Method and device for detecting significant wave height of marginal sea through spaceborne altimeter

Abstract

The invention discloses a method and a device for detecting marginal sea significant wave height by a spaceborne altimeter, relates to the technical field of ocean remote sensing, and aims to solve the problem of poor marginal sea significant wave height detection precision of the spaceborne altimeter in the prior art. The method comprises the following steps: acquiring sub-satellite point echo waveform data acquired by a spaceborne altimeter; the method comprises the following steps: determining the waveform category of each echo waveform in sub-satellite point echo waveform data collected by a spaceborne altimeter by using an echo waveform classification model constructed based on the sub-satellite point echo waveform data collected by a SWIM spectrometer, and obtaining a first echo waveform classification library; obtaining a first edge sea echo waveform from a first echo waveform classification library, determining a target characteristic parameter of the first edge sea echo waveform, and determining an effective wave height of the first edge sea echo waveform by using an effective wave height inversion model constructed based on sub-satellite point echo waveform data collected by an SWIM spectrometer and wave height data in ERA5; therefore, the edge sea significant wave detection precision is improved.

Description

Technical Field

[0001] The invention relates to the technical field of ocean remote sensing, in particular to a method and a device for detecting effective wave height of marginal sea by a satellite-borne altimeter. Background Art

[0002] Significant wave heigh (SWH) is a key parameter to characterize ocean waves, and is of vital importance to ocean condition monitoring and ocean dynamics research. Satellite radar altimeters are the main tools for measuring sea surface information. Radar altimeters transmit microwave pulse signals to the nadir point, and obtain the echo waveform of the sea surface by tracking and processing the energy reflected by the sea surface. In the open ocean, due to the small change of the reflecting surface, the echo waveform is almost the same, which is an ocean waveform, which can be represented by the Brown-Hayne model. The leading edge of the echo waveform is the direct source of the inverted significant wave height, and the waveform re-tracking method can be used directly for inversion. Most of the current algorithms simplify or improve the original Brown-Hayne model, fit the original waveform, and invert the SWH. Such as MLE4, ICE-2, ALES, adaptive algorithms, etc. In marginal seas (non-open sea areas), such as offshore and ice sheet edges, the ocean waveform is affected by land and sea ice, and the waveform will produce large noise, but it also contains sea surface information. This type of waveform presents a non-Brown model form, and traditional re-tracking methods are usually not possible.

[0003] At present, the processing methods for the marginal sea waveforms detected by the satellite-borne radar altimeter are to first classify the waveforms, pick out the marginal sea waveforms, then perform some processing on the marginal sea waveforms, and then perform re-tracking to invert the effective wave height; among them, the re-tracking methods are mostly based on models, and the actual echo waveforms need to be fitted with a given echo model, and the appropriate parameter estimation method needs to be selected to obtain the waveform parameters. Due to the iterative calculation, the accuracy of the fitting results has been improved, but the calculation speed is relatively slow. For more complex waveform shapes (such as the edge of the ice sheet), the fitting often fails; while the algorithm based on experience has no clear physical meaning, does not require iterative calculation, and the calculation speed is relatively fast, but the accuracy of the results for complex waveforms is relatively low; for example: the SWIM L2 product, which is currently recognized on the market as having a high accuracy in detecting the effective wave height of the echo waveform, uses the re-tracking method to fit the effective wave height of the sea surface echo waveform. Compared with the effective wave height of the echo waveform in the ERA5 reanalysis data set, the root mean square error is about 1.83 / m. It can be seen that the detection accuracy of the SWIML2 product still needs to be improved.

[0004] In view of this, it is urgent to design a more advanced method for satellite-borne altimeter to detect the effective wave height of marginal seas, so as to solve the problem of poor accuracy of effective wave height of marginal sea waveforms detected by satellite-borne radar altimeter in the prior art. Summary of the invention

[0005] The present invention aims to provide a method and device for detecting the effective wave height of the marginal sea by using a satellite-borne altimeter. The method and device utilize a pre-constructed echo waveform classification model and an effective wave height inversion model. The method first determines the waveform classification of sub-satellite point echo waveform data collected by the satellite-borne altimeter based on the echo waveform classification model to obtain the marginal sea echo waveform. The target characteristic parameters of the marginal sea echo waveform are further calculated. Finally, based on the target characteristic parameters, the effective wave height of the marginal sea echo waveform is determined using the effective wave height inversion model. The method thus realizes efficient detection of the effective wave height of the marginal sea by using the satellite-borne altimeter, improves the detection efficiency and detection accuracy of the effective wave height of the marginal sea, and solves the problem of poor accuracy of the satellite-borne altimeter in detecting the effective wave height of the marginal sea in the prior art.

[0006] In order to achieve the above object, the present invention provides the following technical solutions: In a first aspect, the present invention provides a method for detecting significant wave height of a marginal sea using a satellite-borne altimeter, which may include: Obtain sub-satellite point echo waveform data collected by the satellite-borne altimeter; Determine the waveform category of each echo waveform in the sub-satellite point echo waveform data collected by the satellite altimeter by using the echo waveform classification model, and obtain a first echo waveform classification library; the echo waveform classification model is constructed based on the sub-satellite point echo waveform data collected by the SWIM spectrometer; Acquire a first marginal sea echo waveform from the first echo waveform classification library; Determine target characteristic parameters of the first marginal sea echo waveform by using a preset waveform characteristic parameter determination strategy; the target characteristic parameters at least include general parameters, OCOG algorithm parameters and ICE2 algorithm parameters; Based on the target characteristic parameters, the effective wave height of the first marginal sea echo waveform is determined using the trained effective wave height inversion model; the effective wave height inversion model is constructed based on the sub-satellite point echo waveform data collected by the SWIM spectrometer and the wave height data in the ERA5 reanalysis data set.

