A precipitation prediction method and device, electronic equipment and storage medium

Abstract

The application provides a precipitation prediction method and device, electronic equipment and storage medium, the method comprises the following steps: obtaining a plurality of frequency polarization channel brightness temperature data and infrared channel brightness temperature data of a target area based on a polar orbit satellite and a geosynchronous orbit satellite; determining whether a target area has a precipitation event according to the obtained data; if so, filtering the target frequency polarization channel brightness temperature data according to the sea-land classification result of the target area; determining the precipitation prediction result of the target area according to the target frequency polarization channel brightness temperature data and the infrared channel brightness temperature data. By combining the meteorological monitoring data of the polar orbit satellite and the geosynchronous orbit satellite, the temporal and spatial resolution of the meteorological monitoring data is improved, and the passive microwave data, infrared data including water vapor channel data are integrated, thereby improving the accuracy of the precipitation prediction.

Description

TECHNICAL FIELD

[0001] The present application relates to the meteorological prediction technical field, and particularly relates to a precipitation prediction method and device, electronic equipment and storage medium. BACKGROUND

[0002] Precipitation is a common weather phenomenon, and precipitation generally has certain influence on human production and life and the growth of crops, so if precipitation prediction is always a hot research content.

[0003] In the prior art, meteorological monitoring data is generally obtained based on a passive microwave radiometer (PWM), and precipitation is estimated by analyzing the direct relationship between the vertical characteristics of the atmosphere and water condensate represented by the meteorological monitoring data.

[0004] However, since the passive microwave radiometer is generally carried on a low orbit satellite, it cannot perform real-time monitoring of meteorological data on a target area, and the time resolution of the obtained meteorological monitoring data is low, so that the accuracy of the final obtained precipitation prediction result is low. SUMMARY

[0005] The present application provides a precipitation prediction method, device, electronic equipment and storage medium to solve the defects that the accuracy of the final obtained precipitation prediction result in the prior art is low.

[0006] The first aspect of the present application provides a precipitation prediction method, comprising:

[0007] Obtaining a plurality of frequency polarization channel brightness temperature data and infrared channel brightness temperature data of a target area based on a polar orbit satellite and a geosynchronous orbit satellite, wherein the infrared channel brightness temperature data comprises water vapor channel brightness temperature data;

[0008] Determining whether a precipitation event exists in the target area according to the plurality of frequency polarization channel brightness temperature data and the infrared channel brightness temperature data;

[0009] In a case where it is determined that the target area has a precipitation event, screening target frequency polarization channel brightness temperature data from the plurality of frequency polarization channel brightness temperature data according to a sea-land classification result of the target area;

[0010] Determining a precipitation prediction result of the target area according to the target frequency polarization channel brightness temperature data and the infrared channel brightness temperature data.

[0011] Optionally, the determining whether a precipitation event exists in the target area according to the plurality of frequency polarization channel brightness temperature data and the infrared channel brightness temperature data comprises:

[0012] According to the brightness temperature data of the several frequency polarization channels and the infrared channel, a precipitation amount of the target area is estimated, and an estimated value of the precipitation amount of the target area is obtained.

[0013] When the estimated value of the precipitation amount reaches a preset threshold, it is determined that the target area has a precipitation event.

[0014] Optionally, the estimating the precipitation amount of the target area according to the brightness temperature data of the several frequency polarization channels and the infrared channel, and obtaining the estimated value of the precipitation amount of the target area, comprises:

[0015] According to the brightness temperature data of the several frequency polarization channels and the infrared channel, a precipitation amount of the target area is estimated, and an estimated value of the precipitation amount of the target area is obtained.

