Radar data inversion method, marine meteorological detection method and device

Abstract

The invention provides a radar data inversion method, a maritime meteorological detection method and a maritime meteorological detection device. The inversion method comprises the following steps: acquiring multi-channel meteorological satellite observation data of a target area; inputting the multi-channel meteorological satellite observation data into a pre-trained radar echo inversion model to obtain predicted radar reflectivity data of the target area; the radar echo inversion model is obtained by training a pre-collected training sample set by adopting a generative adversarial learning strategy; the training sample set comprises a plurality of training samples, the training samples are multichannel meteorological satellite observation data at the previous moment of an observation area, and labels of the training samples are radar reflectivity networking observation data at the next moment of the same observation area. According to the inversion method, radar reflectivity data can be accurately inverted based on meteorological satellite observation data, and the defect that maritime meteorological radar data are deficient due to the fact that a radar base station is difficult to construct on the sea is overcome.

Description

Technical Field

[0001] The present invention relates to the technical field of meteorological observation, and in particular to a radar data inversion method, a marine meteorological detection method and a device. Background Art

[0002] In current marine meteorological observations, it is difficult to build radar base stations at sea, resulting in a lack of marine meteorological radar data. To solve this problem, the industry usually uses a method of establishing statistical correlations between meteorological observation elements and satellite observation data, and then inverting radar observation data, but this method is not very accurate. Summary of the invention

[0003] One or more embodiments of this specification describe a radar data inversion method, a marine meteorological detection method and a device, which can effectively solve the above-mentioned problems existing in the prior art.

[0004] In a first aspect, a radar data inversion method is provided, the method comprising: Acquire multi-channel meteorological satellite observation data of the target area; Inputting the multi-channel meteorological satellite observation data into a pre-trained radar echo inversion model to obtain predicted radar reflectivity data of the target area; The radar echo inversion model is trained using a generative adversarial learning strategy on a pre-collected training sample set; the training sample set includes multiple training samples, the training samples are multi-channel meteorological satellite observation data of the observation area at the previous moment, and the labels of the training samples are radar reflectivity network observation data of the same observation area at the next moment.

[0005] As an optional implementation manner of the method described in the first aspect, in the above method, constructing the training sample specifically includes: Collect observation data from multi-channel meteorological satellites and radar networks deployed in the same observation area; Performing equal longitude and latitude projection conversion on the observation data of the multi-channel meteorological satellite, and interpolating the missing values ​​of the converted projection data to obtain the multi-channel meteorological satellite observation data; Piecing together the observation data of the radar network to obtain radar network puzzle data; The multi-channel meteorological satellite observation data and the radar network puzzle data are temporally and spatially matched to obtain the radar reflectivity network observation data of the same observation area at the next moment.

[0006] As an optional implementation manner of the method described in the first aspect, in the above method, training the radar echo inversion model specifically includes: Inputting the training samples into a generator formed by the radar echo inversion model to obtain predicted radar reflectivity data; Determining a loss function based on the predicted radar reflectivity data and the labels of the training samples; Inputting the predicted radar reflectivity data and the real radar reflectivity data into a discriminator to obtain a discriminant result of the discriminator for the input data; Determining a discrimination loss function according to a discrimination result of the discriminator on the input data and a true value label of the input data; the true value label is used to characterize whether the input data is true radar reflectivity data; Based on the generation loss function and the discrimination loss function, the parameters of the radar echo inversion model are updated.

[0007] Specifically, training the radar echo inversion model also includes: For each training sample, determining a first feature image according to radar reflectivity data predicted by the generator for the training sample; Determining a second feature image according to the label of the training sample; Determining a style loss function according to a difference in image style between the first feature image and the second feature image; The parameters of the radar echo inversion model are updated according to the style loss function, the generation loss function and the discrimination loss function.

