CN116563667A - Sea ice roughness inversion method based on ensemble learning method and two-dimensional wavelet transformation - Google Patents
Sea ice roughness inversion method based on ensemble learning method and two-dimensional wavelet transformation Download PDFInfo
- Publication number
- CN116563667A CN116563667A CN202310535507.6A CN202310535507A CN116563667A CN 116563667 A CN116563667 A CN 116563667A CN 202310535507 A CN202310535507 A CN 202310535507A CN 116563667 A CN116563667 A CN 116563667A
- Authority
- CN
- China
- Prior art keywords
- sea ice
- roughness
- dimensional
- wavelet
- inversion
- 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
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000009466 transformation Effects 0.000 title claims abstract description 21
- 238000007636 ensemble learning method Methods 0.000 title claims abstract description 11
- 238000012549 training Methods 0.000 claims abstract description 8
- 238000011156 evaluation Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000005428 wave function Effects 0.000 claims description 6
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 claims description 4
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000005855 radiation Effects 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000002844 melting Methods 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 3
- 230000003746 surface roughness Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/766—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using regression, e.g. by projecting features on hyperplanes
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention provides a sea ice roughness inversion method based on an ensemble learning method and two-dimensional wavelet transformation, which comprises the steps of firstly extracting the space characteristics of sea ice from SAR images containing the sea ice in a target period in a target area through two-dimensional continuous wavelet transformation, then obtaining the actual sea ice roughness through all footprint data in the target period in the target area, and carrying out space matching on the original information of the SAR images and the space characteristics of the sea ice in the target period in the target area and the corresponding actual sea ice roughness to construct a total data set; and finally, taking the SAR image original information and sea ice spatial characteristics as inputs, and training the integrated learning model by taking the corresponding sea ice prediction roughness as output to obtain a sea ice roughness inversion model based on an integrated learning method. The invention can effectively solve the problems of large sea ice roughness inversion error and low resolution in the prior art.
Description
Technical Field
The invention belongs to the technical field of ocean remote sensing, and particularly relates to an sea ice roughness inversion method based on an integrated learning method and two-dimensional wavelet transformation.
Background
Sea ice roughness is an important factor affecting sea energy exchange and plays an important role in arctic climate systems. Therefore, the invention is very important to invent an accurate high-resolution sea ice roughness inversion method. The traditional field observation and the airborne LiDAR observation can obtain the altitude information of sea ice more accurately, so that the roughness of the sea ice is calculated more accurately. However, the two modes have small coverage in space and are scattered in [1]; the time is limited by extremely severe weather, so that all-day and all-weather observation cannot be realized; and both the two methods are quite labor and material consuming. Satellite remote sensing (such as synthetic aperture radar) can obtain sea ice backscattering images with large area and high space-time resolution. But it is difficult to invert the sea ice roughness by a trivial linear regression or the like model from the backscattering coefficient alone. The invention thus inverts the roughness of sea ice by combining the SAR image (Sentinel-1 data) with the elevation data of the airborne radar (OIB ATM L2 data).
There are two main ways of inverting sea ice roughness by the former. The first method is to calculate the Normalized Difference Angle Index (NDAI) by using the multi-angle reflection information obtained by different cameras in the multi-angle imaging spectrometer (MISR) 2, and then to establish the relation between NDAI and sea ice roughness by using a certain empirical algorithm. Common empirical algorithms include K-nearest neighbor (KNN) regression algorithms, support Vector Machine (SVM) algorithms, and the like. Although the sea ice roughness with higher resolution (275 m multiplied by 275 m) can be obtained by the method, the operation is simpler, but the roughness error obtained by inversion is very large. Moreover, the method needs to calculate the roughness of the whole product by adopting the elevation of the whole ATM product, and the calculation mode often ignores the roughness change of small scale inside the ATM product.
The second is to invert the sea ice roughness by a theoretical back scattering model of sea ice (e.g. IEM model) using the back scattering coefficient data of each pixel point of the SAR image [3]. This approach, while capable of achieving higher resolution sea ice roughness (depending on the resolution of the SAR image pixels) than the previous approach, also has a backscatter coefficient calculated from the inverted roughness that is closer to the backscatter coefficient of the SAR image itself. However, this method is not only difficult to implement, but also has high complexity of program time, and is difficult to apply to inversion with a large area.
