An airborne platform-based high-altitude ice crystal water content estimation method

Abstract

The application provides an airborne platform-based high-altitude ice crystal water content estimation method, and belongs to the technical field of airborne weather radar detection, and specifically comprises the following steps: constructing echo inversion data of an airborne weather radar based on an airborne platform, abandoning an idealized model for water content estimation based on equidistant data in existing methods, proposing a characteristic quantity capable of characterizing changes in beam width, and strengthening the attention of a classification model to the change relationship between beam width and high-altitude ice crystal water content; proposing a double-layer stratified sampling method, solving the problem of unbalanced sample numbers of high-altitude ice crystals of different concentration levels in actual situations, and reducing the dependence of high-altitude ice crystal water content on temperature from the sample level, realizing robust high-altitude ice crystal water content estimation under an airborne platform, and aiming to improve the accuracy of subsequent airborne weather radar in predicting the danger level of high-altitude ice crystals in the cruising stage, and ensuring the flight safety of an airplane.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of airborne weather radar detection, and in particular to a high-altitude ice crystal water content estimation method based on an airborne platform. BACKGROUND

[0002] High-altitude ice crystal (HIWC) is one of the main meteorological threats when an aircraft flies at high altitudes. When the aircraft passes through a cloud layer containing a large amount of supercooled water, the supercooled water condenses to form ice crystals by impacting the surface of the aircraft. Icing can cause varying degrees of damage to the aircraft, such as causing the aircraft to stall, deteriorating the aircraft's aerodynamic performance, increasing the aircraft's fuel consumption, reducing the engine's performance, and blocking the pitot tube, etc.

[0003] Currently, the sensors available on board for high-altitude ice crystal detection are mainly divided into two categories, namely in-situ detection sensors and weather radars. Among them, as a commonly used airborne weather detection device, the detection performance of high-altitude ice crystals by weather radars has attracted more and more researchers' attention. The principle of high-altitude ice crystal detection by airborne weather radars is based on the Z-IWC relationship. Generally, the higher the ice crystal water content IWC, the larger the Z value, and the greater the corresponding radar echo intensity. Therefore, airborne weather radars can realize indirect estimation of high-altitude ice crystal water content and danger level judgment by obtaining the intensity information of the echo.

[0004] Existing HIWC estimation usually divides the three-dimensional information of the meteorological echo into uniformly spaced grid points, and then estimates the water content of each grid point. Common estimation methods include constructing a reflectivity and water content relationship equation (Z-IWC), etc. However, these studies are based on uniformly divided meteorological grid points for water content prediction, but in actual flight, the volume of the meteorological target detected by the radar will change as the beam coverage range increases. Obviously, as the beam irradiation volume widens with increasing distance, the particle species within the beam coverage range also tends to be more complex, and when the size of the meteorological target is smaller than the beam coverage range, the error estimation of the size of the meteorological target will also affect the accuracy of the ice crystal water content prediction. Therefore, in order to further explore the performance of the airborne weather radar ice crystal water content estimation method, it is necessary to carry out research on the airborne weather radar IWC estimation method under the airborne platform, which takes into account the effect of the increasing beam coverage range. SUMMARY

[0005] Therefore, the present application provides a high-altitude ice crystal water content estimation method based on an airborne platform, which solves the problems in the prior art, proposes a beam width representation operator, combines radar reflectivity factors and other features, realizes a robust high-altitude ice crystal water content estimation method under multiple temperature layers, and effectively improves the perception ability of airborne weather radars for high-altitude ice crystals.

[0006] The high-altitude ice crystal water content estimation method based on an airborne platform provided in the application adopts the following technical scheme:

[0007] A high-altitude ice crystal water content estimation method based on an airborne platform comprises the following steps:

[0008] An ice crystal data set at high altitude is obtained as a meteorological target, and three-dimensional position information of the meteorological target is set;

[0009] An airborne weather radar echo inversion model is established to simulate a real detection scenario of an airborne weather radar, a plurality of initial positions and flight paths of the aircraft are set according to the position of the meteorological target, aircraft avionics information is set, and airborne weather radar parameter information is set;

[0010] Features of the high-altitude ice crystals covered by the airborne weather radar beam during the flight process are extracted to obtain airborne weather radar echo inversion data;