[0016] Optionally, the polar orbit satellite and the geosynchronous orbit satellite are FY3-D satellite and GOES satellite respectively, and the obtaining the brightness temperature data of the several frequency polarization channels and the infrared channel of the target area based on the polar orbit satellite and the geosynchronous orbit satellite comprises:

[0017] The brightness temperature data of the several frequency polarization channels of the target area are obtained based on the FY3-D satellite, and the brightness temperature data of the several frequency polarization channels comprise polarization channel brightness temperature data of the FY3-D satellite at frequencies of 10.65 GHz, 18.7 GHz, 23.8 GHz, 36.5 GHz and 89 GHz;

[0018] The infrared channel brightness temperature data of the target area are obtained based on the GOES satellite, and the infrared channel brightness temperature data comprise brightness temperature data of the GOES satellite at a 10.8 μm channel, and the water vapor channel brightness temperature data are brightness temperature data of the GOES satellite at a 6.7 μm channel.

[0019] Optionally, the selecting target frequency polarization channel brightness temperature data from the several frequency polarization channel brightness temperature data according to the sea-land classification result of the target area when it is determined that the target area has a precipitation event comprises:

[0020] When it is determined that the target area has a precipitation event, if the sea-land classification result of the target area indicates that the target area is a sea area, polarization channel brightness temperature data of the FY3-D satellite at frequencies of 23.8 GHz, 36.5 GHz and 89 GHz are determined as target polarization channel brightness temperature data.

[0021] If the sea-land classification result of the target area represents that the target area is a land area, the polarized channel brightness temperature data of the FY3-D satellite at frequencies of 18.7 GHz, 23.8 GHz and 36.5 GHz are determined as the target polarized channel brightness temperature data.

[0022] Optionally, the determining of the precipitation prediction result of the target area according to the target frequency polarized channel brightness temperature data and the infrared channel brightness temperature data comprises:

[0023] If the sea-land classification result of the target area represents that the target area is a sea area, the precipitation prediction result of the target area is determined according to the polarized brightness temperature data and the infrared channel brightness temperature data of the FY3-D satellite at frequencies of 23.8 GHz, 36.5 GHz and 89 GHz based on a preset sea precipitation prediction model.

[0024] If the sea-land classification result of the target area represents that the target area is a land area, the precipitation prediction result of the target area is determined according to the polarized channel brightness temperature data and the infrared channel brightness temperature data of the FY3-D satellite at frequencies of 18.7 GHz, 23.8 GHz and 36.5 GHz based on a preset land precipitation prediction model.

[0025] Optionally, the method further comprises:

[0026] determining a rainfall prediction range according to the scanning footprints of the FY3-D satellite and the GOES satellite;

[0027] dividing a plurality of rainfall prediction grid points in the rainfall prediction range, and determining a target rainfall prediction grid point corresponding to the target area; wherein each of the rainfall prediction grid points is provided with a sea-land mark;

[0028] determining a sea-land classification result of the target area according to the sea-land mark of the target rainfall prediction grid point.

[0029] The second aspect of the present application provides a precipitation prediction device, comprising:

[0030] an acquisition module configured to acquire a plurality of frequency polarized channel brightness temperature data and infrared channel brightness temperature data of a target area based on a polar orbit satellite and a geosynchronous orbit satellite, wherein the infrared channel brightness temperature data comprises water vapor channel brightness temperature data;

[0031] a judgment module configured to judge whether a precipitation event exists in the target area according to the plurality of frequency polarized channel brightness temperature data and the infrared channel brightness temperature data;

[0032] a screening module configured to, in a case where it is determined that the target area has a precipitation event, screen target frequency-polarization channel brightness temperature data from the plurality of frequency-polarization channel brightness temperature data according to a sea-land classification result of the target area;

[0033] a prediction module configured to determine a precipitation amount prediction result of the target area according to the target frequency-polarization channel brightness temperature data and infrared channel brightness temperature data.

[0034] Optionally, the determining module is specifically configured to:

[0035] estimate the precipitation amount of the target area according to the plurality of frequency-polarization channel brightness temperature data and the infrared channel brightness temperature data to obtain a precipitation amount estimation value of the target area;

[0036] determine that the target area has a precipitation event when the precipitation amount estimation value reaches a preset threshold.

[0037] Optionally, the determining module is specifically configured to:

[0038] estimate the precipitation amount of the target area according to the plurality of frequency-polarization channel brightness temperature data and the infrared channel brightness temperature data based on a preset precipitation amount estimation model to obtain the precipitation amount estimation value of the target area.