[0007] Preferably, the echo waveform classification model can be constructed based on the following steps: Obtain sub-satellite point echo waveform data collected by the SWIM spectrometer from the SWIM spectrometer product database; Based on the waveform geometric characteristics of the sub-satellite point echo waveform data collected by the SWIM spectrometer, the sub-satellite point echo waveform data collected by the SWIM spectrometer is classified and processed to obtain a second echo waveform classification library; Using a preset waveform characteristic parameter determination strategy, a plurality of characteristic parameters corresponding to the echo waveforms of each category in the second echo waveform classification library are determined; the plurality of characteristic parameters at least include general parameters, OCOG algorithm parameters and ICE2 algorithm parameters; The plurality of characteristic parameters are used as input, and the echo waveform categories corresponding to the plurality of characteristic parameters are used as output, and model training is performed until the model prediction result meets the preset convergence condition, thereby obtaining the echo waveform classification model.

[0008] Preferably, the neural network model for model training may include an output layer, a hidden layer and an output layer; wherein the hidden layer includes three hidden layers, the first hidden layer includes 32 neurons, the second hidden layer includes 16 neurons, and the third hidden layer includes 8 neurons.

[0009] Preferably, the significant wave height inversion model can be constructed based on the following steps: Acquire a second marginal sea echo waveform from the second echo waveform classification library; According to the second marginal sea echo waveform, target wave height data having the same geographical time and space as the second marginal sea echo waveform is obtained from the ERA5 reanalysis data set; The characteristic parameters of the second marginal sea echo waveform are used as input and the target wave height data is used as output to perform model training until the model prediction result meets the preset convergence condition, thereby obtaining the effective wave height inversion model.

[0010] Preferably, the determining the target characteristic parameter of the first marginal sea echo waveform by using a preset waveform characteristic parameter determination strategy may include using the formula: ; Fit the echo waveform to calculate the ICE2 algorithm parameters; among them, For the ICE2 algorithm model, is the error function, is the amplitude of the waveform, is the influence of thermal noise, L is the slope of the leading edge of the waveform, The midpoint of the leading edge, is the leading edge rise time, is the number of sampling gates corresponding to the waveform data.

[0011] Preferably, the determining the target characteristic parameter of the first marginal sea echo waveform by using a preset waveform characteristic parameter determination strategy may include using the formula: ; The kurtosis of the first edge sea echo waveform is calculated; wherein, is the kurtosis, N is the number of waveform data sampling gates, is the normalized waveform data, is the mean, is the standard deviation.

[0012] Preferably, the determining the target characteristic parameter of the first marginal sea echo waveform by using a preset waveform characteristic parameter determination strategy may include using the formula: ; The height of the first edge sea echo waveform is calculated; wherein, is the height, N is the number of waveform data sampling gates, is the normalized waveform data.

[0013] Preferably, the general parameters may include mean, standard deviation, skewness, kurtosis and pulse peak value; the OCOG algorithm parameters may include height, width, center of gravity and half power point; the ICE2 algorithm parameters may include waveform leading edge slope and leading edge rise time.

[0014] Preferably, the input layer of the echo waveform classification model is the sub-satellite point echo waveform data, and the output layer is the echo waveform with a category identifier; the input layer of the effective wave height inversion model is the characteristic parameters of the marginal sea echo waveform, and the output layer is the wave height.

[0015] In a second aspect, the present invention provides a device for detecting significant wave height of marginal seas using a satellite-borne altimeter, which may include: A waveform data acquisition module, wherein the waveform data acquisition module is used to acquire sub-satellite point echo waveform data collected by a satellite-borne altimeter; A waveform classification module, wherein the waveform classification module is used to determine the waveform category of each echo waveform in the sub-satellite point echo waveform data collected by the satellite altimeter using an echo waveform classification model, and obtain a first echo waveform classification library; the echo waveform classification model is constructed based on the sub-satellite point echo waveform data collected by the SWIM spectrometer; An edge sea waveform acquisition module, the edge sea waveform acquisition module is used to acquire a first edge sea echo waveform from the first echo waveform classification library; A characteristic parameter determination module, the characteristic parameter determination module is used to determine the target characteristic parameters of the first marginal sea echo waveform by using a preset waveform characteristic parameter determination strategy; the target characteristic parameters at least include general parameters, OCOG algorithm parameters and ICE2 algorithm parameters; An effective wave height determination module, the effective wave height determination module is used to determine the effective wave height of the first marginal sea echo waveform based on the target characteristic parameters and using the trained effective wave height inversion model; the effective wave height inversion model is constructed based on the sub-satellite point echo waveform data collected by the SWIM spectrometer and the wave height data in the ERA5 reanalysis data set.