[0011] A high-altitude ice crystal water content estimation feature matrix for the airborne platform is established, and the minimum feature set of the matrix is a radar reflectivity factor Z, a temperature T and a beam width characteristic W, wherein the radar reflectivity factor Z and the temperature T are obtained from the airborne weather radar echo inversion data, and the beam width characteristic W is a volume between adjacent distance gates;

[0012] A label matrix is constructed: threshold values of different danger levels of the high-altitude ice crystals are determined, the ice crystal water content IWC values in the airborne weather radar echo inversion data are quantified according to the specified threshold values to obtain high-altitude ice crystal sample labels, and a data set D is established, which includes the reflectivity factor Z, the temperature T, the beam width characteristic W and the corresponding high-altitude ice crystal sample label Y;

[0013] The data set D is first stratified sampled according to the sample label Y to obtain balanced samples of each type;

[0014] In the extraction process of each type of sample, the temperature T information in the feature set is used for second stratified sampling to obtain a data set F with balanced sample numbers at different temperature layers;

[0015] An identification model is established, the data set F is used as the input of the identification model for training, and a high-altitude ice crystal water content estimation model is obtained;

[0016] The actual obtained airborne platform high-altitude ice crystal data is input into the high-altitude ice crystal water content estimation model for online testing, and the high-altitude ice crystal water content estimation model after testing is used for estimation of the high-altitude ice crystal water content of the airborne platform.

[0017] Optionally, the method for obtaining the echo inversion data of the airborne weather radar comprises: the echo inversion data corresponding to the kth distance gate of the radar beam at the current aircraft position is the average value of the weather data covered in the k-1th to kth distance gate; the scanning in the azimuth and elevation directions and the traversal of different aircraft positions are completed to obtain the echo inversion data of the airborne weather radar.

[0018] Optionally, the beam width representation W = l x h x w, wherein, l is the length corresponding to the distance gate; h is the height of the distance gate, that is, the length in the elevation direction corresponding to the Rth distance gate; and w is the width of the distance gate. n

[0019] Optionally, the setting of the aircraft avionics information comprises setting the flight speed, flight height and heading angle of the aircraft.

[0020] Optionally, the setting of the airborne weather radar parameter information comprises setting the beam width in the elevation and azimuth directions, the scanning range in the elevation and azimuth directions, the maximum detection range and the actual distance corresponding to one distance gate.

[0021] Optionally, the step of determining the threshold values of different danger levels of high-altitude ice crystals comprises: when IWC < A g / m2, Ag / m2 3 < Ag / m2 3 ≤ IWC < B g / m2, IWC 3 ≥ B g / m2, IWC 3 is high concentration, wherein IWC is the ice crystal water content, A represents the first threshold value, and B represents the second threshold value, and B is greater than A.

[0022] Optionally, the step of establishing the data set D comprises:

[0023] The obtained ice crystal water content IWC is quantized according to the given threshold value, and the specific quantization manner is as follows:

[0024]

[0025] The number of samples of the data set is K, and the data set D is specifically represented as:

[0026]

[0027] Y = [y1 y2…y K ] T is the quantized label vector.

[0028] In summary, the present application has the following beneficial technical effects:

[0029] ​The present application fully considers the problem of inaccurate ice crystal water content grade estimation caused by the increase of beam coverage range due to beam broadening in the actual application of airborne weather radar, constructs echo inversion data based on airborne weather radar under the airborne platform, discards the idealized model of existing methods based on equal-interval data for water content estimation, proposes a characteristic quantity that can represent the change of beam width, and strengthens the attention of the classification model to the relationship between beam width and high-altitude ice crystal water content. A double stratified sampling method is proposed to solve the problem of unbalanced sample number of high-altitude ice crystals of different concentration grades in actual situation, and to reduce the dependence of high-altitude ice crystal water content on temperature from the sample level, realize robust high-altitude ice crystal water content estimation under the airborne platform, and improve the accuracy of subsequent airborne weather radar in predicting the danger grade of high-altitude ice crystals in the cruising stage, and ensure the flight safety of the aircraft. BRIEF DESCRIPTION OF DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0031] Figure 1 The flow chart for constructing the high-altitude ice crystal data set and the label matrix in the embodiments of the present application;

[0032] Figure 2 The schematic diagram of the echo inversion process of the airborne weather radar in the embodiments of the present application;

[0033] Figure 3 The principle schematic diagram of the double data feature sampling method in the embodiments of the present application;

[0034] Figure 4 The model training and testing schematic diagram of the ice crystal water content estimation model in the embodiments of the present application. DETAILED DESCRIPTION

[0035] The embodiments of the present application will be described in detail below with reference to the drawings.