Both methods invert sea ice roughness directly based on the statistical relationship of roughness and parameters measured directly by different sensors. However, the spatial distribution information of the sea ice features is not considered in the construction of the model, but the spatial information of the sea ice features can be obtained from the high-resolution SAR image. Therefore, the invention discloses a simple and feasible arctic sea ice roughness inversion method, which aims to solve the problems of low roughness inversion precision and low resolution in the prior art, and is a technical problem to be solved in the technical field.
Document [1]A.Nolin and E.Mar, "Arctic sea ice surface roughness estimated from multi-angular reflectance satellite imagery," Remote Sensing, vol.11, p.50,122018.
Document [2]E.Mosadegh and A.Nolin, "A new data processing system for generating sea ice surface roughness products from the multi-angle imaging spectroradiometer (MISR) imaging," Remote Sensing, vol.14, p.4979,102022.
Document [3]X.Wen,C.Xue,and Q.Dong, "The Arctic sea ice surface roughness estimation and application," Proceedings of the International Offshore and Polar Engineering Conference, pp.958-961,012011.
Disclosure of Invention
The invention aims to invent a simple and easy method for inverting the sea ice roughness, which aims to solve the problems of large sea ice roughness inversion error and low resolution in the prior art.
In order to achieve the aim of the invention, the invention provides a sea ice roughness inversion method based on an integrated learning method and two-dimensional wavelet transformation, which mainly comprises the following steps:
step 1: acquiring SAR images containing sea ice in a target period in a target area, and carrying out data preprocessing on each SAR image, wherein the preprocessing sequentially comprises the following steps: track correction, thermal noise removal, radiation calibration, speckle filtering, decibelization, two-dimensional linear interpolation. Obtaining a spatially uniform decibeled backscattering coefficient image, namely a two-dimensional space SAR image Coordinate vectors of pixel points in the image;
step 2: acquiring all sea ice footprint point data in a target period in a target area, and calculating the standard deviation of the elevation of the nearest preset number of footprint points for each footprint point to obtain the sea ice actual roughness of each footprint point;
step 3: SAR image for each two-dimensional spacePerforming complex two-dimensional continuous wavelet transformation to obtain each two-dimensional space SAR image +.>The complex wavelet coefficient of each pixel in (a)>Wherein phi is the wavelet rotation angle of each pixel point, a is the scale parameter of complex wavelet transformation in each pixel point,/and>a translation parameter for complex wavelet transformation in each pixel;
in the two-dimensional complex continuous wavelet transformation, the calculation formula of complex wavelet coefficients is shown in the following equation;
and->R -φ The formula of (2) is as follows:
wherein c ψ In order for the equation to meet the constant of the normalization condition,for spatial frequency +.>Conjugate of the two-dimensional Fourier transform function, which is the wavelet function ψ, +.>For spatial image +.>Is a two-dimensional fourier transform of (a); the scale parameter a is 1-32, the rotation angle phi is 0-2 pi interval +.>And (5) taking a value.
The wavelet mother function is a two-dimensional Ke Xixiao wave function, and the result after two-dimensional Fourier transformation is as follows:
wherein omega x Is the frequency in the x direction omega y The frequency in the y direction is the expansion parameter of the wavelet function, the alpha is the half open angle of the convex cone where the two-dimensional Ke Xixiao wave function definition domain is located.
Step 4: traversing all scale parameters and rotation angle parameters for each pixel point in each SAR image to obtain a scale parameter a corresponding to the maximum modulus of the complex wavelet coefficient m And rotation angle parameter phi m ，a m And phi m Constructing spatial information of sea ice, wherein I.I. represents taking a model;
step 5: spatially matching SAR image original information and sea ice space characteristic information in a target period in a target area and corresponding sea ice actual roughness to construct a total data set containing the information;
step 6: taking SAR image original information and sea ice space feature information as inputs, taking corresponding sea ice prediction roughness as a model output, and training an Adaboost regression learner by using a training set to obtain a trained sea ice roughness inversion model based on Adaboost regression;
step 7: and (3) predicting the test set through the regression model obtained in the step (6) to obtain sea ice predicted roughness of the test set, and carrying out model preliminary evaluation, authenticity inspection and deep evaluation.
The model preliminary evaluation is to calculate model evaluation indexes by using actual roughness and predicted roughness of a test set, and the calculation formulas of the indexes are as follows:
wherein R is 2 To determine the coefficients, MAE is the mean absolute error, RMSE is the root mean square error, MAPE is the mean absolute percentage error, y i Is a true value,Is a predictive value,/->Is the average of the true values, N is the number of samples.