[0008] More specifically, determining a style loss function according to the difference in image style between the first feature image and the second feature image specifically includes: Using a first Gram matrix to represent the style features of the first feature image; Using a second Gram matrix to represent the style features of the second feature image; According to the first Gram matrix and the second Gram matrix, the style loss function is constructed: ; in, represents the style loss, represents the number of channels of the first feature image and the second feature image, represents the heights of the first feature image and the second feature image, indicates the width of the first feature image and the second feature image, Represents the first Gram matrix Line The element value of the column, represents the second Gram matrix Line The element value of the column.

[0009] In a second aspect, a radar data inversion device is provided, the device comprising: A first data acquisition module is configured to acquire multi-channel meteorological satellite observation data of a target area; The first inversion module is configured to input the multi-channel meteorological satellite observation data into a pre-trained radar echo inversion model to obtain the predicted radar reflectivity data of the target area; the radar echo inversion model is trained using a generative adversarial learning strategy on a pre-collected training sample set; the training sample set includes multiple training samples, the training samples are the multi-channel meteorological satellite observation data of the observation area at the previous moment, and the labels of the training samples are the radar reflectivity network observation data of the same observation area at the next moment.

[0010] In a third aspect, a method for detecting marine weather is provided, the method comprising: Obtain multi-channel meteorological satellite observation data of the current time of the marine area to be detected; According to the multi-channel meteorological satellite observation data of the area to be detected at the current moment, the radar reflectivity data of the area to be detected at the next moment is inverted by using the above radar data inversion method; Meteorological detection is performed based on the radar reflectivity data of the area to be detected at the next moment.

[0011] In a fourth aspect, a marine meteorological detection device is provided, the device comprising: The second data acquisition module is configured to acquire multi-channel meteorological satellite observation data of the marine area to be detected at the current moment; A second inversion module is configured to invert the radar reflectivity data of the area to be detected at the next moment using the above radar data inversion method according to the multi-channel meteorological satellite observation data of the area to be detected at the current moment; The meteorological detection module is configured to perform meteorological detection according to the radar reflectivity data of the area to be detected at the next moment.

[0012] In a fifth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program. When the computer program runs on an electronic device, the electronic device executes the above-mentioned radar data inversion method, or executes the above-mentioned marine meteorological detection method.

[0013] In a sixth aspect, an electronic device is provided, including: at least one memory for storing a program; At least one processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the above-mentioned radar data inversion method, or execute the above-mentioned marine meteorological detection method.

[0014] Beneficial effect: The present invention utilizes the strategy of generative adversarial learning to train the radar echo inversion model, and realizes the inversion of radar reflectivity data based on multi-channel meteorological satellite observation data through the radar echo inversion model, thereby solving the problem of lack of marine meteorological radar data caused by the difficulty in building radar base stations at sea. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 It is a flowchart of a radar data inversion method involved in the embodiments of this specification.

[0017] Figure 2 It is a flow chart of the radar data inversion method involved in the embodiments of this specification in an implementation scenario.

[0018] Figure 3 It is a flowchart of the training sample construction method involved in the embodiments of this specification.

[0019] Figure 4 It is the observation image of the Fengyun-4 satellite involved in the embodiments of this specification.

[0020] Figure 5 It is a schematic diagram of the training process of the generative adversarial model involved in the embodiments of this specification.

[0021] Figure 6 It is a structural schematic diagram of a radar data inversion device involved in the embodiments of this specification.

[0022] Figure 7 It is a flow chart of a marine weather detection method involved in the embodiments of this specification.

[0023] Figure 8 It is a structural schematic diagram of a marine meteorological detection device involved in the embodiments of this specification.

[0024] Fig. 9 It is a structural diagram of an electronic device involved in the embodiments of this specification. DETAILED DESCRIPTION

[0027] First of all, it should be noted that the terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "the" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates otherwise.

[0028] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Therefore, it should be recognized by those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0029] It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this specification. In some other embodiments, the steps included in the method may be more or less than those described in this specification. In addition, a single step described in this specification may be decomposed into multiple steps for description in other embodiments; and multiple steps described in this specification may be combined into a single step for description in other embodiments.

