X-band dual-polarization radar attenuation correction method based on artificial intelligence

Abstract

The embodiment of the invention provides an X-band dual-polarization radar attenuation correction method based on artificial intelligence. The method is applied to the field of X-band dual-polarization radar attenuation correction. The method comprises the steps of performing space-time matching on existing observation data of an X-band dual-polarization radar and existing observation data of an S / C-band radar in each region to generate a space-time matching data set of each region; according to the space-time matching data set of each region, training an attenuation correction model of the corresponding region, and generating an attenuation correction model of each region; and performing quality control on the observation data of the X-band dual-polarization radar to be subjected to attenuation correction, and inputting the observation data into the attenuation correction model of the corresponding region to obtain the horizontal reflectivity and the differential reflectivity of the X-band dual-polarization radar after attenuation correction. Therefore, the signal attenuation of the horizontal reflectivity and the differential reflectivity of the X-band dual-polarization radar can be effectively corrected, the deviation between the X-band dual-polarization radar and the observation value of the adjacent S-band radar can be reduced, the hardware resource overhead can be reduced, and the method can be efficiently applied nationwide.

Description

Technical Field

[0001] The present invention relates to the field of X-band dual-polarization radar attenuation correction, and in particular to an X-band dual-polarization radar attenuation correction method based on artificial intelligence. Background Art

[0002] Rain area attenuation seriously affects the meteorological interpretation of radar reflectivity factor. Therefore, in order to ensure the accuracy of radar detection, it is necessary to correct the error caused by rain area attenuation. General attenuation correction methods include DP method and X-band dual polarization radar echo intensity attenuation correction method combined with CINRAD / SA radar. However, DP method has the following disadvantages: the corrected attenuation coefficient is easily affected by the uneven spatial and temporal distribution of raindrop spectrum, the change of real ambient temperature, and the unclean filtering of backscattering phase in differential propagation phase. Moreover, KDP is easily affected by noise and has large errors in non-uniform propagation paths. The X-band dual polarization radar echo intensity attenuation correction method combined with CINRAD / SA radar needs to rely on the echo data of CINRAD / SA radar, and the spatial and temporal matching algorithm of X-band dual polarization radar and CINRAD / SA radar causes great overhead on hardware resources in real-time business, which makes it difficult to be applied in real-time business. Summary of the invention

[0003] The present invention provides an artificial intelligence-based X-band dual-polarization radar attenuation correction method, device, equipment and storage medium.

[0004] According to a first aspect of the present disclosure, an X-band dual-polarization radar attenuation correction method based on artificial intelligence is provided. The method comprises:

[0005] The existing observation data of X-band dual-polarization radar and S / C-band radar in each region are temporally and spatially matched to generate a temporal and spatial matching data set for each region.

[0006] The attenuation correction model of the corresponding region is trained according to the spatiotemporal matching data set of each region to generate the attenuation correction model of each region;

[0007] The observation data of the X-band dual polarization radar that needs attenuation correction is quality controlled and input into the attenuation correction model of the area where the X-band dual polarization radar that needs attenuation correction is located to obtain the horizontal reflectivity and differential reflectivity of the X-band dual polarization radar after attenuation correction.

[0008] In some implementable manners of the first aspect, time-space matching is performed on existing observation data of an X-band dual-polarization radar and existing observation data of an S / C-band radar in each region, respectively, including:

[0009] Quality control is performed on the existing observation data of the X-band dual-polarization radar and the existing observation data of the S / C-band radar in each area, the existing observation data of the S / C-band radar after quality control is rasterized and interpolated into three-dimensional data, and the existing observation data of the X-band dual-polarization radar is matched with the three-dimensional data in time and space.

[0010] In some implementations of the first aspect, the quality control includes:

[0011] Non-precipitation echo identification, initial phase correction, and phase defolding of the differential propagation phase.

[0012] In some implementations of the first aspect, the spatiotemporal matching of the dataset includes:

[0013] Differential propagation phase, horizontal reflectivity and differential reflectivity after quality control for X-band dual polarization radar, and horizontal reflectivity and differential reflectivity for S / C-band radar.