[0016] Compared with the prior art, the present invention provides a method for detecting the effective wave height of the marginal sea by using a satellite-borne altimeter, which obtains the sub-satellite point echo waveform data collected by the satellite-borne altimeter; uses an echo waveform classification model to determine the waveform category of each echo waveform in the sub-satellite point echo waveform data collected by the satellite-borne altimeter, and obtains a first echo waveform classification library; wherein the echo waveform classification model is constructed based on the sub-satellite point echo waveform data collected by a SWIM spectrometer; obtains the first marginal sea echo waveform from the first echo waveform classification library; uses a preset waveform feature parameter determination strategy to determine the target feature parameters of the first marginal sea echo waveform; the target feature parameters at least include general parameters, OCOG algorithm parameters and ICE2 algorithm parameters; finally, based on the target feature parameters, uses the trained effective wave height inversion model to determine the first marginal sea echo waveform. The effective wave height of the marginal sea echo waveform; wherein, the effective wave height inversion model is constructed based on the sub-satellite point echo waveform data collected by the SWIM spectrometer and the wave height data in the ERA5 reanalysis data set; based on this, the echo waveform classification model can be directly used to finely classify the original echo waveform of the satellite-borne radar altimeter, and the effective wave height inversion model can be further directly used to efficiently invert the effective wave height of the marginal sea waveform, without the need to use a given echo model to fit the actual echo waveform and then solve the waveform parameters, thereby avoiding fitting failure; the effective wave height obtained by the method provided by the present invention is compared with the effective wave height in the ERA5 reanalysis data set, and a root mean square error of 0.46 / m is obtained. It can be seen that the method provided by the present invention greatly improves the detection accuracy of the satellite-borne radar altimeter for the effective wave height of the marginal sea. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 This is a schematic diagram showing the comparison between the significant wave height of the marginal sea waveform of the SWIM L2 product and the significant wave height of the ERA5 product; Figure 2 The present invention provides a schematic diagram of the main process of a method for detecting significant wave height of marginal seas using a satellite-borne altimeter; Figure 3 A schematic diagram of waveform categories obtained after fine waveform classification using the echo waveform classification model provided by the present invention; Figure 4 A schematic diagram of the verification effect of a waveform classification model for detecting effective high-mid echoes of marginal sea waves by a satellite-borne altimeter provided by the present invention; Figure 5 A schematic diagram of the comparison results between the significant wave height calculated by the method of detecting the significant wave height of the marginal sea by a satellite-borne altimeter provided by the present invention and the significant wave height of ERA5; Figure 6 The present invention provides a structural schematic diagram of a device for detecting effective wave height of marginal seas using a satellite-borne altimeter. DETAILED DESCRIPTION

[0018] In order to facilitate the clear description of the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second" and the like are used to distinguish the same items or similar items with substantially the same functions and effects. For example, the first threshold and the second threshold are only used to distinguish different thresholds, and do not limit their order of precedence. Those skilled in the art can understand that the words "first", "second" and the like do not limit the quantity and execution order, and the words "first", "second" and the like do not necessarily limit them to be different.

[0019] It should be noted that, in the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0020] In the present invention, "at least one" means one or more, and "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the associated objects in the previous time are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, the combination of a and b, the combination of a and c, the combination of b and c, or the combination of a, b and c, where a, b, c can be single or multiple.

[0021] At present, the sea surface waveforms detected by the spaceborne radar altimeter have not been finely classified, and their processing is often completed by manual screening, which is inefficient and prone to errors. Moreover, when fitting the wave height of the selected waveform, whether it is the re-tracking method or the empirical algorithm method, the fitting accuracy of the sea surface waveform detected by the spaceborne radar altimeter or iterative processing to obtain the effective wave height needs to be improved. The effective wave height detected by the SWIM L2 product, which is currently recognized on the market as having a higher accuracy in detecting sea surface echo waveforms, is compared with the wave height data in the ERA5 reanalysis dataset; please refer to Figure 1 , Figure 1 This is a schematic diagram showing the comparison between the significant wave height detected by the SWIM L2 product and the significant wave height detected by the ERA5 product. Figure 1 It can be concluded without a doubt that the deviation between the effective wave height of the marginal sea waveform of the SWIM L2 product and the effective wave height of ERA5 is 0.36m, the standard deviation is 1.83 / m, the root mean square error is 1.83 / m, and the correlation coefficient is 0.64; it can be seen that the accuracy of the effective wave height detected by the SWIM L2 product still needs to be improved.

[0022] It should be noted that the ERA5 reanalysis data is a global climate reanalysis dataset released by the European Centre for Medium-Range Weather Forecasts (ECMWF), covering the period from 1979 to the present. This comprehensive ERA5 reanalysis dataset contains a series of meteorological elements, including 10-meter wind, waves, precipitation, temperature and pressure. It has been widely used in the study of meteorological and marine environmental factors. The research results show the rationality and credibility of using ERA5 SWH as the basic truth.

[0023] In view of this, the present invention provides a method and device for detecting the effective wave height of the marginal sea by a satellite-borne altimeter. The method and device improve the detection accuracy of the satellite-borne radar altimeter for the effective wave height of the marginal sea by using an echo waveform classification model to perform fine classification on the original echo waveform of the satellite-borne radar altimeter, and using an effective wave height inversion model to efficiently invert the effective wave height of the marginal sea waveform.

[0024] Next, the technical solution of the present invention is described in detail with reference to the accompanying drawings: In the first aspect, the present invention provides a method for detecting significant wave height of marginal seas using a satellite-borne altimeter. Figure 2 , Figure 2 The present invention provides a main flow chart of a method for detecting effective wave height of marginal seas by using a satellite-borne altimeter; the execution subject of the method is a server or a terminal device, such as a detection service platform, a radar altimeter or a SWIM spectrometer.