[0039] Optionally, the polar orbit satellite and the geosynchronous orbit satellite are FY3-D satellite and GOES satellite respectively, and the obtaining module is specifically configured to:

[0040] obtain the plurality of frequency-polarization channel brightness temperature data of the target area based on the FY3-D satellite; wherein the plurality of frequency-polarization channel brightness temperature data includes polarization channel brightness temperature data of the FY3-D satellite at frequencies of 10.65 GHz, 18.7 GHz, 23.8 GHz, 36.5 GHz and 89 GHz;

[0041] obtain infrared channel brightness temperature data of the target area based on the GOES satellite; wherein the infrared channel brightness temperature data includes brightness temperature data of the GOES satellite at a 10.8 μm channel, and the water vapor channel brightness temperature data is brightness temperature data of the GOES satellite at a 6.7 μm channel.

[0042] Optionally, the screening module is specifically configured to:

[0043] in a case where it is determined that the target area has a precipitation event, if the sea-land classification result of the target area indicates that the target area is a sea area, determine polarization channel brightness temperature data of the FY3-D satellite at frequencies of 23.8 GHz, 36.5 GHz and 89 GHz as target polarization channel brightness temperature data;

[0044] If the sea-land classification result of the target area represents that the target area is a land area, the polarization channel brightness temperature data of the FY3-D satellite at 18.7 GHz, 23.8 GHz and 36.5 GHz frequencies is determined as the target polarization channel brightness temperature data.

[0045] Optionally, the prediction module is specifically configured to:

[0046] If the sea-land classification result of the target area represents that the target area is a sea area, the polarization brightness temperature data and infrared channel brightness temperature data of the FY3-D satellite at 23.8 GHz, 36.5 GHz and 89 GHz frequencies are used to determine the precipitation prediction result of the target area based on a preset sea precipitation prediction model.

[0047] If the sea-land classification result of the target area represents that the target area is a land area, the polarization channel brightness temperature data and infrared channel brightness temperature data of the FY3-D satellite at 18.7 GHz, 23.8 GHz and 36.5 GHz frequencies are used to determine the precipitation prediction result of the target area based on a preset land precipitation prediction model.

[0048] Optionally, the device further comprises:

[0049] The classification module is configured to determine a rainfall prediction range according to the scanning footprints of the FY3-D satellite and the GOES satellite, divide a plurality of rainfall prediction grid points in the rainfall prediction range, and determine a target rainfall prediction grid point corresponding to the target area; wherein each of the rainfall prediction grid points is provided with a sea-land mark; and determine the sea-land classification result of the target area according to the sea-land mark of the target rainfall prediction grid point.

[0050] The third aspect of the present application provides an electronic device, comprising: at least one processor and a memory;

[0051] The memory stores computer execution instructions;

[0052] The at least one processor executes the computer execution instructions stored in the memory, so that the at least one processor executes the method as described in the first aspect and various possible designs of the first aspect.

[0053] The fourth aspect of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores computer execution instructions, and when the processor executes the computer execution instructions, the method as described in the first aspect and various possible designs of the first aspect is realized.

[0054] The technical solution of the present application has the following advantages:

[0055] The application provides a precipitation prediction method and device, electronic equipment and storage medium. The method comprises the following steps: obtaining several frequency polarization channel brightness temperature data and infrared channel brightness temperature data of a target area based on a polar orbit satellite and a geosynchronous orbit satellite, wherein the infrared channel brightness temperature data comprises water vapor channel brightness temperature data; determining whether a precipitation event exists in the target area according to the several frequency polarization channel brightness temperature data and the infrared channel brightness temperature data; in the case that it is determined that the precipitation event exists in the target area, screening target frequency polarization channel brightness temperature data from the several polarization channel brightness temperature data according to a sea-land classification result of the target area; and determining a precipitation amount prediction result of the target area according to the target frequency polarization channel brightness temperature data and the infrared channel brightness temperature data. The method provided by the above scheme improves the spatiotemporal resolution of meteorological monitoring data by combining meteorological monitoring data of the polar orbit satellite and the geosynchronous orbit satellite, and improves the accuracy of precipitation amount prediction by comprehensively considering passive microwave data and infrared channel brightness temperature data including water vapor channel. BRIEF DESCRIPTION OF DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art based on these drawings.