[0030] This specification aims to propose a solution to the problem of the lack of marine weather radar data caused by the difficulty in building radar base stations at sea. One or more embodiments of this specification propose a radar data inversion method, a marine weather detection method and a device, which use the strategy of generative adversarial learning to train a radar echo inversion model, and use the radar echo inversion model to realize the inversion of radar reflectivity data based on multi-channel meteorological satellite observation data, so as to make up for the lack of marine weather radar data.

[0031] The radar data inversion method, marine meteorological detection method and device described in one or more embodiments of this specification will be further described in detail below in conjunction with the drawings and specific embodiments of the specification, but this detailed description does not constitute a limitation on the embodiments of this specification.

[0032] Please refer to Figure 1 , Figure 1 A flow chart of a radar data inversion method is schematically given. The method comprises steps S100 to S102: S100: Acquire multi-channel meteorological satellite observation data of the target area.

[0033] The above-mentioned multi-channel meteorological satellite observation data can be collected from the observation data of a single meteorological satellite, or from the observation data of a satellite network composed of multiple meteorological satellites. The number and location of multi-channel meteorological satellites can be adaptively selected according to specific needs, and this implementation does not impose any restrictions on this.

[0034] S102: Input the multi-channel meteorological satellite observation data into a pre-trained radar echo inversion model to obtain the predicted radar reflectivity data of the target area.

[0035] The above radar echo inversion model is trained by using a generative adversarial learning strategy on a pre-collected training sample set. The training sample set here includes multiple training samples, each of which is a multi-channel meteorological satellite observation data of the observation area at the previous moment, and the label of the training sample is the radar reflectivity network observation data of the same observation area at the next moment.

[0036] Considering that it is difficult to obtain marine weather radar observation data, this embodiment uses ground multi-channel meteorological satellite observation data to train the radar echo inversion model, and then migrates the trained radar echo inversion model to the marine weather observation scene. Therefore, when constructing the above training samples, the following methods can be used: Collect observation data from multi-channel meteorological satellites and radar networks deployed in the same ground observation area.

[0037] The observation data of multi-channel meteorological satellites are transformed into equal longitude and latitude projections, and the missing values ​​of the transformed projection data are interpolated to obtain multi-channel meteorological satellite observation data.

[0038] The observation data of the radar network are jigsawed to obtain radar network jigsaw data.

[0039] The multi-channel meteorological satellite observation data and radar network mosaic data are temporally and spatially matched to obtain the radar reflectivity network observation data of the same observation area at the next moment.

[0040] Based on the above training samples, the above radar echo inversion model can be trained in the following ways, including: The training samples are input into the generator composed of the radar echo inversion model to obtain the predicted radar reflectivity data.

[0041] Based on the predicted radar reflectivity data and the labels of the training samples, a loss function is generated.

[0042] The predicted radar reflectivity data and the actual radar reflectivity data are input into the discriminator to obtain the discriminant result of the discriminator for the input data.

[0043] The discriminant loss function is determined according to the discriminant result of the input data and the true value label of the input data; the true value label here is used to characterize whether the input data is real radar reflectivity data.

[0044] The parameters of the radar echo inversion model are updated based on the generation loss function and the discrimination loss function.

[0045] In the above scheme, a generative adversarial learning strategy is used to train the radar echo inversion model. Therefore, when constructing the loss function, the generation loss and the discrimination loss are considered. In addition, the style transfer loss can be introduced in the training process to optimize the above radar echo inversion model. Style transfer is a deep learning technology that is mainly used in image processing. It can convert the content of one picture into the style of another picture to generate a new image. Style transfer can make the inverted radar echo similar to the true value echo in horizontal structure to a certain extent, and the inversion result is more similar to the real weather system. Based on this, in some embodiments, the style transfer loss function can be constructed to make the model focus on the style features in the training samples. Specifically, the style transfer loss function can be constructed in the following way: For each training sample, a first feature image is determined according to radar reflectivity data predicted by the generator for the training sample.