[0025] exist Figure 2 The methods may include: Step 210: Acquire sub-satellite point echo waveform data collected by the satellite-borne altimeter.

[0026] Step 220: Determine the waveform category of each echo waveform in the sub-satellite point echo waveform data collected by the satellite-borne altimeter using the echo waveform classification model, and obtain a first echo waveform classification library; the echo waveform classification model is constructed based on the sub-satellite point echo waveform data collected by the SWIM spectrometer.

[0027] In step 210 to step 220, the working principle of the satellite-borne (radar) altimeter is to transmit signals vertically to the sea surface and then receive the signals; the sub-satellite point echo waveform data obtained by the present invention is the echo waveform signal data received after the altimeter transmits signals vertically to the sea surface, which is the original data; firstly, the original data collected by the satellite-borne altimeter is refinedly classified using the echo waveform classification model, for example, divided into 9 categories, and the waveform category of each echo waveform in the echo waveform data is determined to obtain a first echo waveform classification library; since the echo waveform classification model is based on the sub-satellite point echo waveform data collected by the SWIM spectrometer, after refined classification and training of the neural network model, a refined classification model is obtained; therefore, compared with the classification method using the prior art, the echo waveform categories in the first echo waveform classification library are more accurate and have higher classification efficiency.

[0028] Step 230: Acquire a first marginal sea echo waveform from the first echo waveform classification library.

[0029] Step 240: Determine target characteristic parameters of the first marginal sea echo waveform using a preset waveform characteristic parameter determination strategy; the target characteristic parameters at least include general parameters, OCOG algorithm parameters, and ICE2 algorithm parameters.

[0030] Step 250: Based on the target characteristic parameters, the effective wave height of the first marginal sea echo waveform is determined using the trained effective wave height inversion model; the effective wave height inversion model is constructed based on the sub-satellite point echo waveform data collected by the SWIM spectrometer and the wave height data in the ERA5 reanalysis data set.

[0031] In step 230 to step 250, since each category of echo waveform in the first echo waveform classification library carries its corresponding identifier, the marginal sea echo waveform can be directly screened and extracted according to the identifier to obtain the first marginal sea echo waveform required for wave height inversion in the present invention; further, it is necessary to determine the strategy according to the preset waveform characteristic parameters to calculate the target characteristic parameters of the first marginal sea echo, such as OCOG algorithm parameters: height A, width Width, center of gravity COG and half power point HP; ICE2 algorithm parameters: waveform leading edge slope L, leading edge rise time And so on; finally, based on the target characteristic parameters, the effective wave height inversion model is used to invert the effective wave height, and the effective wave height for the first marginal sea echo waveform is obtained. Since the effective wave height inversion model is based on the sub-satellite point echo waveform data collected by the SWIM spectrometer and the wave height data in the ERA5 reanalysis data set, the inversion model is obtained after the neural network model is trained; and experimental verification shows that: the effective wave height of the marginal sea detected by the method provided by the present invention is compared with the effective wave height in the ERA5 reanalysis data set, and the root mean square error is only 0.46 / m, which greatly improves the detection accuracy of the satellite-borne radar altimeter for the effective wave height of the marginal sea.

[0032] Based on this, the present invention provides a method for detecting the effective wave height of the marginal sea by a satellite-borne altimeter. The method uses an echo waveform classification model to perform fine classification on the original echo waveform of the satellite-borne radar altimeter, and uses an effective wave height inversion model to efficiently invert the effective wave height of the marginal sea waveform. There is no need to use a given echo model to fit the actual echo waveform and then solve the waveform parameters, thus avoiding fitting failure. Moreover, the root mean square error between the effective wave height in the ERA5 reanalysis data set is only 0.46 / m, which greatly improves the detection accuracy of the satellite-borne radar altimeter for the effective wave height of the marginal sea.

[0033] It should be noted that the BP neural network model has powerful nonlinear mapping capabilities and adaptive feature learning, can efficiently process high-dimensional data, support multi-classification problems, and can fit complex functional relationships in regression tasks, flexibly respond to tasks of different scales, and thus performs well in classification and regression problems. In theory, using the BP neural network to finely classify the sub-satellite echo waveform of the satellite-borne altimeter, and then inverting the effective wave height for the marginal sea waveform can further improve the accuracy; based on this, the echo waveform classification model and the effective wave height inversion model in the present invention are obtained by self-learning or semi-supervised learning of the BP neural network model based on relevant data. Compared with the prior art, the present invention uses the waveform classification model and the effective wave height inversion model to obtain the effective wave height of the marginal sea echo waveform with higher accuracy, which solves the problem of poor accuracy of the effective wave height of the marginal sea detected by the satellite-borne altimeter in the prior art.

[0034] In step 220, preferably, the waveform categories of the first echo waveform classification library can be divided into 9 waveform categories; Figure 3 , Figure 3 The figure is a schematic diagram of waveform categories obtained after fine waveform classification is performed using the echo waveform classification model provided by the present invention.

[0035] exist Figure 3In the figure, category 1 represents ocean waveforms observed in the open ocean; category 2 represents waveforms that are shaped like spikes and are mostly found in sea ice areas; category 3 represents waveforms with multiple spikes of varying heights and are mostly found in land areas; category 4 represents waveforms with a leading edge that is shaped like a spike and a trailing edge that drops gently and are mostly found in sea ice areas; category 5 represents waveforms with a leading edge that is shaped like a spike and a trailing edge that rises first and then drops, and are mostly found in marginal sea areas, where the leading edge is affected by land and sea ice; category 6 represents waveforms with a leading edge that rises and a trailing edge that drops first and then rises, and are mostly found in marginal sea areas, where the trailing edge is affected by land and sea ice; category 7 represents noise waveforms that fluctuate and rise and are mostly found on land or in areas where radars are interfered with; category 8 represents noise waveforms that fluctuate and fall and are mostly found on land or in areas where radars are interfered with; category 9 represents fluctuating noise waveforms and are mostly found on land or in areas where radars are interfered with.