[0057] Figure 1 Structure diagram of a precipitation prediction system based on the embodiments of the present application;

[0058] Figure 2 Flow diagram of a precipitation prediction method provided by the embodiments of the present application;

[0059] Figure 3 Structure diagram of an exemplary preset precipitation amount estimation model provided by the embodiments of the present application;

[0060] Figure 4 Overall flow diagram of an exemplary precipitation prediction method provided by the embodiments of the present application;

[0061] Figure 5 Structure diagram of a precipitation prediction device provided by the embodiments of the present application;

[0062] Figure 6 Structure diagram of an electronic equipment provided by the embodiments of the present application.

[0063] The above drawings have shown the specific embodiments of the present application, and the following will have more detailed description. These drawings and text description are not intended to limit the scope of the present disclosure concept by any means, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0065] Furthermore, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. In the following descriptions of embodiments, "a plurality of" means two or more, unless otherwise explicitly defined.

[0066] In existing technologies, meteorological monitoring data is typically acquired using passive microwave radiometers (PWM), and precipitation is estimated by analyzing the direct relationship between the vertical characteristics of the atmosphere and condensates as represented by the meteorological monitoring data. However, since passive microwave radiometers are generally mounted on low-Earth orbit satellites, they cannot perform real-time monitoring of meteorological data in the target area, resulting in low temporal resolution of the obtained meteorological monitoring data and consequently, low accuracy of the final precipitation prediction results.

[0067] To address the aforementioned issues, the precipitation prediction method, apparatus, electronic device, and storage medium provided in this application acquire brightness temperature data of several frequency polarization channels and infrared channels for a target area based on polar-orbiting satellites and geostationary satellites. The infrared channel brightness temperature data includes water vapor channel brightness temperature data. Based on the brightness temperature data of these channels, it is determined whether a precipitation event exists in the target area. If a precipitation event is determined, target frequency polarization channel brightness temperature data is selected from the several polarization channel brightness temperature data based on the land-sea classification results of the target area. Finally, based on the target frequency polarization channel brightness temperature data and the infrared channel brightness temperature data, the precipitation prediction result for the target area is determined. The method provided by the above scheme improves the spatiotemporal resolution of meteorological monitoring data by combining meteorological monitoring data from polar-orbiting satellites and geostationary satellites, and improves the accuracy of precipitation prediction by integrating passive microwave data and infrared channel brightness temperature data, including water vapor channel data.

[0068] The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the present invention will now be described with reference to the accompanying drawings.

[0069] First, the structure of the precipitation prediction system on which this application is based will be described:

[0070] The precipitation prediction method, apparatus, electronic device, and storage medium provided in this application are applicable to predicting precipitation in any region worldwide. Figure 1 The diagram shown is a schematic of the precipitation prediction system based on the embodiments of this application. It mainly includes polar-orbiting satellites, geostationary orbit satellites, and precipitation prediction devices. Specifically, it can collect brightness temperature data of several frequency polarization channels and infrared channels of the target area based on polar-orbiting satellites and geostationary orbit satellites, that is, obtain multi-source satellite data. Then, the obtained multi-source satellite data is sent to the precipitation prediction device, which performs precipitation prediction for the target area based on the obtained data.

[0071] This application provides a precipitation forecasting method for predicting precipitation in any region globally. The execution subject of this application is an electronic device, such as a server, desktop computer, laptop computer, tablet computer, or other electronic devices capable of processing and analyzing satellite data.

[0072] like Figure 2 The diagram shown is a flowchart illustrating the precipitation prediction method provided in this application embodiment. The method includes:

[0073] Step 201: Obtain brightness temperature data of several frequency polarization channels and infrared channels of the target area based on polar-orbiting satellites and geostationary satellites.

[0074] The infrared channel includes a water vapor channel, meaning the infrared channel brightness temperature data includes the water vapor channel brightness temperature data.