The beneficial effects are that: compared with the prior art, the technical scheme of the invention has the following beneficial technical effects: the invention provides a simple and feasible method for inverting sea ice roughness by combining SAR images through Adaboost regression and two-dimensional wavelet transformation, which solves the defects of large inversion error, low resolution or long program calculation time and difficult realization in the prior art. The method provides a data source for inverting characteristics such as sea ice thickness and density, and can also provide a certain reference for predicting the climate evolution of a target area.
Drawings
FIG. 1 is a flow chart of the sea ice roughness inversion method based on the ensemble learning method and the two-dimensional wavelet transform of the present invention;
FIG. 2 is a chart of the results of inversion of sea ice concentration during the ice melting period based on an Adaboost regression model;
fig. 3 is a graph of the verification result based on the Adaboost regression model.
Detailed Description
The present invention is further illustrated in the accompanying drawings and detailed description which are to be understood as being merely illustrative of the invention and not limiting of its scope, and various equivalent modifications to the invention will fall within the scope of the appended claims to the skilled person after reading the invention.
The invention discloses a sea ice roughness inversion method based on an ensemble learning method and two-dimensional wavelet transformation, which is shown in fig. 1, wherein the method comprises the following steps: acquiring SAR images containing sea ice in a target period in a target area, and carrying out data preprocessing on each SAR image, wherein the preprocessing sequentially comprises the following steps: track correction, thermal noise removal, radiation calibration, speckle filtering, decibelization, two-dimensional linear interpolation. Obtaining a spatially uniform decibeled backscattering coefficient image, namely a two-dimensional space SAR image Coordinate vectors of pixel points in the image;
step 2: acquiring all sea ice footprint point data in a target period in a target area, and calculating the standard deviation of the elevation of the nearest preset number of footprint points for each footprint point to obtain the sea ice actual roughness of each footprint point;
step 3: SAR image for each two-dimensional spacePerforming complex two-dimensional continuous wavelet transformation to obtain each two-dimensional space SAR image +.>The complex wavelet coefficient of each pixel in (a)>Wherein phi is the wavelet rotation angle of each pixel point, and a is the complex in each pixel pointScale parameters of the several wavelet transforms, +.>A translation parameter for complex wavelet transformation in each pixel;
in the two-dimensional complex continuous wavelet transformation, the calculation formula of complex wavelet coefficients is shown in the following equation;
and->R -φ The formula of (2) is as follows:
wherein c ψ In order for the equation to meet the constant of the normalization condition,for spatial frequency +.>Conjugate of the two-dimensional Fourier transform function, which is the wavelet function ψ, +.>For spatial image +.>Is a two-dimensional fourier transform of (a); the scale parameter a is 1-32, the rotation angle phi is 0-2 pi interval +.>And (5) taking a value.
The wavelet mother function is a two-dimensional Ke Xixiao wave function, and the result after two-dimensional Fourier transformation is as follows:
wherein omega x Is the frequency in the x direction omega y The frequency in the y direction is the expansion parameter of the wavelet function, the alpha is the half open angle of the convex cone where the two-dimensional Ke Xixiao wave function definition domain is located.
Step 4: traversing all scale parameters and rotation angle parameters for each pixel point in each SAR image to obtain a scale parameter a corresponding to the maximum modulus of the complex wavelet coefficient m And rotation angle parameter phi m ，a m And phi m Constructing spatial information of sea ice, wherein I.I. represents taking a model;
step 5: spatially matching SAR image original information and sea ice space characteristic information in a target period in a target area and corresponding sea ice actual roughness to construct a total data set containing the information;
step 6: taking SAR image original information and sea ice space feature information as inputs, taking corresponding sea ice prediction roughness as a model output, and training an Adaboost regression learner by using a training set to obtain a trained sea ice roughness inversion model based on Adaboost regression;
step 7: and (3) predicting the test set through the regression model obtained in the step (6) to obtain sea ice predicted roughness of the test set, and carrying out model preliminary evaluation, authenticity inspection and deep evaluation.
The model preliminary evaluation is to calculate model evaluation indexes by using actual roughness and predicted roughness of a test set, and the calculation formulas of the indexes are as follows:
wherein R is 2 To determine the coefficients, MAE is the mean absolute error, RMSE is the root mean square error, MAPE is the mean absolute percentage error, y i Is a true value,Is a predictive value,/->Is the average of the true values, N is the number of samples.