[0046] According to the label of the training sample, a second feature image is determined.

[0047] A style loss function is determined according to the difference in image style between the first feature image and the second feature image.

[0048] The above-mentioned style loss function is a loss function used to measure the style similarity between the generated image and the specified style image. In this embodiment, the Gram matrix can be used to represent the style features of the image. The calculation method of the Gram matrix is ​​to regard the number of channels of the feature map as a dimension, reshape the feature map into a two-dimensional matrix, and then calculate the product of the transposed matrix of the matrix and itself, and the result is the Gram matrix.

[0049] The Gram matrix is ​​used to construct the above style loss function. The specific method is: Using the first Gram matrix to represent the style features of the first feature image; Using the second Gram matrix to represent the style features of the second feature image; According to the first Gram matrix and the second Gram matrix, the style loss function is constructed: ; in, represents the style loss, represents the number of channels of the first feature image and the second feature image, represents the height of the first feature image and the second feature image, represents the width of the first feature image and the second feature image, Represents the first Gram matrix Line The element value of the column, represents the second Gram matrix Line The element value of the column.

[0050] After the style loss function is introduced, the parameters of the radar echo inversion model can be updated according to the style loss function, the generation loss function and the discrimination loss function. Specifically, the style loss function, the generation loss function and the discrimination loss function can be weighted and summed to obtain a total loss function, and then the total loss function can be used to perform echelon updates on the parameters of the radar echo inversion model to achieve end-to-end training of the above radar echo inversion model.

[0051] The above radar data inversion method is further explained below in combination with specific application scenarios.

[0052] Please refer to Figure 2 , Figure 2 A flow chart of the above radar data inversion method in an implementation scenario is shown.

[0053] In this scenario, this embodiment selects the Fengyun-4 satellite data in Jiangsu Province in the past five years and the radar reflectivity network observation data of the nine existing dual-polarization meteorological radars in Jiangsu Province at the corresponding time, and then performs spatiotemporal matching of the satellite observation data and the radar observation data to construct a training sample set. Figure 3 , for the construction of training samples, we can use Figure 3 This is accomplished by the process shown.

[0054] like Figure 4 As shown in the figure, the Fengyun-4 satellite has a total of 14 observation channels of different wavelengths, of which 2 visible channels have no data at night and cannot be used. Here, the observation data of 2 water vapor window channels and 4 atmospheric transparent window channels (B09 to B14) are selected as training samples.

[0055] Before inputting the above training samples into the radar echo inversion model, the observation data of channels B09 to B14 need to be preprocessed to convert these observation data into data forms that meet the input layer format requirements of the radar echo inversion model. Specifically, the full disk data of brightness temperature in different bands of channels B09 to B14 can be transformed into equal longitude and latitude projections, and the missing values ​​in the projection data can be filled by interpolation processing. For example, the projection data can be uniformly interpolated to 0.04°×0.04° equal longitude and latitude grid points to form the input data of the radar echo inversion model.

[0056] Accordingly, it is also necessary to perform quality control such as deblurring and clutter elimination on the observation data of the above-mentioned 9 dual-polarization meteorological radars before networking across the province to obtain radar network reflectivity data.

[0057] Finally, the networked puzzle reflectivity data of the above-mentioned nine dual-polarization meteorological radars and the pre-processed observation data of the Fengyun-4 satellite are temporally downscaled and matched. Here, the networked puzzle reflectivity data closest in time is found based on the satellite observation data for temporal matching, and the matched networked puzzle reflectivity data is used as the label of the corresponding satellite observation data.