[0036] Following, the embodiments of the present application are described through specific examples, and other advantages and effects of the present application can be easily understood by those skilled in the art from the disclosure. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application can also be implemented or applied through other different specific embodiments, and various modifications or changes can be made to the details in the specification based on different views and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0037] It should be noted that various aspects of the embodiments described below are within the scope of the appended claims. It should be apparent that the aspects described herein can be embodied in a wide variety of forms and that any specific structure and / or function described herein is merely illustrative. Based on the teachings herein one skilled in the art should appreciate that an aspect described herein can be implemented independently of any other aspects and that an aspect can be implemented both as any number of software running on a device and / or as an apparatus.

[0038] It should also be noted that the figures provided in the following embodiments are only schematically illustrating the basic concepts of the present application, and only show the components related to the present application in the figures, not drawn according to the number, shape and size of the components in actual implementation, and the shape, number and proportion of each component in actual implementation can be arbitrarily changed, and the layout of the components can be more complex.

[0039] In addition, in the following description, specific details are provided in order to facilitate a thorough understanding of examples. However, one skilled in the art will understand that the aspects described can be practiced without these specific details.

[0040] The embodiment of the present application provides a high-altitude ice crystal water content estimation method based on an airborne platform.

[0041] A high-altitude ice crystal water content estimation method based on an airborne platform, comprising the following steps:

[0042] An ice crystal data set at high altitude is obtained as a meteorological target, and three-dimensional position information of the meteorological target is set.

[0043] The airborne weather radar echo inversion model is established, a real detection scene of the airborne weather radar is simulated, a plurality of initial positions and flight paths of the aircraft are set according to positions of the meteorological targets, aircraft avionics information is set, and airborne weather radar parameter information is set. The aircraft avionics information includes setting the flight speed, flight height and heading angle of the aircraft. The airborne weather radar parameter information includes setting the beam width in the elevation direction and the azimuth direction, the scanning range in the elevation direction and the azimuth direction, the maximum detection range and the actual distance corresponding to one distance gate.

[0044] The characteristics of the high-altitude ice crystals covered by the airborne weather radar beam during the flight process are extracted, and airborne weather radar echo inversion data is obtained.

[0045] An airborne platform-oriented high-altitude ice crystal water content estimation feature matrix is established, and the minimum feature set of the matrix is radar reflectivity factor Z, temperature T and beam width characteristic W. The radar reflectivity factor Z and the temperature T are obtained from the airborne weather radar echo inversion data, and the beam width characteristic W is the volume between adjacent distance gates. The beam width characteristic W = l x h x w, wherein l is the length corresponding to the distance gate; h is the height of the distance gate, that is, the elevation length corresponding to the Rth distance gate; and w is the width of the distance gate. n

[0046] A label matrix is constructed: the threshold values of different risk levels of the high-altitude ice crystals are determined, the ice crystal water content IWC values in the airborne weather radar echo inversion data are quantified according to the specified threshold values to obtain high-altitude ice crystal sample labels, and a data set D is established. The data set D includes the reflectivity factor Z, the temperature T, the beam width characteristic W and the corresponding high-altitude ice crystal sample label Y.

[0047] The steps of determining the threshold values of different risk levels of the high-altitude ice crystals include: when IWC < A g / m 3 , the concentration is low, A g / m 3 ≤ IWC < B g / m 3 , the concentration is medium, and IWC ≥ B g / m 3 , the concentration is high, wherein IWC is the ice crystal water content, A represents the first threshold value, B represents the second threshold value, and B is greater than A.

