Method, device and equipment for inverting typhoon wind speed through synthetic aperture radar, medium and product

Abstract

The invention discloses a method, a device, equipment, a medium and a product for inverting typhoon wind speed through a synthetic aperture radar, and relates to the field of ocean remote sensing and application, and the method comprises the steps: obtaining a group of observation data of the synthetic aperture radar when the typhoon wind speed is inverted through the synthetic aperture radar; obtaining an inversion value of the typhoon wind speed based on the weight of each observation parameter and a group of observation data of the synthetic aperture radar when the typhoon wind speed is inverted by the synthetic aperture radar; the weight determination process comprises the following steps: constructing a synthetic aperture radar inversion typhoon wind speed target function based on elastic network regularization; according to the training data set, solving a synthetic aperture radar inversion typhoon wind speed target function based on elastic network regularization to obtain the weight of each observation parameter; the training data set comprises multiple groups of observation data of the synthetic aperture radar and typhoon wind speeds corresponding to the observation data when the sample typhoon wind speeds are monitored by the synthetic aperture radar. According to the invention, high-precision inversion of the typhoon wind speed can be realized.

Description

Technical Field

[0001] The present application relates to the field of ocean remote sensing and its applications, and in particular to a method, device, equipment, medium and product for inverting typhoon wind speed using synthetic aperture radar. Background Art

[0002] Typhoon wind field detection methods can be divided into surface, aerial, and satellite. Surface buoys cannot track typhoons and have difficulty capturing strong wind areas. For safety reasons, ships generally need to avoid typhoons. Aircraft equipped with SFMR payloads are generally used to detect typhoon core areas from the air, but observations are difficult, infrequent, and limited to the North Atlantic and eastern Pacific Oceans. Satellite altimeters, scatterometers, radiometers, and synthetic aperture radars can all obtain sea surface wind field data over a wide range and in all weather conditions. However, altimeters can only obtain wind speeds at points below the satellite along the track, with limited coverage. Under typhoon conditions, the sea surface tends to be saturated. Scatterometers have weak high wind speed inversion capabilities. L-band radiometers can obtain high wind speeds under typhoon conditions, but their spatial resolution is less than 50 km, making it impossible to accurately depict wind speed variations in the typhoon core. Synthetic aperture radar is the only spaceborne instrument capable of detecting and quantitatively analyzing sea surface information with a spatial resolution of up to 1 km under extreme conditions. Its swath can reach hundreds of kilometers and its pixel resolution can reach several meters.

[0003] In related technologies, the method of using synthetic aperture radar to invert typhoon wind speed is usually to perform a linear fit between certain parameters of the synthetic aperture radar and the wind speed, and predict the wind speed through the fitting curve, but the accuracy is very low. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, equipment, medium and product for inverting typhoon wind speed using synthetic aperture radar, which can achieve high-precision inversion of typhoon wind speed.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a method for inverting typhoon wind speed using synthetic aperture radar, comprising:

[0007] Obtaining a set of synthetic aperture radar observation data when the synthetic aperture radar inverts the typhoon wind speed, where the set of observation data includes values ​​of multiple observation parameters;

[0008] When typhoon wind speed is inverted based on the weights of each observation parameter and synthetic aperture radar, a set of synthetic aperture radar observation data is used to obtain the inverted value of typhoon wind speed. The weights of each observation parameter are determined as follows:

[0009] A synthetic aperture radar (SAR) objective function for typhoon wind speed inversion based on elastic network regularization is constructed; the weights of each observation parameter are obtained by solving the SAR objective function for typhoon wind speed inversion based on elastic network regularization according to the training data set; the training data set includes multiple groups of observation data of the SAR when the SAR monitors the sample typhoon wind speed, as well as the sample typhoon wind speed corresponding to each group of observation data.

[0010] In one embodiment, the observation parameters are: synthetic aperture radar incident angle, cross-polarization backscatter coefficient, cross-polarization equivalent noise backscatter coefficient, vertical polarization backscatter coefficient and vertical polarization equivalent noise backscatter coefficient.