[0058] After obtaining the training sample set, the radar echo inversion model is trained using the training sample set. Figure 5 , Figure 5 The training process of the generative adversarial model is shown. In generative adversarial training, two models are included, one is a generator consisting of a radar echo inversion model, and the other is a discriminator. The generator generates predicted radar reflectivity data based on the input training samples. The predicted radar reflectivity data and the real radar reflectivity data are input into the discriminator together, and the discriminator is used to determine whether the input data is generated radar reflectivity data or real radar reflectivity data. The task of the generator is to generate radar reflectivity data that is as real as possible to deceive the discriminator, and the task of the discriminator is to identify the authenticity of the input data as accurately as possible. The two are in a confrontational situation. Through generative adversarial training, the generator can pay more attention to the feature information related to the real radar reflectivity data during the learning process.

[0059] Please continue to refer to Figure 2 ,exist Figure 2 In this paper, SEResUnet is used as the radar echo inversion model. The channel attention mechanism and residual mechanism of SEResUnet can better adapt to multi-channel business scenarios, have good feature extraction capabilities for multi-channel satellite data, and can better distinguish the features related to the inverted radar echo data between different channels.

[0060] The radar data inversion method provided in this embodiment can accurately and effectively realize radar data inversion, can be widely used in areas where no meteorological radar is installed at sea, and can provide assistance for meteorological guidance and weather emergency warnings in the fields of ocean navigation, fishing, and maritime combat exercises.

[0062] Corresponding to the above radar data inversion method, this embodiment also proposes a radar data inversion device. It should be noted that: Figure 1 The radar data inversion shown can be performed with this device, but is not limited to this device. Figure 6 , the device comprises: The first data acquisition module 601 is configured to acquire multi-channel meteorological satellite observation data of a target area.

[0063] The first inversion module 602 is configured to input the multi-channel meteorological satellite observation data into a pre-trained radar echo inversion model to obtain the predicted radar reflectivity data of the target area.

[0064] For the first inversion module 602, the radar echo inversion model here is trained by using a generative adversarial learning strategy on a pre-collected training sample set. The training sample set includes multiple training samples, the training samples are multi-channel meteorological satellite observation data of the observation area at the previous moment, and the labels of the training samples are radar reflectivity network observation data of the same observation area at the next moment.

[0065] The above radar echo inversion model can be directly trained by the first inversion module 602. It can also be pre-trained and stored in a storage module, and then loaded from the storage module by the first inversion module 602.

[0066] The training process of the radar echo inversion model can be implemented by using the corresponding scheme in the above-mentioned radar data inversion method, which will not be described in detail here.

[0067] For the above-mentioned radar data inversion device, taking a module as an example of a software functional unit, the first data acquisition module 601 may include code running on a computing instance. Among them, the computing instance may include at least one of a physical host (computing device), a virtual machine, and a container. Further, the above-mentioned computing instance may be one or more. For example, the first data acquisition module 601 may include code running on multiple hosts / virtual machines / containers. Multiple hosts / virtual machines / containers for running the code may be distributed in the same region (region) or in different regions. Furthermore, multiple hosts / virtual machines / containers for running the code may be distributed in the same availability zone (AZ) or in different AZs, each AZ including a data center or multiple data centers with similar geographical locations. Among them, usually a region may include multiple AZs.

[0068] Similarly, multiple hosts / virtual machines / containers used to run the code can be distributed in the same virtual private cloud (VPC) or in multiple VPCs. Usually, a VPC is set up in a region. For cross-region communication between two VPCs in the same region and between VPCs in different regions, a communication gateway needs to be set up in each VPC to achieve interconnection between VPCs through the communication gateway.

[0069] As an example of a hardware functional unit, the first data acquisition module 601 includes at least one computing device, such as a server, etc. Alternatively, the first data acquisition module 601 may also be a device implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The PLD may be a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof.

[0070] The multiple computing devices included in the first data acquisition module 601 can be distributed in the same region or in different regions. The multiple computing devices included in the first data acquisition module 601 can be distributed in the same AZ or in different AZs. Similarly, the multiple computing devices included in the first data acquisition module 301 can be distributed in the same VPC or in multiple VPCs. The multiple computing devices can be any combination of computing devices such as servers, ASICs, PLDs, CPLDs, FPGAs, and GALs.