[0048] The steps of establishing the data set D include:

[0049] The obtained ice crystal water content IWC is quantified according to the given threshold value, and the specific quantification method is as follows:

[0050]

[0051] In one embodiment, A is 1 and B is 3, and the ice crystal water content IWC quantification method is as follows:

[0052] ​

[0053] The data set D is specifically represented as follows: K is the number of samples of the data set.

[0054]

[0055] Y = [y1 y2…yK] is the label vector of the data set D, wherein yk is the label of the kth sample in the data set D. K T Y is the quantized label vector.

[0056] The data set D is first stratified sampled according to the sample label Y to obtain samples of each class with balanced number.

[0057] In the sampling process of each class of samples, the second stratified sampling is performed according to the temperature T information in the feature set to obtain the data set F with balanced number of samples under different temperature layers.

[0058] The recognition model is established, the data set F is taken as the input of the recognition model for training, and the high-altitude ice crystal water content estimation model is obtained.

[0059] The actual obtained high-altitude ice crystal data of the airborne platform is input into the high-altitude ice crystal water content estimation model for online testing, and the high-altitude ice crystal water content estimation model after the testing is used for the estimation of the high-altitude ice crystal water content of the airborne platform.

[0060] The method for obtaining the echo inversion data of the airborne weather radar includes: the echo inversion data corresponding to the kth distance gate of the radar beam at the current aircraft position is the average value of the weather data covered in the k-1th distance gate to the kth distance gate, and the echo inversion data of the airborne weather radar is obtained based on the logic to complete the scanning in the azimuth and pitch directions and the traversal of different aircraft positions.

[0061] In one specific embodiment, a high-altitude ice crystal water content estimation method based on an airborne platform includes:

[0062] Step 1: Obtain a high-altitude ice crystal data set:

[0063] As shown in Figure 1 , a high-altitude ice crystal data set is obtained, which can be obtained by a numerical model or the like, or can be obtained by an airborne in-situ sensor. The data is usually stored as a three-dimensional array, and the resolution of the array is known. According to public information, a high-altitude ice crystal event occurred in the UTC time on May 26, 2015 in Cayenne, French Guiana. A numerical model is used to simulate the event to obtain high-altitude ice crystal gridded data. The data set includes radar reflectivity factor Z, temperature T, water content IWC, and three-direction wind speed information.

[0064] Step 2: Set the echo inversion parameters of the airborne weather radar: ​

[0065] The position of the left lower corner of the three-dimensional weather target is set as (0, 0, 0), and the initial position of the aircraft is set as (-1000, 50000, 8000) to ensure that the aircraft can detect the weather target on the flight track. The aircraft flies at a speed of 400 knots at the specified heading angle, and the position is updated every minute. The echo data is also updated at a rate of 1 / min, and the whole flight process lasts for 10 minutes. It is assumed that the effective detection distance of the airborne weather radar for high-altitude ice crystals is 80 km, and the azimuth and elevation beam widths of the airborne weather radar are both set to 4°. During the scanning process, ±60° azimuth scanning and ±5° elevation scanning are performed, respectively. Considering the richness and diversity of the actual detection scene of the airborne weather radar, multiple flight trajectories can be planned in the simulation test, such as flying at multiple heading angles of ±45°, ±30°, 0°, etc.

[0066] Step three: obtaining the echo inversion data of the airborne weather radar

[0067] As shown in Figure 2 , it is assumed that the current azimuth angle is α and the elevation angle is β. The position coordinates of the grid points covered by the k-1th to kth range gates of the radar beam at the current aircraft position are calculated, and the echo information of the corresponding region in the high-altitude ice crystal data set is extracted, such as ice water content [IWC1, IWC2, …, IWC M ], radar reflectivity factor [Z1, Z2, …, Z M ], etc. Where M represents the number of grid points covered by the kth range gate of the beam to the weather target, and the statistical average of each echo feature corresponding to the coverage area is taken as the echo signal inverted under the kth range gate. Thus, the ice water content radar reflectivity factor In the embodiment, the heading angle of the aircraft is set to -45°, 0° and 45° respectively under the condition that other parameters are the same. Based on the above process, the azimuth and elevation scanning of the three aircraft positions is completed, and the echo inversion data of the airborne weather radar is obtained. Note that the mutual conversion between the weather target coordinate system, the aircraft coordinate system and the beam coordinate system is involved in the calculation process.