[0014] In some implementations of the first aspect, training an attenuation correction model for a corresponding region according to a spatiotemporal matching dataset of each region includes:

[0015] The differential propagation phase, horizontal reflectivity and differential reflectivity of the X-band dual-polarization radar after quality control in the time-space matching dataset of each region are used as training samples, and the horizontal reflectivity and differential reflectivity of the S / C-band radar in the time-space matching dataset of each region are used as annotations;

[0016] According to the training samples and annotations of each region, the attenuation correction model of each region is trained using the fitting function.

[0017] In some implementations of the first aspect, the attenuation correction model of each region is trained using a fitting function according to the training samples and annotations of each region, including:

[0018] The fitting function is used to fit the relationship between the differential propagation phase and horizontal reflectivity of the X-band dual polarization radar after quality control in the training sample set of each region and the horizontal reflectivity of the S / C-band radar in the corresponding regional annotation, as well as the relationship between the differential propagation phase and differential reflectivity of the X-band dual polarization radar after quality control in the training sample set of each region and the differential reflectivity of the S / C-band radar in the corresponding regional annotation, to generate the attenuation correction model of each region.

[0019] In some implementable embodiments of the first aspect, fitting the relationship between the differential propagation phase and the horizontal reflectivity of the X-band dual polarization radar after quality control in the training sample set of each region and the horizontal reflectivity of the S / C-band radar in the corresponding regional annotation using a fitting function includes:

[0020] In the process of fitting the horizontal reflectivity of the X-band dual-polarization radar in each region, the fitting function is used to fit the relationship between the differential propagation phase and horizontal reflectivity of the X-band dual-polarization radar after quality control in the training sample set of each region and the horizontal reflectivity of the S / C-band radar in the corresponding regional annotation;

[0021] Compare the horizontal reflectivity of the S / C band radar in each area obtained by fitting with the horizontal reflectivity of the S / C band radar in the corresponding area annotation, and use the loss function to calculate the horizontal reflectivity difference value of the corresponding area;

[0022] According to the horizontal reflectivity difference value of the corresponding area, the fitting function parameters of the corresponding area are adjusted and updated by using a gradient descent algorithm;

[0023] The fitting process of the X-band dual-polarization radar horizontal reflectivity of each region is repeated until the loss function of each region converges, and the attenuation correction model of each region when the loss function converges is used as the trained attenuation correction model corresponding to each region.

[0024] In some implementable embodiments of the first aspect, fitting the relationship between the differential propagation phase and the differential reflectivity of the X-band dual polarization radar after quality control in the training sample set of each region and the differential reflectivity of the S / C-band radar in the corresponding regional annotation using a fitting function includes:

[0025] In the process of fitting the differential reflectivity of the X-band dual-polarization radar in each region, the fitting function is used to fit the relationship between the differential propagation phase and differential reflectivity of the X-band dual-polarization radar after quality control in the training sample set of each region and the differential reflectivity of the S / C-band radar in the corresponding regional annotation;

[0026] Compare the differential reflectivity of the S / C band radar in each area obtained by fitting with the differential reflectivity of the S / C band radar in the corresponding area annotation, and use the loss function to calculate the differential reflectivity difference value of the corresponding area;

[0027] According to the differential reflectivity gap value of the corresponding area, the fitting function parameters of the corresponding area are adjusted and updated by using a gradient descent algorithm;

[0028] The fitting process of the X-band dual-polarization radar differential reflectivity of each region is repeated until the loss function of each region converges, and the attenuation correction model of each region when the loss function converges is used as the trained attenuation correction model corresponding to each region.

[0029] In some implementable embodiments of the first aspect, the horizontal reflectivity of the X-band dual polarization radar after attenuation correction is the horizontal reflectivity of the S / C-band radar output by the attenuation correction model of the area where the X-band dual polarization radar that needs attenuation correction is located, and the differential reflectivity is the differential reflectivity of the S / C-band radar output by the attenuation correction model of the area where the X-band dual polarization radar that needs attenuation correction is located.