[0011] In one embodiment, the weights of the observation parameters are obtained by solving the elastic network regularized synthetic aperture radar inversion typhoon wind speed objective function based on the training data set, specifically including:

[0012] For any observation parameter, at the current iteration number, the residual of the observation parameter corresponding to each group of observation data in the training data set at the current iteration number is obtained according to the weight of the observation parameter in the training data set and the previous iteration number;

[0013] Calculate the weight of the observation parameter at the current number of iterations based on the residual of the observation parameter corresponding to each group of observation data in the training data set at the current number of iterations and the soft threshold function;

[0014] Calculating the absolute value of the difference between the weight of the observation parameter at the current iteration number and the weight of the observation parameter at the previous iteration number;

[0015] If the absolute value of the difference between the weight of the observation parameter at the current iteration number and the weight of the observation parameter at the previous iteration number is less than the convergence threshold, the weight of the observation parameter at the current iteration number is determined as the weight of the observation parameter;

[0016] If the absolute value of the difference between the weight of the observation parameter at the current iteration number and the weight of the observation parameter at the previous iteration number is greater than or equal to the convergence threshold, the iteration number is updated and the next iteration is entered.

[0017] In one embodiment, the weight of the observation parameter at the current iteration number is calculated based on the residual of the observation parameter corresponding to each group of observation data in the training data set at the current iteration number and the soft threshold function, specifically including:

[0018] Calculating a first auxiliary variable of the observation parameter at the current iteration number based on the residual of the observation parameter corresponding to each group of observation data in the training data set at the current iteration number;

[0019] Calculate, based on the first auxiliary variable of the observation parameter at the current iteration number, the second auxiliary variable of the observation parameter at the current iteration number and the third auxiliary variable of the observation parameter at the current iteration number;

[0020] The weight of the observation parameter at the current iteration number is calculated based on the second auxiliary variable of the observation parameter at the current iteration number, the third auxiliary variable of the observation parameter at the current iteration number, and the soft threshold function.

[0021] In one embodiment, the residual of the observation parameter corresponding to each group of observation data in the training dataset at the current iteration number is obtained based on the training dataset and the weight of the observation parameter at the previous iteration number, specifically:

[0022] If the current number of iterations is the initial number of iterations, then according to the formula calculate;

[0023] If the current number of iterations is not the initial number of iterations, then according to the formula calculate;

[0024] in, It represents the residual of the jth observation parameter corresponding to the i-th group of observation data in the training data set under the initial number of iterations, Y i represents the sample typhoon wind speed corresponding to the i-th group of observation data in the training data set, β0 represents the intercept of the inversion wind speed model, β k represents the weight of the initial k-th observation parameter, represents the value of the kth observation parameter in the i-th group of observation data in the training data set, It represents the residual of the jth observation parameter corresponding to the i-th group of observation data in the training data set under the n+1th iteration number, It represents the residual of the jth observation parameter corresponding to the i-th group of observation data in the training data set under the n-th iteration number, represents the weight of the jth observation data under the nth iteration number, represents the weight of the j-th observation data under the n-1th iteration number, Represents the value of the jth observation parameter in the i-th group of observations in the training dataset.

[0025] In one embodiment, the weight of the observation parameter at the current iteration number is calculated based on the second auxiliary variable of the observation parameter at the current iteration number, the third auxiliary variable of the observation parameter at the current iteration number, and the soft threshold function, specifically:

[0026] According to the formula Calculate, where β jIndicates the weight of the jth observation parameter under the current number of iterations, SoftThreshold() represents the soft threshold function, γ j The second auxiliary variable representing the observation parameter at the current iteration number, A j represents the third auxiliary variable of the observation parameter at the current iteration number, λ represents the regularization strength, and α represents the elastic network mixing parameter.

[0027] In a second aspect, the present application provides a device for inverting typhoon wind speed using synthetic aperture radar, comprising:

[0028] An acquisition module is used to acquire a set of observation data of the synthetic aperture radar when the synthetic aperture radar inverts the typhoon wind speed, where the set of observation data includes values ​​of multiple observation parameters;

[0029] An inversion module is used to obtain an inverted value of typhoon wind speed based on the weights of each observation parameter and a set of observation data of the synthetic aperture radar when the synthetic aperture radar inverts the typhoon wind speed. The process of determining the weight of each observation parameter is as follows: constructing a synthetic aperture radar inversion typhoon wind speed objective function based on elastic network regularization; solving the synthetic aperture radar inversion typhoon wind speed objective function based on elastic network regularization based on a training data set to obtain the weight of each observation parameter; the training data set includes multiple sets of synthetic aperture radar observation data when the synthetic aperture radar monitors the sample typhoon wind speed and the sample typhoon wind speed corresponding to each set of observation data.

[0030] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described methods for inverting typhoon wind speed using synthetic aperture radar.

[0031] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned methods for inverting typhoon wind speed using synthetic aperture radar.

[0032] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned methods for inverting typhoon wind speed using synthetic aperture radar.