[0068] Step four: constructing the high-altitude ice water content estimation feature matrix for the airborne platform

[0069] From the basic principles of radar detection of high-altitude ice crystals, ice crystal formation mechanism, and the existence of beam coverage range in the detection process, the minimum feature set of airborne weather radar high-altitude ice crystal water content identification is constructed, that is, {radar reflectivity factor Z, temperature T, beam width characteristic W}. It should be noted that adding other features to the minimum feature set in actual application should also be within the scope of the present invention. Among them, Z and T can be obtained from the echo inversion data obtained in step three; the beam width characteristic W is a physical quantity that measures the change of the beam width, which helps to identify the relationship between the high-altitude ice crystal water content and the beam width, and improves the estimation ability of the model to the water content. For a conventional directional antenna, W can be represented by the volume between two adjacent range gates R n-1 ,R n , which is approximated by a cuboid, specifically defined as: W = l x h x w; where l is the length corresponding to the range gate; h is the height of the range gate, that is, the length in the elevation direction corresponding to the R n th range gate; w is the width of the range gate, that is, the length in the azimuth direction corresponding to the R n th range gate. Therefore, the minimum feature set for estimating the high-altitude ice crystal water content can be recorded as:

[0070]

[0071] Where K is the total number of sample data sets obtained in step three, and each row in the formula corresponds to the feature vector of a sample, for example, the i-th sample x i corresponds to the feature vector X i = [Z i T i W i ].

[0072] Step five: construct the label matrix

[0073] According to the definition of RTCA for high-altitude ice crystal hazard level, when IWC < 1 g / m 3 , it is low concentration, 1 g / m 3 ≤ IWC < 3 g / m 3 , it is medium concentration, and IWC ≥ 3 g / m 3 , it is high concentration. Considering the difference between radar resolution and ice crystal size and the actual use of weather radar hazard weather indication, the ice crystal water content IWC obtained in step three is quantized according to the threshold value given in the above literature, and the specific quantization method is as follows:

[0074]

[0075] So far, the echo data obtained in step three after step four and step five obtains a new data set D. Assuming that the sample number of the data set is K, then D can be specifically represented as:

[0076]

[0077] Where, Y=[y1 y2…y K ] T is the quantized label vector.

[0078] Step 6: Double Data Feature Sampling Method

[0079] like Figure 3 As shown in the figure, according to the statistical results of the paper "Feasibility Study Weather Radar for Ice Crystal Detection," there is a significant imbalance in the number of ice crystal samples of different concentrations. To reduce the impact of this problem on the performance of the classification model, the data is first stratified and sampled according to the sample label Y. Even for ice crystal samples of the same type, the corresponding radar echo data volume is very large. To avoid the random sampling bias that still exists in the first stratified sampling, a second stratified sampling is actually performed during the extraction of each type of sample based on the temperature T information in the feature set, ensuring that each type of sample covers a feature set containing multiple temperatures. Based on the above process, the quality control of dataset D is completed, and after double stratified sampling, the new dataset F is obtained.

[0080] Step 7: Moisture content estimation model training

[0081] like Figure 4 As shown, a recognition model is constructed, which can be any classification algorithm such as support vector machine, random forest or neural network. The data set obtained in step six is ​​used as the input of the classification algorithm, the hyperparameters of the algorithm are set, and the optimization function is used as the goal. The parameter set of the classification model or the optimization function is obtained through training to obtain the high-altitude ice crystal water content model. Specifically, a 3-class support vector machine SVM is constructed, each classifier uses a radial basis kernel function, and the hyperparameters of the kernel function are determined by the grid search method. The hyperparameter γ used in the embodiment is 1, and the penalty factors of 1 to 3 classes of SVM are set to [0.5, 0.8, 0.9] respectively. The maximization of the interval between categories is used as the optimization goal, and the parameter set of the classification model or the optimization function is obtained through training to obtain the high-altitude ice crystal water content model.

[0082] Step 8: Test the water content of ice crystals at high altitude on the airborne platform

[0083] During the testing phase, the acquired high-altitude ice crystal data of the airborne platform is input into the classification model SVM obtained in step seven for online testing to complete the prediction of the water content of the high-altitude ice crystals of the airborne platform, providing the necessary data input for subsequent airborne weather radar warnings.