[0075] It should be noted that compared to traditional ground-based precipitation measurements, satellite remote sensing of precipitation offers advantages such as global coverage and high spatiotemporal resolution. Currently, mainstream meteorological satellites carry passive microwave radiometers (PWM) and radiation imagers that provide microwave and visible / infrared (VIS / IR) data, with a few satellites carrying precipitation radar. However, traditional infrared brightness temperature data itself cannot contain sufficient precipitation-related information, and the introduction of visible light observations limits its application during the day. In contrast, while microwave data can provide more direct instantaneous precipitation measurements, its spatiotemporal resolution is inferior to that of PWM.

[0076] Specifically, in order to improve the accuracy of precipitation prediction, this application embodiment acquires brightness temperature data of several frequency polarization channels and infrared channels of the target area based on polar-orbiting satellites and geostationary satellites to obtain multi-source satellite data. It combines the advantages of passive microwave brightness temperature data and visible / infrared (VIS / IR) brightness temperature data, and adds water vapor channel (WV) brightness temperature data as an auxiliary, laying the foundation for improving the accuracy of the final precipitation prediction result.

[0077] Step 202, determining whether a precipitation event exists in the target region according to the brightness temperature data of the several frequency polarization channels and the brightness temperature data of the infrared channel.

[0078] Specifically, the precipitation possibility of the target region can be estimated according to the brightness temperature data of the several frequency polarization channels and the brightness temperature data of the infrared channel of the target region, and then whether a precipitation event exists in the target region can be determined according to the estimation result.

[0079] Step 203, in the case that it is determined that the target region has a precipitation event, screening target frequency polarization channel brightness temperature data from the several frequency polarization channel brightness temperature data according to the sea-land classification result of the target region.

[0080] It should be noted that the land and the sea have different microwave radiation characteristics. For the sea, the background radiation signal of passive remote sensing is small due to the low microwave emissivity of the sea surface (0.4-0.5), which is close to a constant. In this background, the emission radiation signal of precipitation is strong, and the low polarization characteristics of precipitation are obviously different from the high polarization characteristics of the sea surface, so the sea surface precipitation can be distinguished and quantitatively inverted at a low frequency. For the land, the microwave emissivity of the ground is usually high (0.7-0.9) and has a large variation range, so it is difficult to identify and quantify the emission radiation from water condensate. At the same time, the polarization characteristics of the land surface are not obvious, which increases the difficulty of land precipitation inversion. Since the scattering effect of ice particles at a high frequency will weaken the uplink radiation intensity of the ground, this feature can be used for land precipitation information extraction.

[0081] Specifically, the target frequency polarization channel brightness temperature data meeting the microwave radiation characteristics of the land and the sea can be screened from the several frequency polarization channel brightness temperature data according to the microwave radiation characteristics of the land and the sea.

[0082] Step 204, determining the precipitation amount prediction result of the target region according to the target frequency polarization channel brightness temperature data and the infrared channel brightness temperature data.

[0083] Specifically, the precipitation amount of the target region can be further predicted in a targeted manner according to the target frequency polarization channel brightness temperature data and the infrared channel brightness temperature data to obtain the precipitation amount prediction result of the target region.

[0084] On the basis of the above embodiment, as a kind of implementable mode, in an embodiment, according to the brightness temperature data of the several frequency polarization channels and the brightness temperature data of the infrared channel, whether target region has precipitation event, including:

[0085] Step 2021, according to the brightness temperature data of the several frequency polarization channels and the brightness temperature data of the infrared channel, the precipitation amount of target region is estimated, and the precipitation amount estimation value of target region is obtained;

[0086] Step 2022, when the precipitation estimation value reaches the preset threshold, it is determined that the target area has a precipitation event.

[0087] Wherein, the precipitation specifically refers to IMERG hourly precipitation, when the precipitation estimation value of the target area reaches 0.1 mm / h, it is determined that the target area has a high possibility of precipitation, and thus it is determined that the target area has a precipitation event.