[0033] According to the specific embodiments provided in this application, this application has the following technical effects:

[0034] The present application provides a method, apparatus, equipment, medium and product for inverting typhoon wind speed using synthetic aperture radar. The present application constructs a synthetic aperture radar inverting typhoon wind speed objective function based on elastic network regularization; and solves the synthetic aperture radar inverting typhoon wind speed objective function based on elastic network regularization to obtain the weights of each observation parameter; and then obtains the inverted value of typhoon wind speed based on the weights of each observation parameter, which can improve the inversion accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0036] Figure 1 This is a graph showing the relationship between wind speed, wind direction, and co-polarization synthetic aperture radar backscatter coefficient;

[0037] Figure 2 Flowchart for solving the cost function;

[0038] Figure 3 This is a scatter plot of MS1AHW2 wind speed and SMAP wind speed;

[0039] Figure 4 The root mean square error curves of MS1AHW2 wind speed and SMAP wind speed corresponding to different offsets;

[0040] Figure 5 This is a scatter plot of the corrected MS1AHW2 wind speed and SMAP wind speed;

[0041] Figure 6 This is a scatter plot of the elastic net regularized wind speed and the SMAP wind speed;

[0042] Figure 7 This is a flow chart of a method for inverting typhoon wind speed using synthetic aperture radar in one embodiment of the present application;

[0043] Figure 8 This is a block diagram of a device for inverting typhoon wind speed using synthetic aperture radar in one embodiment of the present application;

[0044] Figure 9 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0046] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0047] Tropical cyclones are classified into six categories based on the maximum average wind speed near their underlying center: tropical depression, tropical storm, severe tropical storm, typhoon, severe typhoon, and super typhoon, as shown in Table 1. The term "typhoon" as used herein refers to a tropical cyclone of severe tropical storm (maximum average wind speed near the underlying center ≥ 24.5 m / s) or higher.

[0048] Table 1 Tropical cyclone levels

[0049] Tropical cyclone category Wind speed level Wind speed (m / s) tropical depression 6～7 10.8～17.1 tropical storm 8～9 17.2～24.4 severe tropical storm 10～11 24.5～32.6 typhoon 12～13 32.7～41.4 strong typhoon 14～15 41.5～50.9 super typhoon ≥16 ≥51.0

[0050] The backscatter coefficient of the co-polarization (vertical polarization mode transmission and vertical polarization mode reception, or horizontal polarization mode transmission and horizontal polarization mode reception) synthetic aperture radar changes cosinely with the increase of wind direction value, as shown in Figure 1 As shown in part (a) of , it increases with the increase of wind speed, such as Figure 1 As shown in part (b) of the figure, the greater the wind speed, the smaller the change in the backscatter coefficient. Especially under typhoon conditions (maximum average wind speed near the bottom center ≥ 24.5 m / s), the co-polarization synthetic aperture radar backscatter coefficient is insensitive to wind speed.

[0051] Recent studies have shown that the backscatter coefficient of cross-polarized SAR (vertically polarized transmission and horizontally polarized reception, or vice versa) exhibits completely different characteristics from the backscatter coefficient of co-polarized SAR. The backscatter coefficient of cross-polarized SAR increases with wind speed but is insensitive to wind direction. Further research has shown that the equivalent noise factor of the SAR and the angle of incidence have a significant impact on wind speed retrieval.

[0052] Based on this, in an exemplary embodiment, the present application provides a method for inverting typhoon wind speed using synthetic aperture radar, such as Figure 7 As shown, specifically including:

[0053] Step 101: Obtain a set of observation data of the synthetic aperture radar when the synthetic aperture radar inverts the typhoon wind speed. The set of observation data includes values ​​of multiple observation parameters.

[0054] Step 102: When the typhoon wind speed is inverted based on the weights of each observation parameter and the synthetic aperture radar, a set of observation data of the synthetic aperture radar is used to obtain an inverted value of the typhoon wind speed; wherein the weights of each observation parameter are determined by: constructing a synthetic aperture radar inversion typhoon wind speed objective function based on elastic network regularization; solving the synthetic aperture radar inversion typhoon wind speed objective function based on elastic network regularization according to a training data set to obtain the weights of each observation parameter; the training data set includes multiple sets of synthetic aperture radar observation data when the synthetic aperture radar monitors the sample typhoon wind speed and the sample typhoon wind speed corresponding to each set of observation data.

[0055] In another exemplary embodiment of the present application, the observation parameters are: synthetic aperture radar incident angle, cross-polarization backscatter coefficient, cross-polarization equivalent noise backscatter coefficient, vertical polarization backscatter coefficient, and vertical polarization equivalent noise backscatter coefficient. This application comprehensively considers the five radar observation parameters of synthetic aperture radar incident angle, cross-polarization backscatter coefficient, cross-polarization equivalent noise backscatter coefficient, vertical polarization backscatter coefficient, and vertical polarization equivalent noise backscatter coefficient, constructs a synthetic aperture radar inversion typhoon wind speed objective function based on elastic network regularization, and provides a calculation implementation method to achieve high-precision inversion of typhoon wind speed by cross-polarization synthetic aperture radar.