[0084] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any changes or replacements within the technical scope disclosed by the present application can be easily conceived by the person skilled in the art, and should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for estimating ice crystal water content at high altitudes based on an airborne platform, characterized in that, The method comprises the following steps: Obtain a high-altitude ice crystal dataset as a meteorological target, and set three-dimensional position information of the meteorological target; Establish a model for inversion of airborne weather radar echoes, simulate a real detection scenario of the airborne weather radar, set multiple initial positions and flight paths of the aircraft according to the position of the meteorological target, set aircraft avionics information, and set parameter information of the airborne weather radar; Extract features of the high-altitude ice crystals covered by the airborne weather radar beam during flight, and obtain inversion data of the airborne weather radar echoes; Establish a feature matrix for estimation of the high-altitude ice crystal water content for the airborne platform, the minimum feature set of the matrix being radar reflectivity factor Z, temperature T and beam width characteristic W, wherein the radar reflectivity factor Z and the temperature T are obtained from the inversion data of the airborne weather radar echoes, and the beam width characteristic W is the volume between adjacent range gates; Construct a label matrix: determine threshold values of different danger levels of the high-altitude ice crystals, quantize the ice crystal water content IWC values in the inversion data of the airborne weather radar echoes according to the specified threshold values to obtain sample labels of the high-altitude ice crystals, and establish a dataset D, the dataset D comprising the radar reflectivity factor Z, the temperature T, the beam width characteristic W and the corresponding sample labels Y of the high-altitude ice crystals; First stratified sampling is performed on the dataset D according to the sample labels Y to obtain balanced samples of each type; Second stratified sampling is performed on each type of sample according to the temperature T information in the feature set during the sampling process to obtain a dataset F with balanced sample numbers at different temperature layers; An identification model is established, the dataset F is taken as an input of the identification model for training, and a high-altitude ice crystal water content estimation model is obtained; Actual airborne platform high-altitude ice crystal data is input into the high-altitude ice crystal water content estimation model for online testing, and the high-altitude ice crystal water content estimation model after the testing is used for estimation of the high-altitude ice crystal water content of the airborne platform.

2. The airborne platform-based estimation of ice crystal content aloft method of claim 1, wherein, The method for obtaining the inversion data of the airborne weather radar echoes comprises: the inversion data of the kth range gate of the radar beam at the current aircraft position is the average value of the meteorological data covered in the (k-1) th to kth range gates, the scanning in the azimuth and elevation directions is completed, and the traversal of different aircraft positions is completed, thereby obtaining the inversion data of the airborne weather radar echoes.

3. The airborne platform-based estimation of ice crystal content aloft method of claim 1, wherein, Beam width characterization quantity W = l × h × w, where l is the length corresponding to the range gate; h is the height of the range gate, that is, the R n The pitch length corresponding to a range gate; w is the width of the range gate.

4. The airborne platform-based estimation of ice crystal content aloft method of claim 1, wherein, The setting of the aircraft avionics information comprises setting the flight speed, flight height and heading angle of the aircraft.

5. The airborne platform-based estimation of ice crystal content aloft method of claim 1, wherein, The setting of the parameter information of the airborne weather radar comprises setting the beam widths in the elevation and azimuth directions, the scanning ranges in the elevation and azimuth directions, the maximum detection range and the actual distance corresponding to one range gate.

6. The airborne platform-based estimation of ice crystal content aloft method of claim 1, wherein, The step of determining the threshold values of different danger levels of high altitude ice crystals includes: when IWC < Ag / m 3 is low concentration, Ag / m 3 ≤ IWC < Bg / m 3 is medium concentration, IWC ≥ Bg / m 3 is high concentration, wherein IWC is ice crystal water content, wherein A represents a first threshold value, B represents a second threshold value, and B is greater than A.

7. The airborne platform-based estimation of ice crystal content aloft method of claim 6, wherein, The step of establishing the dataset D comprises: The obtained ice crystal water content IWC is quantized according to the given threshold value, and the specific quantization method is as follows: The number of samples of the dataset is K, and the dataset D is specifically represented as: where Y = [yl y2… y K ] T is the quantized label vector.

Images