[0088] Specifically, in an embodiment, the precipitation of the target area can be estimated based on a preset precipitation estimation model according to the brightness temperature data of the plurality of frequency polarization channels and the brightness temperature data of the infrared channel, to obtain the precipitation estimation value of the target area.

[0089] For example, as shown in Figure 3 The structure diagram of the exemplary preset precipitation estimation model provided by the embodiment of the present application is shown in the figure. The preset precipitation estimation model is a binary classification model, which can be constructed based on a supervised learning algorithm. The cost function uses a cross-entropy function, and the activation function uses a tanh function. The brightness temperature data of the plurality of frequency polarization channels (passive microwave data FY3-D MWRI BT) and the brightness temperature data of the infrared channel (infrared / water vapor channel data GOES BT) are input features of the preset precipitation estimation model, i.e. the input layer input grid brightness temperature data. In the case of dividing the scanning range of the polar orbit satellite and the geosynchronous orbit satellite into a plurality of rainfall prediction grid points, the input features of the model can include the brightness temperature data of the plurality of frequency polarization channels and the brightness temperature data of the infrared channel corresponding to the plurality of rainfall prediction grid points, Figure 3 As shown in the figure, n rainfall prediction grid points, X11~X1n represent the brightness temperature data of the plurality of frequency polarization channels of 1~n rainfall prediction grid points, X21~X2n represent the brightness temperature data of the infrared channel of 1~n rainfall prediction grid points, and the output layer outputs the judgment result of whether each rainfall prediction grid point has a precipitation event after the hidden layer one and the hidden layer two.

[0090] Wherein, in the training process of the preset precipitation estimation model, a large number of time and space matched brightness temperature data of the plurality of frequency polarization channels, the infrared channel and the actual IMERG hourly precipitation can be selected as a sample set, and the data in the sample set is z-score standardized and then divided into a training set, a validation set and a test set three parts. In order to evaluate the performance of the model in predicting the occurrence of precipitation events, commonly used classification evaluation indicators are used, including detection probability (POD), false alarm rate (FAR) and critical success index (CSI), to evaluate the performance of the trained model:

[0091]

[0092]

[0093]

[0094] Wherein, H (hit) represents the number of precipitation events that both the preset precipitation estimation model and the ground observation appear, M (miss) represents the number of precipitation events that the ground observation captures but is missed by the preset precipitation estimation model, and F (false alarm) represents the number of precipitation events that the ground observation does not appear precipitation but the preset precipitation estimation model misreports. When each classification evaluation index reaches the preset standard, it is determined that the model reaches the standard and can be put into use.

[0095] On the basis of the above embodiment, as an implementable manner, in an embodiment, the polar orbit satellite and the geosynchronous orbit satellite are FY3-D satellite and GOES satellite respectively, and the several frequency polarization channel brightness temperature data and the infrared channel brightness temperature data of the target region are acquired based on the polar orbit satellite and the geosynchronous orbit satellite, including:

[0096] In step 2011, the several frequency polarization channel brightness temperature data of the target region are acquired based on the FY3-D satellite; wherein the several frequency polarization channel brightness temperature data include the polarization channel brightness temperature data of the FY3-D satellite in the 10.65Ghz, 18.7Ghz, 23.8Ghz, 36.5Ghz and 89Ghz frequencies;

[0097] In step 2012, the infrared channel brightness temperature data of the target region are acquired based on the GOES satellite; wherein the infrared channel brightness temperature data include the brightness temperature data of the GOES satellite in the 10.8μm channel, and the water vapor channel brightness temperature data is the brightness temperature data of the GOES satellite in the 6.7μm channel.

[0098] In step 2011, the several frequency polarization channel brightness temperature data of the target region are acquired based on the FY3-D satellite; wherein the several frequency polarization channel brightness temperature data include the polarization channel brightness temperature data of the FY3-D satellite in the 10.65Ghz, 18.7Ghz, 23.8Ghz, 36.5Ghz and 89Ghz frequencies;

[0099] Specifically, all the original data collected by the FY3-D satellite and the GOES satellite in a preset scanning period can be acquired first, and the original data includes the several frequency polarization channel brightness temperature data and the infrared channel brightness temperature data. Then the required information in the FY3-D satellite and the GOES satellite is extracted, at least including the scanning time (UTC) of the satellite, the scanning strip algebra and the latitude and longitude of the scanning footprint, the method of synchronous conical bridge (SCO) is used for pairing the data of the FY3-D satellite and the GOES satellite, and the matching principle is that the distance of the center point pixels of the scanning footprint does not exceed 5km and the time difference does not exceed 30min. Subsequently, the matched data is converted into 0.25°×0.25° hourly grid data through linear interpolation.