[0056] In another exemplary embodiment of the present application, a synthetic aperture radar inversion typhoon wind speed objective function based on elastic network regularization is constructed, and the specific process is as follows:

[0057] Suppose the observation data is X = [X1, X2, X3, X4, X5], which are the synthetic aperture radar incident angle X1, the cross-polarization backscatter coefficient X2, the cross-polarization equivalent noise backscatter coefficient X3, the vertical polarization backscatter coefficient X4, and the vertical polarization equivalent noise backscatter coefficient X5, respectively. The output parameter is the sea surface wind speed (i.e., typhoon wind speed) Y. Assume that the inverted wind speed model is linear:

[0058] Y=β0+β1X1+β2X2+β3X3+β4X4+β5X5 (1)

[0059] Among them, β0 represents the intercept of the model, β j Represents the weight of the j-th observation parameter (j=1,...,5), with an initial value of 0.

[0060] The model objective is to minimize the elastic net regularization objective function: J(β) = loss function + regularization term.

[0061] Let the loss function be:

[0062]

[0063] m is the number of observation groups in the training data set, y i represents the sample typhoon wind speed corresponding to the i-th group of observation data in the training data set, Represents the value of the jth observation parameter in the i-th group of observations in the training dataset.

[0064] The regularization term is a linear combination of L1 regularization and L2 regularization ||β||1, Right now

[0065]

[0066] Where λ represents the regularization strength and α represents the elastic network mixing parameter, which is used to adjust the weights of L1 regularization and L2 regularization (α = 1 for Lasso and α = 0 for Ridge).

[0067] Therefore, the objective function of typhoon wind speed inversion using synthetic aperture radar based on elastic network regularization is:

[0068] J(β)=L(β)+R(β) (4)

[0069] In another exemplary embodiment of the present application, based on the weights of the observation parameters and the inversion of the typhoon wind speed by the synthetic aperture radar, a set of observation data of the synthetic aperture radar is used to obtain an inversion value of the typhoon wind speed. Specifically, the weights of the observation parameters and the set of observation data of the synthetic aperture radar are substituted into formula (1).

[0070] In another exemplary embodiment of the present application, the weights of each observation parameter are obtained by solving the typhoon wind speed inversion objective function of synthetic aperture radar based on elastic network regularization according to the training data set, specifically including:

[0071] For any observation parameter, at the current iteration number, the residual of the observation parameter corresponding to each group of observation data in the training data set at the current iteration number is obtained according to the weight of the observation parameter in the training data set and the previous iteration number;

[0072] The weight of the observation parameter at the current number of iterations is calculated based on the residual of the observation parameter corresponding to each group of observation data in the training data set at the current number of iterations and the soft threshold function.

[0073] Calculate the absolute value of the difference between the weight of the observation parameter at the current iteration number and the weight of the observation parameter at the previous iteration number.

[0074] If the absolute value of the difference between the weight of the observation parameter at the current iteration number and the weight of the observation parameter at the previous iteration number is less than the convergence threshold, the weight of the observation parameter at the current iteration number is determined to be the weight of the observation parameter.

[0075] If the absolute value of the difference between the weight of the observation parameter at the current iteration number and the weight of the observation parameter at the previous iteration number is greater than or equal to the convergence threshold, the iteration number is updated and the next iteration is entered.

[0076] In another exemplary embodiment of the present application, the weight of the observation parameter at the current iteration number is calculated based on the residual of the observation parameter corresponding to each group of observation data in the training data set at the current iteration number and the soft threshold function, specifically including:

[0077] Calculating a first auxiliary variable of the observation parameter at the current iteration number based on the residual of the observation parameter corresponding to each group of observation data in the training data set at the current iteration number;

[0078] Calculate, based on the first auxiliary variable of the observation parameter at the current iteration number, the second auxiliary variable of the observation parameter at the current iteration number and the third auxiliary variable of the observation parameter at the current iteration number;

[0079] The weight of the observation parameter at the current iteration number is calculated based on the second auxiliary variable of the observation parameter at the current iteration number, the third auxiliary variable of the observation parameter at the current iteration number, and the soft threshold function.

[0080] In practical applications, since there is no analytical solution for the elastic network, it is necessary to assume that j All parameters except (j=1,...,5) are fixed, only β j As variables, the iterative method is used to solve β j .