FIG. 2 is a graph showing the inversion result of ice-melting period sea ice roughness based on Adaboost regression model, including the spatial distribution of SIR actual values and the spatial distribution of SIR predicted values in the mixed area of the ice-melting period sea ice of the summer and the ice-melting period sea (the range: 74-78 DEG N,158-162 DEG W, hereinafter referred to as research area) of 7 months 13 days and 14 days, and as can be seen from FIG. 2, the difference between the SIR actual values and the SIR predicted values only exists at individual sample points, so that the model can be primarily considered as effective;
FIG. 3 is a verification result based on an Adaboost regression model showing the addition of a test set to a model consisting of two-dimensional waveletAs can be seen from FIG. 3, the inversion after adding the spatial information is significantly better than the inversion before adding the spatial information, and the error index (MAE, RMSE and MAPE) is significantly reduced after adding the spatial information, and the index R is represented 2 The inversion method is significantly improved, and 0.91 is achieved after the spatial information is added, which is enough to show that the inversion method provided by the invention has extremely high precision.
The foregoing is merely illustrative of specific embodiments of the present invention and is not intended to limit the scope of the invention in any way, as long as the scope of the invention is not defined by the claims. All equivalent changes or substitutions made according to the essence of the invention are intended to be covered in the scope of the invention.
Claims (6)
1. The sea ice roughness inversion method based on the ensemble learning method and the two-dimensional wavelet transformation is characterized by comprising the following steps of:
step 1: acquiring SAR images containing sea ice in a target period in a target area, and carrying out data preprocessing on each SAR image to obtain spatially uniform decibelized backscattering coefficient images, namely two-dimensional space SAR images Coordinate vectors of pixel points in the image;
step 2: acquiring all sea ice footprint point data in a target period in a target area, and calculating the standard deviation of the elevation of the nearest preset number of footprint points for each footprint point to obtain the sea ice actual roughness of each footprint point;
step 3: SAR image for each two-dimensional spacePerforming complex two-dimensional continuous wavelet transformation to obtain each two-dimensional space SAR image/>The complex wavelet coefficient of each pixel in (a)>Wherein phi is the wavelet rotation angle of each pixel point, a is the scale parameter of complex wavelet transformation in each pixel point,/and>a translation parameter for complex wavelet transformation in each pixel;
step 4: traversing all scale parameters and rotation angle parameters for each pixel point in each SAR image to obtain a scale parameter a corresponding to the maximum modulus of the complex wavelet coefficient m And rotation angle parameter phi m ，a m And phi m Constructing spatial information of sea ice, wherein I.I. represents taking a model;
step 5: spatially matching SAR image original information and sea ice space characteristic information in a target period in a target area and corresponding sea ice actual roughness to construct a total data set containing the information;
step 6: taking SAR image original information and sea ice space feature information as inputs, taking corresponding sea ice prediction roughness as a model output, and training an Adaboost regression learner by using a training set to obtain a trained sea ice roughness inversion model based on Adaboost regression;
step 7: and (3) predicting the test set through the regression model obtained in the step (6) to obtain sea ice predicted roughness of the test set, and carrying out model preliminary evaluation, authenticity inspection and deep evaluation.
2. The sea ice roughness inversion method based on the ensemble learning method and the two-dimensional wavelet transform as claimed in claim 1, wherein in the two-dimensional complex continuous wavelet transform described in step 3, the calculation formula of complex wavelet coefficients is shown in the following equation;
and->R -φ The formula of (2) is as follows:
wherein c ψ In order for the equation to meet the constant of the normalization condition,for spatial frequency +.>Conjugate of the two-dimensional Fourier transform function, which is the wavelet function ψ, +.>Is a two-dimensional fourier transform of the aerial image s (x); the scale parameter a is 1-32, the rotation angle phi is 0-2 pi interval +.>And (5) taking a value.
3. The sea ice roughness inversion method based on the ensemble learning method and the two-dimensional wavelet transform as claimed in claim 2, wherein in the two-dimensional complex continuous wavelet transform in step 3, the wavelet mother function is a two-dimensional Ke Xixiao wave function, and the result after the two-dimensional fourier transform is:
wherein omega x Is the frequency in the x direction omega y The frequency in the y direction is the expansion parameter of the wavelet function, the alpha is the half open angle of the convex cone where the two-dimensional Ke Xixiao wave function definition domain is located.