[0036] Preferably, the echo waveform classification model in step 220 can be constructed based on the following steps: (1) Obtain the sub-satellite point echo waveform data collected by the SWIM spectrometer from the SWIM spectrometer product database.

[0037] (2) Based on the waveform geometric characteristics of the sub-satellite point echo waveform data collected by the SWIM spectrometer, the sub-satellite point echo waveform data collected by the SWIM spectrometer is classified and processed to obtain a second echo waveform classification library.

[0038] (3) Using a preset waveform feature parameter determination strategy, determine a plurality of feature parameters corresponding to each category of the echo waveform in the second echo waveform classification library; the plurality of feature parameters at least include general parameters, OCOG algorithm parameters, and ICE2 algorithm parameters.

[0039] (4) Taking multiple feature parameters as input and the echo waveform categories corresponding to the multiple feature parameters as output, the model is trained until the model prediction results meet the preset convergence conditions, thereby obtaining an echo waveform classification model.

[0040] Specifically, the SWIM spectrometer can be a SWIM L1 spectrometer product or a product of other levels. After obtaining the sub-satellite point echo waveform data collected by the SWIM spectrometer, firstly, according to the read SWIM L1 sub-satellite point waveform data , and normalize it using the following formula.

[0041] (1) in, is the normalized waveform data, is the number of sampling gates corresponding to the waveform data, It is the waveform data of SWIM L1 sub-satellite point. Usually, the number of sampling gates of SWIM sub-satellite point waveform is 512.

[0042] Further, according to the waveform geometric characteristics of the sub-satellite point echo waveform data, the sub-satellite point echo waveform data collected by the SWIM spectrometer is classified and processed. The classification method can be based on the empirical method or the empirical method combined with the classification tool method to perform fine classification. In the present invention, the sub-satellite point echo waveform data collected by the SWIM spectrometer is finely classified to obtain the following: Figure 3 The 9 categories of echo waveforms shown are used to establish a second echo waveform classification library; wherein the echo waveforms of the 5th and 6th categories can be used as edge sea echo waveforms.

[0043] Furthermore, a preset waveform characteristic parameter determination strategy is used to determine multiple characteristic parameters corresponding to the echo waveforms of each category in the second echo waveform classification library. The above multiple characteristic parameters can be determined using the following formulas (2) to (11). It should be noted that the method for determining the target characteristic parameters of the first marginal sea echo waveform in step 240 is the same as this method and will not be repeated here.

[0044] Preferably, general parameters may include mean M, standard deviation STD, skewness SKEN, kurtosis KURT and pulse peak PP; OCOG algorithm parameters may include height A, width Width, center of gravity COG and half power point HP; ICE2 algorithm parameters may include waveform leading edge slope L and leading edge rise time .

[0045] Specifically, using a preset waveform characteristic parameter determination strategy to determine the target characteristic parameter of the first marginal sea echo waveform may include using the formula: (2) The kurtosis of the first edge sea echo waveform is calculated; wherein, is the kurtosis, N is the number of waveform data sampling gates, is the normalized waveform data, is the mean and STD is the standard deviation.

[0046] And using the formula: (3) (4) (5) (6) The mean, standard deviation, skewness and pulse peak are calculated respectively; in formula (3) to formula (6), is the mean, is the standard deviation, is the skewness, is the pulse peak value, N is the number of waveform data sampling gates, is the normalized waveform data.

[0047] Preferably, using a preset waveform characteristic parameter determination strategy to determine the target characteristic parameter of the first marginal sea echo waveform may include using the formula: (7) The height of the first edge sea echo waveform is calculated; wherein, is the height, N is the number of waveform data sampling gates, is the normalized waveform data.

[0048] And using the formula: (8) (9) (10) The width, center of gravity and half power point are calculated respectively; in formula (8) to formula (10), Width is the width, COG is the center of gravity, HP is the half power point, N is the number of waveform data sampling gates, is the normalized waveform data.

[0049] Preferably, using a preset waveform characteristic parameter determination strategy to determine the target characteristic parameter of the first marginal sea echo waveform may include using the formula: (11) Fit the echo waveform to calculate the ICE2 algorithm parameters; among them, For the ICE2 algorithm model, is the error function, is the amplitude of the waveform, Thermal noise influence is the slope of the leading edge of the waveform, The midpoint of the leading edge, is the leading edge rise time, is the number of sampling gates corresponding to the waveform data.

[0050] Furthermore, in order to construct a refined classification neural network model, a refined echo waveform classification model is constructed using a neural network, and the input layer output of the echo waveform classification model is a plurality of characteristic parameters corresponding to the echo waveforms of various categories in the second echo waveform classification library.

[0051] Preferably, the neural network model for model training may include an output layer, a hidden layer and an output layer; wherein the hidden layer includes three hidden layers, the first hidden layer includes 32 neurons, the second hidden layer includes 16 neurons, and the third hidden layer includes 8 neurons.