[0081] Let the jth observation parameter β corresponding to the i-th group of observation data in the training data set be j The residual is r i

[0082]

[0083] So the objective function can be simplified to contain only β j Item:

[0084]

[0085] Expanding and combining like terms yields:

[0086]

[0087] β j Taking the derivative and setting it to 0 gives:

[0088]

[0089] Among them, sign() represents the sign function.

[0090] Define auxiliary variables:

[0091] The j-th observation parameter β j The first auxiliary variable of is,

[0092]

[0093] The j-th observation parameter β j The second auxiliary variable is:

[0094]

[0095] The j-th observation parameter β j The third auxiliary variable is:

[0096]

[0097] Then the soft threshold form:

[0098]

[0099] The soft threshold function is defined as:

[0100]

[0101] The initial value of β0 is based on the formula Calculate, Y i represents the sample typhoon wind speed corresponding to the i-th group of observation data in the training data set, m is the number of groups of observation data in the training data set, the maximum number of iterations is N (N = 100), the current number of iterations is n, and the convergence threshold is δ (δ = 0.001),

[0102] if

[0103]

[0104] make

[0105]

[0106] Enter the next iteration until

[0107]

[0108] Output current β j , proceed to the next β j Iterative solution of .

[0109] After obtaining β1, β2, β3, β4 and β5, we can get

[0110]

[0111] At this point, the required solutions β0, β1, β2, β3, β4 and β5 are obtained.

[0112] This application also provides an embodiment to illustrate the effect of the wind speed inversion method provided in the above embodiment, and the specific steps include:

[0113] Step 5.1: Collect the C-band synthetic aperture radar data from the Sentinel-1 satellite and the sea surface wind speed retrieval product data from the L-band radiometer of the SMAP satellite, perform spatiotemporal matching, and obtain a matching dataset.

[0114] Step 5.1.1: Sentinel-1 Synthetic Aperture Radar.

[0115] The Sentinel-1 satellite, equipped with a C-band (5.405 GHz) synthetic aperture radar, operates in a solar-coordinated orbit, providing ocean and land imaging in four imaging modes: SM (80 km swath, 5 m × 5 m resolution), IW (250 km swath, 5 m × 20 m resolution), EW (400 km swath, 25 m × 100 m resolution), and WV (100 km swath, 5 m × 20 m resolution). Sentinel-1A was launched on April 3, 2014. Sentinel-1B was launched on April 25, 2016. The spacecraft experienced an anomaly related to the instrument's electronic power supply, resulting in the inability to provide radar data since December 23, 2021. Consequently, the European Space Agency and the European Commission announced the termination of the Sentinel-1B mission on August 3, 2022. Sentinel-1C, scheduled to launch on December 5, 2024, will succeed Sentinel-1B. The Sentinel-1 satellite can be used to detect sea surface wind fields, with a general average resolution of 1km×1km.

[0116] Step 5.1.2: Soil moisture active and passive detection satellite.

[0117] The Soil Moisture Active Passive (SMAP) satellite operates in a near-polar orbit at an altitude of 685 kilometers, with an inclination of 98 degrees and an ascending node time of 18:00. It provides global coverage in approximately three days and has a precise eight-day revisit period. The satellite consists of an active radar and a passive radiometer, both sharing a common L-band feed horn. Launched on January 31, 2015, the passive radiometer has been operating normally to date, with a resolution of approximately 39 km × 47 km. The active radar failed on July 7, 2015. SMAP's primary mission is to measure soil moisture, as well as sea surface salinity and wind speed. From 18 m / s to 70 m / s, SMAP's microwave radiation increases with wind speed and is virtually unaffected by rainfall. Especially in wind speeds above 25 m / s, the SMAP wind speed deviates from the airborne microwave radiometer (SFMR) by only 0.5 m / s, with a standard deviation of only 3.01 m / s. The data is obtained from www.remss.com, and the sea surface wind product data has been interpolated to a 0.25° and 0.25° resolution latitude and longitude grid.

[0118] Step 5.1.3: Data preprocessing.

[0119] Using spatial distances no greater than 0.25° and time intervals no greater than 3 hours as criteria, we performed spatiotemporal matching. We extracted synthetic aperture radar incident angles, cross-polarization backscatter coefficients, cross-polarization equivalent noise backscatter coefficients, vertical polarization backscatter coefficients, vertical polarization equivalent noise backscatter coefficients, and SMAP satellite wind speeds, resulting in 75,750 matching data pairs. Of these, 5,451 matching pairs were found for wind speeds greater than or equal to 24.5 m / s in the SMAP satellite wind speed product. We randomly selected 3,816 matching pairs as the training dataset, and the remaining 1,635 matching pairs as the test dataset.