[0030] According to a second aspect of the present disclosure, an X-band dual-polarization radar attenuation correction device based on artificial intelligence is provided. The device comprises:

[0031] The module for generating time-space matching data sets for each region is used to perform time-space matching on the existing observation data of the X-band dual-polarization radar and the existing observation data of the S / C-band radar in each region to generate the time-space matching data sets for each region;

[0032] The attenuation correction model generation module of each region is used to train the attenuation correction model of the corresponding region according to the spatiotemporal matching data set of each region to generate the attenuation correction model of each region;

[0033] The attenuation correction module is used to perform quality control on the observation data of the X-band dual polarization radar that needs attenuation correction and input it into the attenuation correction model of the area where the X-band dual polarization radar that needs attenuation correction is located, so as to obtain the horizontal reflectivity and differential reflectivity of the X-band dual polarization radar after attenuation correction.

[0034] According to a third aspect of the present disclosure, an electronic device is provided. The electronic device includes: at least one processor; and a memory connected to the at least one processor in communication; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the method described above.

[0035] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, where the computer instructions are used to cause a computer to execute the method as described above.

[0036] In the present disclosure, the existing observation data of the X-band dual polarization radar and the existing observation data of the S / C-band radar in each region are respectively matched in time and space to generate a time and space matching data set for each region; the attenuation correction model of the corresponding region is trained according to the time and space matching data set of each region to generate an attenuation correction model for each region; the observation data of the X-band dual polarization radar that needs to be corrected for attenuation is quality controlled and input into the attenuation correction model of the region where the X-band dual polarization radar that needs to be corrected for attenuation is located, and the horizontal reflectivity and differential reflectivity of the X-band dual polarization radar after attenuation correction are obtained. In this way, the signal attenuation of the horizontal reflectivity and differential reflectivity of the X-band dual polarization radar can be effectively corrected, the deviation from the observation value of the adjacent S-band radar can be reduced, the hardware resource overhead can be reduced, and the application can be efficiently carried out nationwide.

[0037] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, among which:

[0039] Figure 1 A flowchart of an X-band dual-polarization radar attenuation correction method based on artificial intelligence provided by an embodiment of the present disclosure is shown;

[0040] Figure 2 A structural diagram of an X-band dual-polarization radar attenuation correction device based on artificial intelligence provided by an embodiment of the present disclosure is shown;

[0041] Figure 3 A block diagram of an exemplary electronic device capable of implementing an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0043] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0044] In response to the problems in the background technology, the embodiments of the present disclosure provide an X-band dual polarization radar attenuation correction method and device based on artificial intelligence. Specifically, the existing observation data of the X-band dual polarization radar and the existing observation data of the S / C-band radar in each region are temporally and spatially matched to generate a temporal and spatial matching data set for each region; the attenuation correction model of the corresponding region is trained according to the temporal and spatial matching data set of each region to generate an attenuation correction model for each region; the observation data of the X-band dual polarization radar that needs to be attenuated is quality controlled and input into the attenuation correction model of the region where the X-band dual polarization radar that needs to be attenuated is located, and the horizontal reflectivity and differential reflectivity of the X-band dual polarization radar after attenuation correction are obtained. In this way, the signal attenuation of the horizontal reflectivity and differential reflectivity of the X-band dual polarization radar can be effectively corrected, the deviation from the adjacent S-band radar observation value can be reduced, the hardware resource overhead can be reduced, and the application can be efficiently carried out nationwide.

[0045] In conjunction with the accompanying drawings, the artificial intelligence-based X-band dual-polarization radar attenuation correction method and device provided by the embodiments of the present disclosure are described in detail through specific embodiments.

[0046] Figure 1 A flowchart of an X-band dual-polarization radar attenuation correction method based on artificial intelligence provided by an embodiment of the present disclosure is shown. The method 100 includes the following steps:

[0047] S110 , performing time-space matching on existing observation data of the X-band dual-polarization radar and existing observation data of the S / C-band radar in each region respectively, to generate a time-space matching data set for each region.