[0071] In other embodiments, the first data acquisition module 601 can be used to execute any step in the above-mentioned radar data inversion method, and the first inversion module 602 can be used to execute any step in the above-mentioned radar data inversion method. The steps that the first data acquisition module 601 and the first inversion module 602 are responsible for implementing can be specified as needed, and the first data acquisition module 601 and the first inversion module 602 respectively implement different steps in the above-mentioned radar data inversion method to realize all functions of the above-mentioned radar data inversion device.

[0072] In this implementation, the radar data inversion device can also be applied to computing devices such as computers and servers, or to a computing device cluster including at least one computing device, to realize the radar data inversion function.

[0073] This embodiment also proposes a method for detecting marine weather. Figure 7 , the method comprises steps S700 to S704: S700: Acquire multi-channel meteorological satellite observation data of the marine area to be detected at the current moment.

[0074] S702: Based on the multi-channel meteorological satellite observation data of the area to be detected at the current moment, the radar reflectivity data of the area to be detected at the next moment is inverted using a radar data inversion method.

[0075] S704: Meteorological detection is performed based on the radar reflectivity data of the area to be detected at the next moment. For example, in the identification and detection of strong convection, the strong echo of radar reflectivity obtained by inversion can be processed into a grayscale co-occurrence matrix. By extracting the morphology and intensity information of the strong echo of radar reflectivity, the longitude and latitude of the center of gravity of each strong echo, the maximum value of the strong echo, the average value of the strong echo, the area of ​​the strong echo, the radius of the strong echo, and the eccentricity of the strong echo are calculated, so as to identify the strong convection area.

[0076] In addition, considering the limitation of fixed input resolution of radar echo inversion model, when the radar echo inversion model trained based on land observation data is directly used to invert radar echoes in a larger range at sea, Gaussian smoothing is required on the edges of multiple spliced ​​inversion areas.

[0077] Corresponding to the above-mentioned offshore weather detection method, this embodiment also proposes an offshore weather detection device, please refer to Figure 8 , the device comprises: The second data acquisition module 801 is configured to acquire multi-channel meteorological satellite observation data of the marine area to be detected at the current moment.

[0078] The second inversion module 802 is configured to invert the radar reflectivity data of the area to be detected at the next moment using a radar data inversion method based on the multi-channel meteorological satellite observation data of the area to be detected at the current moment.

[0079] The weather detection module 803 is configured to perform weather detection according to the radar reflectivity data of the area to be detected at the next moment.

[0080] For the above-mentioned marine meteorological detection device, taking a module as an example of a software functional unit, the second data acquisition module 801 may include code running on a computing instance. Among them, the computing instance may include at least one of a physical host (computing device), a virtual machine, and a container. Further, the above-mentioned computing instance may be one or more. For example, the second data acquisition module 801 may include code running on multiple hosts / virtual machines / containers. The multiple hosts / virtual machines / containers used to run the code may be distributed in the same region (region) or in different regions. Furthermore, the multiple hosts / virtual machines / containers used to run the code may be distributed in the same availability zone (AZ) or in different AZs, each AZ including a data center or multiple data centers with close geographical locations. Among them, usually a region may include multiple AZs.

[0081] Similarly, multiple hosts / virtual machines / containers used to run the code can be distributed in the same virtual private cloud (VPC) or in multiple VPCs. Usually, a VPC is set up in a region. For cross-region communication between two VPCs in the same region and between VPCs in different regions, a communication gateway needs to be set up in each VPC to achieve interconnection between VPCs through the communication gateway.

[0082] As an example of a hardware functional unit, the second data acquisition module 801 includes at least one computing device, such as a server, etc. Alternatively, the second data acquisition module 801 may also be a device implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The PLD may be a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof.

[0083] The multiple computing devices included in the second data acquisition module 801 can be distributed in the same region or in different regions. The multiple computing devices included in the second data acquisition module 801 can be distributed in the same AZ or in different AZs. Similarly, the multiple computing devices included in the second data acquisition module 801 can be distributed in the same VPC or in multiple VPCs. The multiple computing devices can be any combination of computing devices such as servers, ASICs, PLDs, CPLDs, FPGAs, and GALs.