[0052] Preferably, the formula can be used: (12) Determine the activation function of the hidden layer of the refined classification neural network model .

[0053] The output layer of the echo waveform classification model outputs the refined echo category identification, and the activation function It can be expressed by the following formula: (13) Furthermore, the neural network training algorithm adopts the Levenberg-Marquardt training algorithm, referred to as trainlm, which is used to optimize the weights of the neural network to minimize the loss function. To minimize the loss function, this application needs to calculate the gradient and Hessian matrix and update the weights until a certain stopping condition is met.

[0054] (14) (15) (16) (17) In formula (14) to formula (17), is the loss function, For target output, For the actual output, is the sample size, is the gradient vector, is the grid weight vector, The Hessian matrix is ​​the second-order derivative matrix, is the updated weight vector, is the current weight vector, is a small positive number, is the identity matrix, for right The first-order partial derivative of for right The second-order partial derivative of Used to balance the effects of Newton's method and gradient descent. Usually the initial value is set to a constant less than 1. , is the actual input, f is the activation function .

[0055] It should be noted that the Levenberg-Marquardt training algorithm is usually called the "Levenberg-Marquardt algorithm" or "LM algorithm" in Chinese. It is an optimization algorithm for solving nonlinear least squares problems. It is often used to train neural networks, especially for small data sets and networks with fewer parameters, because it usually has faster convergence speed and better convergence accuracy than other optimization algorithms (such as gradient descent).

[0056] More specifically, in order to optimize the performance of the model and improve the quality of model prediction: you can also set the following: 1. The training goal is to keep the mean square error below 0.001; when the mean square error of the network drops below this value, the training will automatically stop to avoid unnecessary calculations.

[0057] 2. Training progress display: after every 1,000 iterations, the network will display the current training results, including mean square error and training progress; this helps monitor the model learning process and ensure that the training is moving towards the expected goal.

[0058] 3. The maximum number of training iterations is set to 30,000, and training will be performed until this upper limit is reached, until the target mean square error is met or other stopping conditions are met.

[0059] 4. The learning rate is 0.1, which controls the amplitude of each parameter update. The appropriate learning rate helps ensure that the model learns stably and converges effectively.

[0060] 5. The maximum number of validation failures allowed during training is 100; if the performance on the validation set does not improve in consecutive training iterations, the count will be increased; when the count exceeds 100, training will be stopped early to avoid overfitting.

[0061] Through the above parameter settings, the network model provided by the present invention is intended to be trained efficiently and accurately to achieve predetermined performance goals.

[0062] Furthermore, according to the established neural network model, 70% of the data in the refined waveform category library is used as training and 30% as testing to obtain a refined echo waveform classification model.

[0063] Specifically, the training set accounts for 70% of the sample data set, and the test set accounts for 30% of the sample data set; the proportions of the first to ninth categories of data in the training set and in the test set are shown in Table 1.

[0064] Table 1 The proportion of data from category 1 to category 9 in the training set and the proportion in the test set

[0065] Based on the data volume ratio set described in Table 1, the neural network model is trained to obtain the echo waveform classification model; and the echo waveform classification model is verified for the degree of waveform classification refinement. The classification effect is as follows: Figure 4 As shown, Figure 4 This is a schematic diagram of the verification effect of a waveform classification model for detecting effective high-mid echoes of marginal sea waves using a satellite-borne altimeter provided by the present invention.

[0066] Depend on Figure 4 The displayed results can be obtained without any doubt: except for category 4, the verification effects of the other categories are all 100%, and the accuracy of category 4 is 84.6%; since the present invention requires classification data of categories 5 and 6, the above classification results do not affect the marginal sea waveform classification effect required by this application. It can be seen that the method provided by the present invention for detecting the effective wave height of the marginal sea by a satellite-borne altimeter adopts an echo waveform classification model, and waveform classification is performed on the sub-satellite point echo waveform data collected by the satellite-borne altimeter, and its classification accuracy can be improved.

[0067] Further, the significant wave height inversion model in step 250 may be constructed based on the following steps: First, the second marginal sea echo waveform is obtained from the second echo waveform classification library, and then the target wave height data with the same geographical time and space as the second marginal sea echo waveform is obtained from the ERA5 reanalysis data set according to the second marginal sea echo waveform; then, the characteristic parameters of the second marginal sea echo waveform are used as input, and the target wave height data is used as output to train the model until the model prediction results meet the preset convergence conditions, and the effective wave height inversion model is obtained. Based on this, the effective wave height inversion model obtained can be applied to the radar altimeter to invert the effective wave height with higher accuracy; at the same time, there is no need to use formula fitting calculation, and the inversion model can directly output the effective wave height data, and its inversion efficiency has also been greatly improved.

[0068] Specifically, the BP neural network model can be set up in the same way as the above-mentioned setting method for how to train the model to obtain the echo waveform classification model, and then the model training can be carried out; the difference is that in the training process of obtaining the effective wave height inversion model, the input layer input of the training model is the characteristic parameters of the second marginal sea echo waveform, and the output layer output is the target wave height data, that is, the effective wave height.

[0069] In order to verify the accuracy of the effective wave height of the marginal sea obtained by detecting the sea surface using the method provided by the present invention, this application compares the effective wave height of the marginal sea obtained by inverting the method provided by the present invention with the wave height number in the ERA5 reanalysis data set, and obtains an effective wave height with higher accuracy than the SWIM L2 product; please refer to Figure 1 and Figure 5 , Figure 5 This is a schematic diagram of the comparison results between the effective wave height calculated by the method for detecting the effective wave height of the marginal sea using a satellite-borne altimeter provided by the present invention and the effective wave height of ERA5.