[0120] Step 5.2: Solve the cost function.

[0121] Let the maximum number of iterations be N = 100, the convergence threshold be δ = 0.001, the initial value of iteration β0 be the mean of the wind speeds of 3816 typhoons in the training data set, [β1,β2,β3,β4,β5] = [0,0,0,0,0], the regularization strength λ = 0.1, and the elastic network mixing parameter α = 0.5. The cost function solution process is as follows Figure 2 As shown, iterative solution is performed, and the steps of each iteration are:

[0122] In the first step, let β1 be a variable and the other parameters be fixed. The synthetic aperture radar incident angle, cross-polarization backscatter coefficient, cross-polarization equivalent noise backscatter coefficient, vertical polarization backscatter coefficient and vertical polarization equivalent noise backscatter coefficient in the training data set are used as five feature quantities to form a set of observation data X = [X1, X2, X3, X4, X5]. The SMAP wind speed is used as the output parameter y. Substitute it into formula (5) to obtain the parameter residual.

[0123] In the second step, the calculated parameter residuals, training data set, regularization strength and elastic network mixing parameters are substituted into formula (9) to formula (11) to obtain the first auxiliary variable z1, the second auxiliary variable γ1 and the third auxiliary variable A1.

[0124] The third step is to substitute z1, γ1 and A1 into formula (12) and use the soft threshold function of formula (13) to obtain the weight under the number of iterations.

[0125] Step 4: Compare and like Use formula (15) to calculate the new parameter residual and go to the second step; if but is the optimal parameter weight and output.

[0126] Step 6: Compare the results.

[0127] Step 6.1: Currently, the model used by the European Space Agency's Copernicus Ocean Service Center for typhoon wind speed retrieval from the Sentinel-1A synthetic aperture radar is the cross-polarization geophysical model (MS1AHW2), which is expressed as:

[0128]

[0129] Among them, σ vh represents the cross-polarization backscatter coefficient of synthetic aperture radar, Y represents the typhoon wind speed, a z1 ,b z1 ,a z2 ,b z2 are intermediate variables respectively.

[0130]

[0131] The specific coefficient values ​​are shown in Table 2.

[0132] Table 2 Coefficient values ​​of the cross-polarization geophysical model (MS1AHW2)

[0133] coefficient value coefficient value coefficient value <![CDATA[a 0,z1 ]]> 2.13755392e-06 <![CDATA[a 2,z2 ]]> 2.87698338e-08 <![CDATA[c0]]> -0.23257086 <![CDATA[b 0,z1 ]]> 2.47395267 <![CDATA[b 0,z2 ]]> 1.14509104 <![CDATA[c1]]> 12.39717002 <![CDATA[b 1,z1 ]]> -2.85775085e-03 <![CDATA[b 1,z2 ]]> 3.41828829e-02 <![CDATA[c2]]> 0.21667263 <![CDATA[a 0,z2 ]]> 6.54058552e-05 <![CDATA[b 2,z2 ]]> -4.79715441e-04 <![CDATA[c3]]> 12.22862991 <![CDATA[a 1,z2 ]]> -2.43845137e-06

[0134] The incident angle and backscatter coefficient of the synthetic aperture radar in the above test data set are directly substituted into the cross-polarization geophysical model (MS1AHW2), and the MS1AHW2 wind speed V is obtained. MS1AHW2 Compared with the SMAP wind speed scatter plot in the above test data set Figure 3 As shown in the figure, the MS1AHW2 wind speed is clearly systematically overestimated, and the root mean square error between the MS1AHW2 wind speed and the SMAP wind speed in the test dataset is 5.18 m / s.

[0135] Subtract the offset offset∈[0,7] from the above inversion result, the specific formula is Y offset_MS1AHW2 =Y MS1AHW2 -offset, the root mean square error of the result is as follows Figure 4 As shown in Figure 2, when offset = 3.7, the root mean square error between the MS1AHW2 wind speed and the SMAP wind speed is the smallest, which is 3.65 m / s.

[0136] Step 6.2: Substitute the synthetic aperture radar incident angle, cross-polarization backscatter coefficient, cross-polarization equivalent noise backscatter coefficient, vertical polarization backscatter coefficient, vertical polarization equivalent noise backscatter coefficient, and optimal weight in the above test data set into formula (1) to obtain the output result of the elastic network regularization model. The obtained elastic network regularization wind speed is compared with the SMAP wind speed scatter plot in the above test data set, as shown in Figure 6. Figure 6 As shown in the figure, compared with the SMAP satellite wind speed in the test data set, the wind speed error is 3.39m / s.