[0048] In some embodiments, time-space matching is performed on existing observation data of the X-band dual-polarization radar and existing observation data of the S / C-band radar in each region, respectively, including:

[0049] Quality control is performed on the existing observation data of the X-band dual-polarization radar and the existing observation data of the S / C-band radar in each area respectively, the existing observation data of the S / C-band radar after quality control is rasterized and interpolated into three-dimensional data, and the existing observation data of the X-band dual-polarization radar is spatially and temporally matched with the three-dimensional data;

[0050] Furthermore, the three-dimensional data is 1km×1km×0.5km three-dimensional data;

[0051] The observation time limit for matching the same spatial body shall not exceed 5 seconds, and the spatial distance difference shall not exceed 2 kilometers.

[0052] In some embodiments, the spatiotemporal matching is performed offline, effectively saving resources consumed in processing S / C band radar.

[0053] In some embodiments, the S / C band radar refers to an S / C band radar adjacent to an X-band dual polarization radar in the same area; the observation data of the S / C band radar adjacent to the X-band dual polarization radar in the same area is used as a reference value for the observation data of the X-band dual polarization radar in the area.

[0054] In some embodiments, quality control includes:

[0055] Non-precipitation echo identification, initial phase correction, and phase defolding of the differential propagation phase.

[0056] In some embodiments, the spatiotemporal matching dataset includes:

[0057] Differential propagation phase, horizontal reflectivity and differential reflectivity after quality control for X-band dual polarization radar, and horizontal reflectivity and differential reflectivity for S / C-band radar.

[0058] S120, training the attenuation correction model of the corresponding region according to the spatiotemporal matching data set of each region, and generating the attenuation correction model of each region.

[0059] In some embodiments, training the attenuation correction model of the corresponding region according to the spatiotemporal matching dataset of each region includes:

[0060] The differential propagation phase, horizontal reflectivity and differential reflectivity of the X-band dual-polarization radar after quality control in the time-space matching data set of each region are used as training samples, and the horizontal reflectivity and differential reflectivity of the S / C-band radar after time-space matching in the time-space matching data set of each region are used as annotations;

[0061] According to the training samples and annotations of each region, the attenuation correction model of each region is trained using the fitting function.

[0062] In some embodiments, according to the training samples and annotations of each region, the attenuation correction model of each region is trained using a fitting function, including:

[0063] The fitting function is used to fit the relationship between the differential propagation phase and horizontal reflectivity of the X-band dual polarization radar after quality control in the training sample set of each region and the horizontal reflectivity of the S / C-band radar in the corresponding regional annotation, as well as the relationship between the differential propagation phase and differential reflectivity of the X-band dual polarization radar after quality control in the training sample set of each region and the differential reflectivity of the S / C-band radar in the corresponding regional annotation, to generate the attenuation correction model of each region.

[0064] In some embodiments, fitting the relationship between the differential propagation phase and horizontal reflectivity of the X-band dual polarization radar after quality control in the training sample set of each region and the horizontal reflectivity of the S / C-band radar in the corresponding region annotation using a fitting function includes:

[0065] In the process of fitting the horizontal reflectivity of the X-band dual-polarization radar in each region, the fitting function is used to fit the relationship between the differential propagation phase and horizontal reflectivity of the X-band dual-polarization radar after quality control in the training sample set of each region and the horizontal reflectivity of the S / C-band radar in the corresponding regional annotation;

[0066] Compare the horizontal reflectivity of the S / C band radar in each area obtained by fitting with the horizontal reflectivity of the S / C band radar in the corresponding area annotation, and use the loss function to calculate the horizontal reflectivity difference value of the corresponding area;

[0067] According to the horizontal reflectivity difference value of the corresponding area, the fitting function parameters of the corresponding area are adjusted and updated by using a gradient descent algorithm;

[0068] The fitting process of the X-band dual-polarization radar horizontal reflectivity of each region is repeated until the loss function of each region converges, and the attenuation correction model of each region when the loss function converges is used as the trained attenuation correction model corresponding to each region.