[0100] Specifically, in an embodiment, if the sea-land classification result of the target region indicates that the target region is a sea region, the polarized channel brightness temperature data of the FY3-D satellite at frequencies of 23.8 GHz, 36.5 GHz and 89 GHz are determined as the target frequency polarized channel brightness temperature data; if the sea-land classification result of the target region indicates that the target region is a land region, the polarized channel brightness temperature data of the FY3-D satellite at frequencies of 18.7 GHz, 23.8 GHz and 36.5 GHz are determined as the target frequency polarized channel brightness temperature data.

[0101] wherein the infrared channel brightness temperature data of the target region includes the brightness temperature data of the GOES satellite at a wavelength of 10.8 μm channel, and the water vapor channel brightness temperature data is the brightness temperature data of the GOES satellite at a wavelength of 6.7 μm channel.

[0102] Specifically, in an embodiment, the rainfall prediction range can be determined according to the scanning footprints of the FY3-D satellite and the GOES satellite; a plurality of rainfall prediction grid points are divided within the rainfall prediction range, and a target rainfall prediction grid point corresponding to the target region is determined; wherein each rainfall prediction grid point is provided with a sea-land mark; and the sea-land classification result of the target region is determined according to the sea-land mark of the target rainfall prediction grid point.

[0103] wherein the rainfall prediction range is the scanning range of the FY3-D satellite and the GOES satellite, and the rainfall prediction range is divided into a plurality of rainfall prediction grid points according to the specification of 0.25° × 0.25° of longitude and latitude, and then the target rainfall prediction grid point corresponding to the target region is determined according to the longitude and latitude information of the target region, and the sea-land mark of the target rainfall prediction grid point is determined as the sea-land classification result of the target region.

[0104] Specifically, in an embodiment, when the sea-land classification result of the target region indicates that the target region is a sea region, the rainfall amount prediction result of the target region is determined according to the polarized channel brightness temperature data of the FY3-D satellite at frequencies of 23.8 GHz, 36.5 GHz and 89 GHz and the infrared channel brightness temperature data based on a preset sea rainfall amount prediction model; when the sea-land classification result of the target region indicates that the target region is a land region, the rainfall amount prediction result of the target region is determined according to the polarized channel brightness temperature data of the FY3-D satellite at frequencies of 18.7 GHz, 23.8 GHz and 36.5 GHz and the infrared channel brightness temperature data based on a preset land rainfall amount prediction model.

[0105] Specifically, the input features of the preset marine precipitation prediction model include horizontal and vertical polarization channel brightness temperature data of FY3-D satellite at 23.8 GHz, 36.5 GHz and 89 GHz frequencies, and brightness temperature data of GOES satellite at 10.8 μm and 6.7 μm channels, the input features of the preset land precipitation prediction model include horizontal and vertical polarization channel brightness temperature data of FY3-D satellite at 18.7 GHz, 23.8 GHz and 36.5 GHz frequencies, and brightness temperature data of GOES satellite at 10.8 μm and 6.7 μm channels, and the output features of the preset marine precipitation prediction model and the preset land precipitation prediction model are the precipitation prediction results of the target area. The specific structure of the preset marine precipitation prediction model and the preset land precipitation prediction model can be referred to the above Figure 3 , which will not be repeated here. For the precipitation prediction model, a data-driven model using mean square error (MSE) as a cost function is adopted, which tends to be conservative and can avoid predicting too large values, and a Relu function is used as an activation function.