[0084] In other embodiments, the second data acquisition module 801 can be used to execute any step in the above-mentioned offshore meteorological detection method, the second inversion module 802 can be used to execute any step in the above-mentioned offshore meteorological detection method, and the meteorological detection module 803 can be used to execute any step in the above-mentioned offshore meteorological detection method. The steps that the second data acquisition module 801, the second inversion module 802, and the meteorological detection module 803 are responsible for implementing can be specified as needed, and the second data acquisition module 801, the second inversion module 802, and the meteorological detection module 803 respectively implement different steps in the above-mentioned offshore meteorological detection method to realize all the functions of the above-mentioned offshore meteorological detection device.

[0085] In this implementation, the marine weather detection device can also be applied to computing devices such as computers and servers, or to a computing device cluster including at least one computing device, to realize the marine weather detection function.

[0086] In some embodiments, an electronic device is also provided. Fig. 9The electronic device includes: a bus 901, a processor 902, a memory 903 and a communication interface 904. The processor 902, the memory 903 and the communication interface 904 communicate with each other through the bus 901. It should be understood that the present application does not limit the number of processors and memories in the electronic device.

[0087] The bus 901 may be a peripheral component interconnect (PCI) bus, or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig. 9 The use of only one line does not mean that there is only one bus or one type of bus. Bus 901 may include a path for transmitting information between various components of the electronic device (eg, processor 902, memory 903, and communication interface 904).

[0088] The processor 902 may include any one or more processors such as a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0089] The memory 903 may include a volatile memory, such as a random access memory (RAM). The memory 903 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0090] The memory 903 stores executable program codes, and the processor 902 executes the executable program codes to respectively implement the functions of the aforementioned first data acquisition module 601 and the first inversion module 602, that is, to implement the functions of the aforementioned radar data inversion device, thereby implementing the aforementioned radar data inversion method. Alternatively, the processor 902 executes the executable program codes to respectively implement the functions of the aforementioned second data acquisition module 801, the second inversion module 802, and the meteorological detection module 803, that is, to implement the functions of the aforementioned marine meteorological detection device, thereby implementing the aforementioned marine meteorological detection method.

[0091] The communication interface 904 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the electronic device and other devices or a communication network.

[0092] In some embodiments, a computer-readable storage medium is also provided, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned radar data inversion method is implemented, or the above-mentioned marine meteorological detection method is implemented.

[0093] The computer-readable storage medium may be any available medium that can be stored by the electronic device or a data storage device such as a data center containing one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk). The computer-readable storage medium includes instructions that instruct the electronic device to perform the above-mentioned radar data inversion method, or to perform the above-mentioned marine meteorological detection method.

[0094] It is to be understood that the structure illustrated in the embodiments of this specification does not constitute a specific limitation on the system of the embodiments of this specification. In other embodiments of the specification, the above system may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0095] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0096] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0097] It should be noted that the above examples are only specific embodiments of the present invention, and the present invention is obviously not limited to the above examples, and there are many similar variations. All variations directly derived or associated from the contents disclosed by the technicians in this field should fall within the protection scope of the present invention.

Claims

1. A radar data inversion method, characterized in that: include: Acquire multi-channel meteorological satellite observation data of the target area; Inputting the multi-channel meteorological satellite observation data into a pre-trained radar echo inversion model to obtain predicted radar reflectivity data of the target area; The radar echo inversion model is trained using a generative adversarial learning strategy on a pre-collected training sample set; the training sample set includes multiple training samples, the training samples are multi-channel meteorological satellite observation data of the observation area at the previous moment, and the labels of the training samples are radar reflectivity network observation data of the same observation area at the next moment.