[0137] After calculation, as shown in Table 3, the root mean square error between the ESA MS1AHW2 wind speed and the SMAP wind speed is 5.18m / s, which shows an obvious systematic overestimation. After bias correction, the scatter plot of the corrected MS1AHW2 wind speed and SMAP wind speed is as follows: Figure 5 As shown in the figure, the root mean square error between the MS1AHW2 wind speed and the SMAP wind speed after correction is reduced to 3.65m / s. After training with elastic network regularization, the wind speed retrieval error is 3.39m / s, which is significantly better than the ESA MS1AHW2 wind speed accuracy.

[0138] Table 3 Comparison of MS1AHW2 wind speed and elastic network regularized wind speed errors

[0139]

[0140] Based on the same inventive concept, embodiments of the present application also provide a device for inverting typhoon wind speed using a synthetic aperture radar (SAR) for implementing the aforementioned method for inverting typhoon wind speed using a synthetic aperture radar. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the device for inverting typhoon wind speed using a synthetic aperture radar provided below can be found in the limitations of the method for inverting typhoon wind speed using a synthetic aperture radar described above and will not be further elaborated here.

[0141] In an exemplary embodiment, a device for inverting typhoon wind speed using synthetic aperture radar is provided, such as Figure 8 Shown, including:

[0142] The acquisition module A1 is used to obtain a set of observation data of the synthetic aperture radar when the synthetic aperture radar inverts the typhoon wind speed. The set of observation data includes values ​​of multiple observation parameters.

[0143] Inversion module A2 is used to obtain an inverted value of typhoon wind speed based on the weights of each observation parameter and a set of observation data of the synthetic aperture radar when the synthetic aperture radar inverts the typhoon wind speed. The process of determining the weight of each observation parameter is as follows: constructing a synthetic aperture radar inversion typhoon wind speed objective function based on elastic network regularization; solving the synthetic aperture radar inversion typhoon wind speed objective function based on elastic network regularization based on a training data set to obtain the weight of each observation parameter; the training data set includes multiple sets of synthetic aperture radar observation data when the synthetic aperture radar monitors the sample typhoon wind speed and the sample typhoon wind speed corresponding to each set of observation data.

[0144] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 9 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store typhoon wind speed data retrieved by synthetic aperture radar. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for retrieving typhoon wind speed by synthetic aperture radar is implemented.

[0145] Those skilled in the art will understand that Figure 9 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application and does not constitute a limitation on the computer device to which the solution of the present application is applied. A specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the above-mentioned method embodiments when executing the computer program.

[0146] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the above-mentioned method embodiments when executed by a processor.

[0147] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the above method embodiments are implemented.

[0148] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0149] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0150] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0151] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0152] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for inverting typhoon wind speed using synthetic aperture radar, characterized in that: The method for inverting typhoon wind speed using synthetic aperture radar includes: Obtaining a set of synthetic aperture radar observation data when the synthetic aperture radar inverts the typhoon wind speed, where the set of observation data includes values ​​of multiple observation parameters; When typhoon wind speed is inverted based on the weights of each observation parameter and synthetic aperture radar, a set of synthetic aperture radar observation data is used to obtain the inverted value of typhoon wind speed. The weights of each observation parameter are determined as follows: A synthetic aperture radar (SAR) objective function for typhoon wind speed inversion based on elastic network regularization is constructed; the weights of each observation parameter are obtained by solving the SAR objective function for typhoon wind speed inversion based on elastic network regularization according to the training data set; the training data set includes multiple groups of observation data of the SAR when the SAR monitors the sample typhoon wind speed, as well as the sample typhoon wind speed corresponding to each group of observation data.

2. The method for inverting typhoon wind speed using synthetic aperture radar according to claim 1, characterized in that: The observation parameters are: synthetic aperture radar incident angle, cross-polarization backscatter coefficient, cross-polarization equivalent noise backscatter coefficient, vertical polarization backscatter coefficient and vertical polarization equivalent noise backscatter coefficient.

