | Method for realizing large-area near real-time monitoring on phenological period of rice based on compactly polarimetric radar |
| CN105372631A (en) * | 2015-10-29 | 2016-03-02 | 中国科学院遥感与数字地球研究所 | Polarizing radar inversion method based on genetic-partial least square algorithm, and application of polarizing radar inversion method |
Non-Patent Citations (2)
| Title |
|---|
| WANGFEIZHANG等: "USING COMPACT POLARIMETRIC PARAMETERS FOR RAPE(BRASSICA NAPUS L.)LAI INVERSION", 《2017 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS)》 * |
| 杨知: "基于极化SAR的水稻物候期监测与参数反演研究", 《中国博士学位论文全文数据库农业科技辑》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109615551A (en) * | 2018-11-15 | 2019-04-12 | 中国农业科学院农业资源与农业区划研究所 | The wheat crops inversion method of leaf area index simulated based on microwave scattering and canopy |
| CN109992863A (en) * | 2019-03-22 | 2019-07-09 | 北京师范大学 | A kind of LAI inversion method and device |
| CN110378896A (en) * | 2019-07-25 | 2019-10-25 | 内蒙古工业大学 | TomoSAR vegetation pest and disease monitoring method and device based on polarization coherence |
| CN111723328A (en) * | 2020-06-18 | 2020-09-29 | 中国科学院空天信息创新研究院 | Leaf area index time series reconstruction method, device, equipment and storage medium |
| CN111723328B (en) * | 2020-06-18 | 2024-02-13 | 中国科学院空天信息创新研究院 | Leaf area index time sequence reconstruction method, device, equipment and storage medium |
| CN115372970A (en) * | 2022-08-19 | 2022-11-22 | 陕西省土地工程建设集团有限责任公司 | Remote sensing extraction method for crops SAR in mountainous and hilly areas |
| CN115372970B (en) * | 2022-08-19 | 2024-06-28 | 陕西省土地工程建设集团有限责任公司 | SAR remote sensing extraction method for crops in mountainous and hilly areas |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108761456A (en) | A kind of inversion method of leaf area index of crop | |
| Betbeder et al. | Assimilation of LAI and dry biomass data from optical and SAR images into an agro-meteorological model to estimate soybean yield | |
| Paloscia et al. | A comparison of algorithms for retrieving soil moisture from ENVISAT/ASAR images | |
| Durand et al. | Feasibility test of multifrequency radiometric data assimilation to estimate snow water equivalent | |
| CN108303044B (en) | Leaf area index obtaining method and system | |
| Whetton et al. | Nonlinear parametric modelling to study how soil properties affect crop yields and NDVI | |
| CN110455722A (en) | Rubber tree blade phosphorus content EO-1 hyperion inversion method and system | |
| Yang et al. | Soil prediction for coastal wetlands following Spartina alterniflora invasion using Sentinel-1 imagery and structural equation modeling | |
| CN111678866A (en) | Soil water content inversion method for multi-model ensemble learning | |
| Dai et al. | Multivariate distributed ensemble generator: A new scheme for ensemble radar precipitation estimation over temperate maritime climate | |
| Hu et al. | Simultaneous state-parameter estimation supports the evaluation of data assimilation performance and measurement design for soil-water-atmosphere-plant system | |
| Wu et al. | Winter wheat LAI inversion considering morphological characteristics at different growth stages coupled with microwave scattering model and canopy simulation model | |
| CN109615551A (en) | The wheat crops inversion method of leaf area index simulated based on microwave scattering and canopy | |
| CN114140591A (en) | Soil organic matter remote sensing mapping method combining machine learning and land statistics | |
| de Lima Moraes et al. | Steady infiltration rate spatial modeling from remote sensing data and terrain attributes in southeast Brazil | |
| Singh et al. | Incorporation of first-order backscattered power in Water Cloud Model for improving the Leaf Area Index and Soil Moisture retrieval using dual-polarized Sentinel-1 SAR data | |
| CN115443889A (en) | Accurate irrigation method and device for crops | |
| Shakya et al. | Integrated modelling of soil moisture by evaluating backscattering models Dubois, Oh and IoT sensor development for field moisture estimation | |
| Del Frate et al. | Wheat cycle monitoring using radar data and a neural network trained by a model | |
| Lu et al. | Winter wheat leaf area index inversion by the genetic algorithms neural network model based on SAR data | |
| CN109765247A (en) | A kind of different bearing stage wheat crops overlay area Soil Moisture Inversion method | |
| CN113723000A (en) | Farmland soil moisture simulation method based on Sentinel data and deep learning model | |
| Manfreda et al. | On the use of AMSU-based products for the description of soil water content at basin scale | |
| Dou et al. | Soil moisture retrieval over crop fields based on two-component polarimetric decomposition: a comparison of generalized volume scattering models | |
| CN108254323A (en) | A kind of method based on absorption peak characteristic retrieval leaf area 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181106 |