[0069] In some embodiments, fitting the relationship between the differential propagation phase and the differential reflectivity of the X-band dual-polarization radar after quality control in the training sample set of each region and the differential reflectivity of the S / C-band radar in the corresponding region annotation using a fitting function includes:

[0070] In the process of fitting the differential reflectivity of the X-band dual-polarization radar in each region, the fitting function is used to fit the relationship between the differential propagation phase and differential reflectivity of the X-band dual-polarization radar after quality control in the training sample set of each region and the differential reflectivity of the S / C-band radar in the corresponding regional annotation;

[0071] Compare the differential reflectivity of the S / C band radar in each area obtained by fitting with the differential reflectivity of the S / C band radar in the corresponding area annotation, and use the loss function to calculate the differential reflectivity difference value of the corresponding area;

[0072] According to the differential reflectivity gap value of the corresponding area, the fitting function parameters of the corresponding area are adjusted and updated by using a gradient descent algorithm;

[0073] The fitting process of the X-band dual-polarization radar differential reflectivity of each region is repeated until the loss function of each region converges, and the attenuation correction model of each region when the loss function converges is used as the trained attenuation correction model corresponding to each region.

[0074] In some embodiments, a polynomial regression function is used as a fitting function. Compared with a linear fitting function, the attenuation correction result of the X-band dual polarization radar is closer to the observation data of the S / C-band radar adjacent to the X-band dual polarization radar after time and space matching.

[0075] S130, performing quality control on the observation data of the X-band dual polarization radar that needs attenuation correction and inputting the data into an attenuation correction model of the area where the X-band dual polarization radar that needs attenuation correction is located, and obtaining the horizontal reflectivity and differential reflectivity of the X-band dual polarization radar after attenuation correction.

[0076] In some embodiments, the observed data includes differential propagation phase, horizontal reflectivity, and differential reflectivity.

[0077] In some embodiments, the horizontal reflectivity of the X-band dual polarization radar after attenuation correction is the horizontal reflectivity of the S / C-band radar obtained by fitting the output of the attenuation correction model of the area where the X-band dual polarization radar that needs attenuation correction is located, and the differential reflectivity is the differential reflectivity of the S / C-band radar obtained by fitting the output of the attenuation correction model of the area where the X-band dual polarization radar that needs attenuation correction is located.

[0078] In some embodiments, due to the uneven spatiotemporal distribution of raindrop spectra in different regions and different precipitation attenuation coefficients, corresponding attenuation correction models are established for different regions. X-band dual-polarization radars located in different regions select the attenuation correction model corresponding to the corresponding region for attenuation correction, which is both efficient and can reduce the correction deviation, and can be applied nationwide.

[0079] According to the embodiments of the present disclosure, the existing observation data of the X-band dual polarization radar and the existing observation data of the S / C-band radar in each region are respectively matched in time and space to generate a time and space matching data set for each region; the attenuation correction model of the corresponding region is trained according to the time and space matching data set of each region to generate an attenuation correction model for each region; the observation data of the X-band dual polarization radar that needs to be corrected for attenuation is quality controlled and input into the attenuation correction model of the region where the X-band dual polarization radar that needs to be corrected for attenuation is located, and the horizontal reflectivity and differential reflectivity of the X-band dual polarization radar after attenuation correction are obtained. In this way, the signal attenuation of the horizontal reflectivity and differential reflectivity of the X-band dual polarization radar can be effectively corrected, the deviation from the adjacent S-band radar observation value can be reduced, the hardware resource overhead can be reduced, and the application can be efficiently carried out nationwide.

[0080] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present disclosure is not limited by the order of the actions described, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0081] The above is an introduction to the method embodiment. The following is a further explanation of the scheme disclosed in the present invention through an apparatus embodiment.

[0082] Figure 2 The structure diagram of an X-band dual-polarization radar attenuation correction device based on artificial intelligence provided by an embodiment of the present disclosure is shown. The device 200 includes:

[0083] The module 210 for generating the spatiotemporal matching data set for each region is used to perform spatiotemporal matching on the existing observation data of the X-band dual-polarization radar and the existing observation data of the S / C-band radar in each region to generate a spatiotemporal matching data set for each region.

[0084] In some embodiments, module 210 is specifically configured to:

[0085] The existing observation data of X-band dual-polarization radar and S / C-band radar in each region are temporally and spatially matched, including:

[0086] Quality control is performed on the existing observation data of the X-band dual-polarization radar and the existing observation data of the S / C-band radar in each area, the existing observation data of the S / C-band radar after quality control is rasterized and interpolated into three-dimensional data, and the existing observation data of the X-band dual-polarization radar is matched with the three-dimensional data in time and space.