2. The method according to claim 1, characterized in that Constructing the training sample specifically includes: Collect observation data from multi-channel meteorological satellites and radar networks deployed in the same observation area; Performing equal longitude and latitude projection conversion on the observation data of the multi-channel meteorological satellite, and interpolating the missing values ​​of the converted projection data to obtain the multi-channel meteorological satellite observation data; Piecing together the observation data of the radar network to obtain radar network puzzle data; The multi-channel meteorological satellite observation data and the radar network mosaic data are temporally and spatially matched to obtain the radar reflectivity network observation data of the same observation area at the next moment.

3. The method according to claim 1, characterized in that Training the radar echo inversion model specifically includes: Inputting the training samples into a generator formed by the radar echo inversion model to obtain predicted radar reflectivity data; Determining a loss function based on the predicted radar reflectivity data and the labels of the training samples; Inputting the predicted radar reflectivity data and the real radar reflectivity data into a discriminator to obtain a discriminant result of the discriminator for the input data; Determining a discrimination loss function according to a discrimination result of the discriminator on the input data and a true value label of the input data; the true value label is used to characterize whether the input data is true radar reflectivity data; Based on the generation loss function and the discrimination loss function, the parameters of the radar echo inversion model are updated.

4. The method according to claim 3, characterized in that Training the radar echo inversion model also includes: For each training sample, determining a first feature image according to radar reflectivity data predicted by the generator for the training sample; Determining a second feature image according to the label of the training sample; Determining a style loss function according to a difference in image style between the first feature image and the second feature image; The parameters of the radar echo inversion model are updated according to the style loss function, the generation loss function and the discrimination loss function.

5. The method according to claim 4, characterized in that Determining a style loss function according to the difference in image style between the first feature image and the second feature image specifically includes: Using a first Gram matrix to represent the style features of the first feature image; Using a second Gram matrix to represent the style features of the second feature image; According to the first Gram matrix and the second Gram matrix, the style loss function is constructed: ； in, represents the style loss, represents the number of channels of the first feature image and the second feature image, represents the heights of the first feature image and the second feature image, indicates the width of the first feature image and the second feature image, Represents the first Gram matrix Line The element value of the column, represents the second Gram matrix Line The element value of the column.

6. A radar data inversion device, characterized in that: include: A first data acquisition module is configured to acquire multi-channel meteorological satellite observation data of a target area; A first inversion module is configured to input the multi-channel meteorological satellite observation data into a pre-trained radar echo inversion model to obtain predicted radar reflectivity data of the target area; The radar echo inversion model is trained using a generative adversarial learning strategy on a pre-collected training sample set; the training sample set includes multiple training samples, the training samples are multi-channel meteorological satellite observation data of the observation area at the previous moment, and the labels of the training samples are radar reflectivity network observation data of the same observation area at the next moment.

7. A method for detecting marine weather, characterized in that: include: Obtain multi-channel meteorological satellite observation data of the current time of the marine area to be detected; According to the multi-channel meteorological satellite observation data of the area to be detected at the current moment, the radar reflectivity data of the area to be detected at the next moment is inverted using the radar data inversion method described in any one of claims 1 to 5; Meteorological detection is performed based on the radar reflectivity data of the area to be detected at the next moment.

8. A marine weather detection device, characterized in that: include: The second data acquisition module is configured to acquire multi-channel meteorological satellite observation data of the marine area to be detected at the current moment; A second inversion module is configured to invert the radar reflectivity data of the area to be detected at a next moment using the radar data inversion method according to any one of claims 1 to 5 based on the multi-channel meteorological satellite observation data of the area to be detected at a current moment; The meteorological detection module is configured to perform meteorological detection according to the radar reflectivity data of the area to be detected at the next moment.

9. A computer-readable storage medium storing a computer program, wherein when the computer program is executed on an electronic device, the electronic device executes the method according to any one of claims 1 to 5, or the method according to claim 7.

10. An electronic device comprising: at least one memory for storing a program; At least one processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the method according to any one of claims 1 to 5, or execute the method according to claim 7.

Images