3. The method for inverting typhoon wind speed using synthetic aperture radar according to claim 1, characterized in that: According to the training data set, the objective function of synthetic aperture radar inversion of typhoon wind speed based on elastic network regularization is solved to obtain the weights of each observation parameter, including: For any observation parameter, at the current iteration number, the residual of the observation parameter corresponding to each group of observation data in the training data set at the current iteration number is obtained according to the weight of the observation parameter in the training data set and the previous iteration number; Calculate the weight of the observation parameter at the current number of iterations based on the residual of the observation parameter corresponding to each group of observation data in the training data set at the current number of iterations and the soft threshold function; Calculating the absolute value of the difference between the weight of the observation parameter at the current iteration number and the weight of the observation parameter at the previous iteration number; If the absolute value of the difference between the weight of the observation parameter at the current iteration number and the weight of the observation parameter at the previous iteration number is less than the convergence threshold, the weight of the observation parameter at the current iteration number is determined as the weight of the observation parameter; If the absolute value of the difference between the weight of the observation parameter at the current iteration number and the weight of the observation parameter at the previous iteration number is greater than or equal to the convergence threshold, the iteration number is updated and the next iteration is entered.

4. The method for inverting typhoon wind speed using synthetic aperture radar according to claim 3, characterized in that: Based on the residual of the observation parameter corresponding to each group of observation data in the training data set at the current iteration number and the soft threshold function, the weight of the observation parameter at the current iteration number is calculated, specifically including: Calculating a first auxiliary variable of the observation parameter at the current iteration number based on the residual of the observation parameter corresponding to each group of observation data in the training data set at the current iteration number; Calculate, based on the first auxiliary variable of the observation parameter at the current iteration number, the second auxiliary variable of the observation parameter at the current iteration number and the third auxiliary variable of the observation parameter at the current iteration number; The weight of the observation parameter at the current iteration number is calculated based on the second auxiliary variable of the observation parameter at the current iteration number, the third auxiliary variable of the observation parameter at the current iteration number, and the soft threshold function.

5. The method for inverting typhoon wind speed using synthetic aperture radar according to claim 3, characterized in that: The residuals of the observation parameters corresponding to each group of observation data in the training data set at the current iteration number are obtained according to the training data set and the weights of the observation parameters at the previous iteration number, specifically: If the current number of iterations is the initial number of iterations, then according to the formula calculate; If the current number of iterations is not the initial number of iterations, then according to the formula calculate; Among them, r j i It represents the residual of the jth observation parameter corresponding to the i-th group of observation data in the training data set under the initial number of iterations, Y i represents the sample typhoon wind speed corresponding to the i-th group of observation data in the training data set, β0 represents the intercept of the inversion wind speed model, β k represents the weight of the initial k-th observation parameter, represents the value of the kth observation parameter in the i-th group of observation data in the training data set, r j i,n+1 It represents the residual of the jth observation parameter corresponding to the i-th observation data in the training data set at the n+1th iteration, r j i,n It represents the residual of the jth observation parameter corresponding to the i-th group of observation data in the training data set under the n-th iteration number, represents the weight of the jth observation data under the nth iteration number, represents the weight of the j-th observation data under the n-1th iteration number, Represents the value of the jth observation parameter in the i-th group of observations in the training dataset.

6. The method for inverting typhoon wind speed using synthetic aperture radar according to claim 4, characterized in that: Based on the second auxiliary variable of the observation parameter at the current iteration number, the third auxiliary variable of the observation parameter at the current iteration number, and the soft threshold function, the weight of the observation parameter at the current iteration number is calculated, specifically: According to the formula Calculate, where β j Indicates the weight of the jth observation parameter under the current number of iterations, SoftThreshold() represents the soft threshold function, γ j The second auxiliary variable representing the observation parameter at the current iteration number, A j represents the third auxiliary variable of the observation parameter at the current iteration number, λ represents the regularization strength, and α represents the elastic network mixing parameter.

7. A device for inverting typhoon wind speed using synthetic aperture radar, characterized in that: The device for inverting typhoon wind speed using synthetic aperture radar includes: An acquisition module is used to acquire a set of observation data of the synthetic aperture radar when the synthetic aperture radar inverts the typhoon wind speed, where the set of observation data includes values ​​of multiple observation parameters; An inversion module is used to obtain an inverted value of typhoon wind speed based on the weights of each observation parameter and a set of observation data of the synthetic aperture radar when the synthetic aperture radar inverts the typhoon wind speed. The process of determining the weight of each observation parameter is as follows: constructing a synthetic aperture radar inversion typhoon wind speed objective function based on elastic network regularization; solving the synthetic aperture radar inversion typhoon wind speed objective function based on elastic network regularization based on a training data set to obtain the weight of each observation parameter; the training data set includes multiple sets of synthetic aperture radar observation data when the synthetic aperture radar monitors the sample typhoon wind speed and the sample typhoon wind speed corresponding to each set of observation data.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for inverting typhoon wind speed using synthetic aperture radar according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for inverting typhoon wind speed using synthetic aperture radar according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for inverting typhoon wind speed using synthetic aperture radar according to any one of claims 1 to 6 is implemented.

Images