[0087] In some embodiments, module 210 is further configured to:

[0088] Quality control, including:

[0089] Non-precipitation echo identification, initial phase correction, and phase defolding of the differential propagation phase.

[0090] In some embodiments, module 210 is further configured to:

[0091] Spatiotemporal matching datasets, including:

[0092] Differential propagation phase, horizontal reflectivity and differential reflectivity after quality control for X-band dual polarization radar, and horizontal reflectivity and differential reflectivity for S / C-band radar.

[0093] The attenuation correction model generation module 220 for each region is used to train the attenuation correction model of the corresponding region according to the spatiotemporal matching data set of each region, and generate the attenuation correction model of each region.

[0094] In some embodiments, module 220 is specifically configured to:

[0095] The attenuation correction model of the corresponding area is trained based on the spatiotemporal matching dataset of each area, including:

[0096] The differential propagation phase, horizontal reflectivity and differential reflectivity of the X-band dual-polarization radar after quality control in the time-space matching data set of each region are used as training samples, and the horizontal reflectivity and differential reflectivity of the S / C-band radar after time-space matching in the time-space matching data set of each region are used as annotations;

[0097] According to the training samples and annotations of each region, the attenuation correction model of each region is trained using the fitting function.

[0098] In some embodiments, module 220 is further configured to:

[0099] According to the training samples and annotations of each region, the attenuation correction model of each region is trained using the fitting function, including:

[0100] The fitting function is used to fit the relationship between the differential propagation phase and horizontal reflectivity of the X-band dual polarization radar after quality control in the training sample set of each region and the horizontal reflectivity of the S / C-band radar in the corresponding regional annotation, as well as the relationship between the differential propagation phase and differential reflectivity of the X-band dual polarization radar after quality control in the training sample set of each region and the differential reflectivity of the S / C-band radar in the corresponding regional annotation, to generate the attenuation correction model of each region.

[0101] In some embodiments, module 220 is further configured to:

[0102] The fitting function is used to fit the relationship between the differential propagation phase and horizontal reflectivity of the X-band dual-polarization radar after quality control in the training sample set of each region and the horizontal reflectivity of the S / C-band radar in the corresponding regional annotation, including:

[0103] In the process of fitting the horizontal reflectivity of the X-band dual-polarization radar in each region, the fitting function is used to fit the relationship between the differential propagation phase and horizontal reflectivity of the X-band dual-polarization radar after quality control in the training sample set of each region and the horizontal reflectivity of the S / C-band radar in the corresponding regional annotation;

[0104] Compare the horizontal reflectivity of the S / C band radar in each area obtained by fitting with the horizontal reflectivity of the S / C band radar in the corresponding area annotation, and use the loss function to calculate the horizontal reflectivity difference value of the corresponding area;

[0105] According to the horizontal reflectivity difference value of the corresponding area, the fitting function parameters of the corresponding area are adjusted and updated by using a gradient descent algorithm;

[0106] The fitting process of the X-band dual-polarization radar horizontal reflectivity of each region is repeated until the loss function of each region converges, and the attenuation correction model of each region when the loss function converges is used as the trained attenuation correction model corresponding to each region.

[0107] In some embodiments, module 220 is further configured to:

[0108] The relationship between the differential propagation phase and the differential reflectivity of the X-band dual polarization radar after quality control in the training sample set of each region and the differential reflectivity of the S / C-band radar in the corresponding region annotation is fitted by using a fitting function, including:

[0109] In the process of fitting the differential reflectivity of the X-band dual-polarization radar in each region, the fitting function is used to fit the relationship between the differential propagation phase and differential reflectivity of the X-band dual-polarization radar after quality control in the training sample set of each region and the differential reflectivity of the S / C-band radar in the corresponding regional annotation;

[0110] Compare the differential reflectivity of the S / C band radar in each area obtained by fitting with the differential reflectivity of the S / C band radar in the corresponding area annotation, and use the loss function to calculate the differential reflectivity difference value of the corresponding area;

[0111] According to the differential reflectivity gap value of the corresponding area, the fitting function parameters of the corresponding area are adjusted and updated by using a gradient descent algorithm;

[0112] The fitting process of the X-band dual-polarization radar differential reflectivity of each region is repeated until the loss function of each region converges, and the attenuation correction model of each region when the loss function converges is used as the trained attenuation correction model corresponding to each region.