[0070] from Figure 5 It can be concluded without doubt that the deviation between the effective wave height calculated by the method for detecting the effective wave height of the marginal sea provided by the satellite altimeter and the effective wave height of ERA5 is 0m, the standard deviation is 0.46 / m, the root mean square error is 0.46 / m, and the correlation coefficient is 0.96. Figure 5 and Figure 1 By comparison, it can be found that both the deviation and the root mean square error are better than the detection accuracy of the SWIM L2 product; it can be seen that the method provided by the present invention can effectively improve the detection accuracy of the effective wave height of the marginal sea, and can solve the problem of poor accuracy of the satellite-borne altimeter in detecting the effective wave height of the marginal sea in the prior art.

[0071] In the second aspect, the present invention is a device for detecting effective wave height of marginal sea by a satellite-borne altimeter, please refer to Figure 6 , Figure 6 The present invention provides a structural schematic diagram of a device for detecting effective wave height of marginal seas using a satellite-borne altimeter.

[0072] exist Figure 6 In the embodiment, the device may include: The waveform data acquisition module 610 is used to acquire the sub-satellite point echo waveform data collected by the satellite-borne altimeter.

[0073] The waveform classification module 620 is used to determine the waveform category of each echo waveform in the sub-satellite point echo waveform data collected by the satellite altimeter using the echo waveform classification model, and obtain a first echo waveform classification library; the echo waveform classification model is constructed based on the sub-satellite point echo waveform data collected by the SWIM spectrometer.

[0074] The marginal sea waveform acquisition module 630 is used to acquire a first marginal sea echo waveform from the first echo waveform classification library.

[0075] The characteristic parameter determination module 640 is used to determine the target characteristic parameters of the first marginal sea echo waveform by using a preset waveform characteristic parameter determination strategy; the target characteristic parameters at least include general parameters, OCOG algorithm parameters and ICE2 algorithm parameters.

[0076] The effective wave height determination module 650 is used to determine the effective wave height of the first marginal sea echo waveform based on the target characteristic parameters and using the trained effective wave height inversion model; the effective wave height inversion model is constructed based on the sub-satellite point echo waveform data collected by the SWIM spectrometer and the wave height data in the ERA5 reanalysis data set.

[0077] Based on this, the present invention provides a device for detecting the effective wave height of the marginal sea with a satellite-borne altimeter. First, a waveform data acquisition module 610 is used to acquire the sub-satellite point echo waveform data collected by the satellite-borne altimeter. Then, a waveform classification module 620 uses an echo waveform classification model to determine the waveform category of each echo waveform in the sub-satellite point echo waveform data collected by the satellite-borne altimeter, and obtains a first echo waveform classification library; the echo waveform classification model is constructed based on the sub-satellite point echo waveform data collected by the SWIM spectrometer; then, the marginal sea waveform acquisition module 630 is used to acquire the first marginal sea echo waveform from the first echo waveform classification library; then, based on the characteristic parameter determination module 640, a preset waveform feature is used to determine the waveform category of each echo waveform in the sub-satellite point echo waveform data collected by the satellite-borne altimeter. A parameter determination strategy is provided to determine target characteristic parameters of the first marginal sea echo waveform; the target characteristic parameters include at least general parameters, OCOG algorithm parameters and ICE2 algorithm parameters; finally, an effective wave height determination module 650 is used to determine the effective wave height of the first marginal sea echo waveform based on the target characteristic parameters and the trained effective wave height inversion model; the effective wave height inversion model is constructed based on the sub-satellite point echo waveform data collected by the SWIM spectrometer and the wave height data in the ERA5 reanalysis data set; thereby greatly improving the detection accuracy of the satellite-borne radar altimeter for the effective wave height of the marginal sea, and solving the problem of poor accuracy of the satellite-borne altimeter in detecting the effective wave height of the marginal sea in the prior art.

[0078] Although the present invention is described herein in conjunction with various embodiments, in the process of implementing the claimed invention, those skilled in the art may understand and implement other variations of the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in a claim. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0079] Although the present invention has been described in conjunction with specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present invention. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present invention as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present invention. Obviously, those skilled in the art may make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, the present invention is intended to include such modifications and variations if they fall within the scope of the claims of the present invention and their equivalents.

Claims

1. A method for detecting significant wave height in marginal seas using a satellite-borne altimeter, characterized in that: include: Obtain sub-satellite point echo waveform data collected by the satellite-borne altimeter; Determine the waveform category of each echo waveform in the sub-satellite point echo waveform data collected by the satellite altimeter by using the echo waveform classification model, and obtain a first echo waveform classification library; the echo waveform classification model is constructed based on the sub-satellite point echo waveform data collected by the SWIM spectrometer; Acquire a first marginal sea echo waveform from the first echo waveform classification library; Determine target characteristic parameters of the first marginal sea echo waveform by using a preset waveform characteristic parameter determination strategy; the target characteristic parameters at least include general parameters, OCOG algorithm parameters and ICE2 algorithm parameters; Based on the target characteristic parameters, the effective wave height of the first marginal sea echo waveform is determined using the trained effective wave height inversion model; the effective wave height inversion model is constructed based on the sub-satellite point echo waveform data collected by the SWIM spectrometer and the wave height data in the ERA5 reanalysis data set.