4. The sea ice roughness inversion method based on the ensemble learning method and the two-dimensional wavelet transform as claimed in claim 1, wherein the data preprocessing of the SAR image in step 1 sequentially comprises the steps of: track correction, thermal noise removal, radiation calibration, speckle filtering, decibelization, two-dimensional linear interpolation.
5. The sea ice roughness inversion method based on an ensemble learning method and a two-dimensional wavelet transform as claimed in claim 1, wherein step 5 randomly breaks up all samples of the total data set obtained and divides into training set and test set in a ratio of 7:3.
6. The sea ice roughness inversion method based on the ensemble learning method and the two-dimensional wavelet transform as claimed in claim 1, wherein in the step 7, the model preliminary evaluation is to calculate model evaluation indexes by using actual roughness and predicted roughness of a test set, and each index calculation formula is as follows:
wherein R is 2 To determine the coefficients, MAE is the mean absolute error, RMSE is the root mean square error, MAPE is the mean absolute percentage error, y i Is a true value,Is a predictive value,/->Is the average of the true values, N is the number of samples.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310535507.6A CN116563667A (en) | 2023-05-12 | 2023-05-12 | Sea ice roughness inversion method based on ensemble learning method and two-dimensional wavelet transformation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310535507.6A CN116563667A (en) | 2023-05-12 | 2023-05-12 | Sea ice roughness inversion method based on ensemble learning method and two-dimensional wavelet transformation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116563667A true CN116563667A (en) | 2023-08-08 |
Family
ID=87499679
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310535507.6A Pending CN116563667A (en) | 2023-05-12 | 2023-05-12 | Sea ice roughness inversion method based on ensemble learning method and two-dimensional wavelet transformation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116563667A (en) |
-
2023
- 2023-05-12 CN CN202310535507.6A patent/CN116563667A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112213727B (en) | Precipitation correction method of satellite-borne radar based on active and passive microwave combined detection | |
| CN109100717B (en) | Multi-source microwave remote sensing sea surface wind field data fusion method and device | |
| Karvonen | Baltic sea ice concentration estimation using SENTINEL-1 SAR and AMSR2 microwave radiometer data | |
| Lindskog et al. | Doppler radar wind data assimilation with HIRLAM 3DVAR | |
| CN106204539B (en) | A method of the inverting urban architecture object sedimentation based on Morphological Gradient | |
| Bruck et al. | TerraSAR-X/TanDEM-X sea state measurements using the XWAVE algorithm | |
| Anderson et al. | Analysis of ASCAT ocean backscatter measurement noise | |
| Douxchamps et al. | Stereoscopic and velocimetric reconstructions of the free surface topography of antidune flows | |
| JP3783058B2 (en) | Method and system for inverse estimation of wave direction spectrum from radar image | |
| CN116563667A (en) | Sea ice roughness inversion method based on ensemble learning method and two-dimensional wavelet transformation | |
| Refice et al. | On the use of anisotropic covariance models in estimating atmospheric DInSAR contributions | |
| Karaev et al. | Radar sensing of sea ice at the small incidence angles: simulation and comparison of the different approaches | |
| CN114067064A (en) | Target three-dimensional reconstruction method based on multi-view radar image | |
| Pejcic et al. | Polarimetric radar-based methods for evaluation of hydrometeor mixtures in numerical weather prediction models | |
| Chen et al. | Sand ripple characterization using an extended synthetic aperture sonar model and parallel sampling method | |
| Yang et al. | A detection and information extraction approach for uav swarm | |
| CN117310708B (en) | SAR image sea surface wind field inversion method and system independent of external wind direction | |
| CN110991354A (en) | ISAR image identification method based on inverse space transformation network | |
| Krinitskiy et al. | Estimating Significant Wave Height from X-Band Navigation Radar Using Convolutional Neural Networks | |
| Cui et al. | Wave Height Estimation and Validation Based on the UFS Mode Data of Gaofen-3 in South China Sea | |
| Wang et al. | Polarimetric radar observation of the melting layer during the pre-summer rainy season over South China | |
| CN113702977B (en) | Synthetic aperture radar sea surface wind field inversion method based on optimal interpolation model | |
| Tang et al. | Texture Feature Extraction Based on Millimeter-Wave SAR Sea Ice Data | |
| Nie | Wind/rain backscatter modeling and wind/rain retrieval for scatterometer and synthetic aperture radar | |
| Bovith et al. | Detecting weather radar clutter by information fusion with satellite images and numerical weather prediction model output |
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 |