[0113] The attenuation correction module 230 is used to perform quality control on the observation data of the X-band dual polarization radar that needs attenuation correction and input it into the attenuation correction model of the area where the X-band dual polarization radar that needs attenuation correction is located, so as to obtain the horizontal reflectivity and differential reflectivity of the X-band dual polarization radar after attenuation correction.

[0114] In some embodiments, module 230 is specifically configured to:

[0115] The horizontal reflectivity of the X-band dual polarization radar after attenuation correction is the horizontal reflectivity of the S / C-band radar output by the attenuation correction model in the area where the X-band dual polarization radar that needs attenuation correction is located, and the differential reflectivity is the differential reflectivity of the S / C-band radar output by the attenuation correction model in the area where the X-band dual polarization radar that needs attenuation correction is located.

[0116] Understandably, Figure 2 Each module / unit in the detection device 200 shown has the function of implementing each step in the detection method 100 provided in the embodiment of the present disclosure and can achieve its corresponding technical effect. For the sake of brevity, it will not be repeated here.

[0117] Figure 3 A block diagram of an exemplary electronic device capable of implementing an embodiment of the present disclosure is shown. The electronic device 300 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device 300 may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0118] like Figure 3 As shown, the electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An I / O interface 305 is also connected to the bus 304.

[0119] A number of components in the electronic device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0120] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as method 100. For example, in some embodiments, the method 100 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the method 100 described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to perform the method 100 in any other appropriate manner (e.g., by means of firmware).

[0121] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0122] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0123] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0124] It should be noted that the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute method 100 and achieve the corresponding technical effect achieved by executing the method in the embodiment of the present disclosure. For the sake of concise description, they are not repeated here.

[0125] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0126] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0127] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0128] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0129] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An X-band dual-polarization radar attenuation correction method based on artificial intelligence, characterized in that: include: The existing observation data of X-band dual-polarization radar and S / C-band radar in each region are temporally and spatially matched to generate a temporal and spatial matching data set for each region. The attenuation correction model of the corresponding region is trained according to the spatiotemporal matching data set of each region to generate the attenuation correction model of each region; The observation data of the X-band dual polarization radar that needs attenuation correction is quality controlled and input into the attenuation correction model of the area where the X-band dual polarization radar that needs attenuation correction is located to obtain the horizontal reflectivity and differential reflectivity of the X-band dual polarization radar after attenuation correction.

2. The method according to claim 1, characterized in that The performing time-space matching on the existing observation data of the X-band dual-polarization radar and the existing observation data of the S / C-band radar in each region respectively includes: Quality control is performed on the existing observation data of the X-band dual-polarization radar and the existing observation data of the S / C-band radar in each area, the existing observation data of the S / C-band radar after quality control is rasterized and interpolated into three-dimensional data, and the existing observation data of the X-band dual-polarization radar is matched with the three-dimensional data in time and space.

3. The method according to claim 2, characterized in that The quality control includes: Non-precipitation echo identification, initial phase correction, and phase defolding of the differential propagation phase.

4. The method according to claim 3, characterized in that: The spatiotemporal matching dataset includes: Differential propagation phase, horizontal reflectivity and differential reflectivity after quality control for X-band dual polarization radar, and horizontal reflectivity and differential reflectivity for S / C-band radar.

5. The method according to claim 4, characterized in that The attenuation correction model of the corresponding area is trained according to the spatiotemporal matching data set of each area, including: The differential propagation phase, horizontal reflectivity and differential reflectivity of the X-band dual-polarization radar after quality control in the time-space matching dataset of each region are used as training samples, and the horizontal reflectivity and differential reflectivity of the S / C-band radar in the time-space matching dataset of each region are used as annotations; According to the training samples and annotations of each region, the attenuation correction model of each region is trained using the fitting function.