2. The method for detecting significant wave height of marginal seas by a satellite-borne altimeter as claimed in claim 1, characterized in that: The echo waveform classification model is constructed based on the following steps: Obtain sub-satellite point echo waveform data collected by the SWIM spectrometer from the SWIM spectrometer product database; Based on the waveform geometric characteristics of the sub-satellite point echo waveform data collected by the SWIM spectrometer, the sub-satellite point echo waveform data collected by the SWIM spectrometer is classified and processed to obtain a second echo waveform classification library; Using a preset waveform characteristic parameter determination strategy, a plurality of characteristic parameters corresponding to the echo waveforms of each category in the second echo waveform classification library are determined; the plurality of characteristic parameters at least include general parameters, OCOG algorithm parameters and ICE2 algorithm parameters; The plurality of characteristic parameters are used as input, and the echo waveform categories corresponding to the plurality of characteristic parameters are used as output, and model training is performed until the model prediction result meets the preset convergence condition, thereby obtaining the echo waveform classification model.

3. The method for detecting significant wave height of marginal seas by a satellite-borne altimeter as claimed in claim 2, characterized in that: The neural network model for model training includes an output layer, a hidden layer and an output layer; wherein the hidden layer includes three hidden layers, the first hidden layer includes 32 neurons, the second hidden layer includes 16 neurons, and the third hidden layer includes 8 neurons.

4. The method for detecting significant wave height of marginal seas by a satellite-borne altimeter as claimed in claim 2, characterized in that: The significant wave height inversion model is constructed based on the following steps: Acquire a second marginal sea echo waveform from the second echo waveform classification library; According to the second marginal sea echo waveform, target wave height data having the same geographical time and space as the second marginal sea echo waveform is obtained from the ERA5 reanalysis data set; The characteristic parameters of the second marginal sea echo waveform are used as input and the target wave height data is used as output to perform model training until the model prediction result meets the preset convergence condition, thereby obtaining the effective wave height inversion model.

5. The method for detecting significant wave height of marginal seas by a satellite-borne altimeter as claimed in claim 1, characterized in that: The method of using a preset waveform characteristic parameter determination strategy to determine the target characteristic parameter of the first marginal sea echo waveform includes using the formula: ； Fit the echo waveform to calculate the ICE2 algorithm parameters; among them, For the ICE2 algorithm model, is the error function, is the amplitude of the waveform, is the influence of thermal noise, L is the slope of the leading edge of the waveform, The midpoint of the leading edge, is the leading edge rise time, is the number of sampling gates corresponding to the waveform data.

6. The method for detecting significant wave height of marginal seas by using a satellite-borne altimeter as claimed in claim 1, characterized in that: The method of using a preset waveform characteristic parameter determination strategy to determine the target characteristic parameter of the first marginal sea echo waveform includes using the formula: ； The kurtosis of the first edge sea echo waveform is calculated; wherein, is the kurtosis, N is the number of waveform data sampling gates, is the normalized waveform data, is the mean, is the standard deviation.

7. The method for detecting significant wave height of marginal seas by using a satellite-borne altimeter as claimed in claim 1, characterized in that: The method of using a preset waveform characteristic parameter determination strategy to determine the target characteristic parameter of the first marginal sea echo waveform includes using the formula: ； The height of the first edge sea echo waveform is calculated; wherein, is the height, N is the number of waveform data sampling gates, is the normalized waveform data.

8. The method for detecting significant wave height of marginal seas by using a satellite-borne altimeter as claimed in claim 1, characterized in that: The general parameters include mean, standard deviation, skewness, kurtosis and pulse peak value; the OCOG algorithm parameters include height, width, center of gravity and half power point; the ICE2 algorithm parameters include waveform leading edge slope and leading edge rise time.

9. The method for detecting significant wave height of marginal seas by using a satellite-borne altimeter as claimed in claim 1, characterized in that: The input layer of the echo waveform classification model is the sub-satellite point echo waveform data, and the output layer is the echo waveform with a category identifier; the input layer of the effective wave height inversion model is the characteristic parameters of the marginal sea echo waveform, and the output layer is the wave height.

10. A device for detecting significant wave height of marginal seas using a satellite-borne altimeter, characterized in that: include: A waveform data acquisition module, wherein the waveform data acquisition module is used to acquire sub-satellite point echo waveform data collected by a satellite-borne altimeter; A waveform classification module, wherein the waveform classification module is used to determine the waveform category of each echo waveform in the sub-satellite point echo waveform data collected by the satellite altimeter using an echo waveform classification model, and obtain a first echo waveform classification library; the echo waveform classification model is constructed based on the sub-satellite point echo waveform data collected by the SWIM spectrometer; An edge sea waveform acquisition module, the edge sea waveform acquisition module is used to acquire a first edge sea echo waveform from the first echo waveform classification library; A characteristic parameter determination module, the characteristic parameter determination module is used to determine the target characteristic parameters of the first marginal sea echo waveform by using a preset waveform characteristic parameter determination strategy; the target characteristic parameters at least include general parameters, OCOG algorithm parameters and ICE2 algorithm parameters; An effective wave height determination module, the effective wave height determination module is used to determine the effective wave height of the first marginal sea echo waveform based on the target characteristic parameters and using the trained effective wave height inversion model; the effective wave height inversion model is constructed based on the sub-satellite point echo waveform data collected by the SWIM spectrometer and the wave height data in the ERA5 reanalysis data set.

Images