6. The method according to claim 5, characterized in that The attenuation correction model of each region is trained using a fitting function according to the training samples and annotations of each region, including: The fitting function is used to fit the relationship between the differential propagation phase and horizontal reflectivity of the X-band dual polarization radar after quality control in the training sample set of each region and the horizontal reflectivity of the S / C-band radar in the corresponding regional annotation, as well as the relationship between the differential propagation phase and differential reflectivity of the X-band dual polarization radar after quality control in the training sample set of each region and the differential reflectivity of the S / C-band radar in the corresponding regional annotation, to generate the attenuation correction model of each region.

7. The method according to claim 6, characterized in that The method of using a fitting function to fit the relationship between the differential propagation phase and horizontal reflectivity of the X-band dual polarization radar after quality control in the training sample set of each region and the horizontal reflectivity of the S / C-band radar in the corresponding region annotation includes: In the process of fitting the horizontal reflectivity of the X-band dual-polarization radar in each region, the fitting function is used to fit the relationship between the differential propagation phase and horizontal reflectivity of the X-band dual-polarization radar after quality control in the training sample set of each region and the horizontal reflectivity of the S / C-band radar in the corresponding regional annotation; Compare the horizontal reflectivity of the S / C band radar in each area obtained by fitting with the horizontal reflectivity of the S / C band radar in the corresponding area annotation, and use the loss function to calculate the horizontal reflectivity difference value of the corresponding area; According to the horizontal reflectivity difference value of the corresponding area, the fitting function parameters of the corresponding area are adjusted and updated by using a gradient descent algorithm; The fitting process of the X-band dual-polarization radar horizontal reflectivity of each region is repeated until the loss function of each region converges, and the attenuation correction model of each region when the loss function converges is used as the trained attenuation correction model corresponding to each region.

8. The method according to claim 6, characterized in that The relationship between the differential propagation phase and the differential reflectivity of the X-band dual polarization radar after quality control in the training sample set of each region and the differential reflectivity of the S / C-band radar in the corresponding region annotation is fitted by using a fitting function, including: In the process of fitting the differential reflectivity of the X-band dual-polarization radar in each region, the fitting function is used to fit the relationship between the differential propagation phase and differential reflectivity of the X-band dual-polarization radar after quality control in the training sample set of each region and the differential reflectivity of the S / C-band radar in the corresponding regional annotation; Compare the differential reflectivity of the S / C band radar in each area obtained by fitting with the differential reflectivity of the S / C band radar in the corresponding area annotation, and use the loss function to calculate the differential reflectivity difference value of the corresponding area; According to the differential reflectivity gap value of the corresponding area, the fitting function parameters of the corresponding area are adjusted and updated by using a gradient descent algorithm; The fitting process of the X-band dual-polarization radar differential reflectivity of each region is repeated until the loss function of each region converges, and the attenuation correction model of each region when the loss function converges is used as the trained attenuation correction model corresponding to each region.

9. The method according to claim 1, characterized in that: The horizontal reflectivity of the X-band dual polarization radar after attenuation correction is the horizontal reflectivity of the S / C-band radar output by the attenuation correction model in the area where the X-band dual polarization radar that needs attenuation correction is located, and the differential reflectivity is the differential reflectivity of the S / C-band radar output by the attenuation correction model in the area where the X-band dual polarization radar that needs attenuation correction is located.

10. An X-band dual-polarization radar attenuation correction device based on artificial intelligence, characterized in that: include: The module for generating time-space matching data sets for each region is used to perform time-space matching on the existing observation data of the X-band dual-polarization radar and the existing observation data of the S / C-band radar in each region to generate the time-space matching data sets for each region; The attenuation correction model generation module of each region is used to train the attenuation correction model of the corresponding region according to the spatiotemporal matching data set of each region to generate the attenuation correction model of each region; The attenuation correction module is used to perform quality control on the observation data of the X-band dual polarization radar that needs attenuation correction and input it into the attenuation correction model of the area where the X-band dual polarization radar that needs attenuation correction is located, so as to obtain the horizontal reflectivity and differential reflectivity of the X-band dual polarization radar after attenuation correction.

Images