[0106] , the preset marine precipitation prediction model and the preset land precipitation prediction model are used to estimate the hourly precipitation of the target area. In order to evaluate the accuracy and consistency of the model in predicting precipitation, Pearson correlation coefficient (COR), relative bias (Bias) and root mean square error (RMSE) are used as model evaluation indicators, which are defined as:

[0107]

[0108]

[0109]

[0110] , X i represents the hourly precipitation calculated by the model, Y i represents the reference ground precipitation observation value.

[0111] For example, Figure 4As shown, it is the overall flow schematic diagram of the exemplary precipitation prediction method provided by the embodiment of the present application, specifically the construction process of the network model adopted by the embodiment of the present application, the FY3-DMWRL data is the brightness temperature data of a plurality of frequency polarization channels, the GOES data is the brightness temperature data of the infrared channel including the water vapor channel, the brightness temperature data of the SCO configuration is obtained by adopting the method of synchronous conical bridge (SCO) to pair the FY3-D data and the GOES data, then the IMERG precipitation data, the FY3-D data and the GOES data are gridded and longitude-latitude matched in combination with the time and space matched IMERG precipitation data, a one-stage model (preset precipitation amount estimation model) is adopted to screen the grids with precipitation events (precipitation grids), and the one-stage model is evaluated. For the rain grids (precipitation grids), the sea-land classification results of the precipitation grids are determined first, the corresponding two-stage model (preset marine precipitation prediction model or preset land precipitation prediction model) is adopted to perform marine precipitation inversion or land precipitation inversion, and the corresponding precipitation prediction results are obtained, and finally the two-stage model is evaluated according to the precipitation prediction results output by the model.

[0112] The precipitation prediction method provided by the embodiment of the present application acquires a plurality of frequency polarization channel brightness temperature data and infrared channel brightness temperature data of a target region based on a polar orbit satellite and a geosynchronous orbit satellite, and the infrared channel brightness temperature data includes water vapor channel brightness temperature data; determines whether there is a precipitation event in the target region according to the plurality of frequency polarization channel brightness temperature data and the infrared channel brightness temperature data; in the case that it is determined that there is a precipitation event in the target region, screens target frequency polarization channel brightness temperature data from the plurality of polarization channel brightness temperature data according to the sea-land classification results of the target region; and determines the precipitation prediction results of the target region according to the target frequency polarization channel brightness temperature data and the infrared channel brightness temperature data. The method provided by the above scheme improves the temporal and spatial resolution of the meteorological monitoring data by combining the meteorological monitoring data of the polar orbit satellite and the geosynchronous orbit satellite, and improves the accuracy of the precipitation prediction by comprehensively using the passive microwave data, the infrared data including the infrared channel brightness temperature data of the water vapor channel. In addition, a multi-stage precipitation estimation model is developed by combining the deep learning technology, and the precipitation prediction is carried out according to the sea-land classification results of the target region, which improves the accuracy of the precipitation inversion. The multi-channel infrared and microwave observation data are comprehensively used to improve the identification of precipitation, the sea-land inversion of precipitation, and the temporal and spatial resolution of the precipitation prediction, and more accurate and high-quality full-time near real-time rainfall prediction results can be obtained.

[0113] The embodiment of the present application provides a precipitation prediction device for executing the precipitation prediction method provided by the above-mentioned embodiment.

[0114] As Figure 5As shown, a structure schematic diagram of the precipitation prediction device provided by the embodiment of the present application is shown. The precipitation prediction device 50 comprises an acquisition module 501, a judgment module 502, a screening module 503 and a prediction module 504.

[0115] The acquisition module is configured to acquire, based on the polar orbit satellite and the geosynchronous orbit satellite, the several frequency polarization channel brightness temperature data and the infrared channel brightness temperature data of the target region, and the infrared channel brightness temperature data comprises water vapor channel brightness temperature data.

[0116] Specifically, in an embodiment, the judgment module is specifically configured to:

[0117] estimate the precipitation of the target region based on the several frequency polarization channel brightness temperature data and the infrared channel brightness temperature data to obtain a precipitation estimation value of the target region.

[0118] When the precipitation estimation value reaches a preset threshold, it is determined that the target region has a precipitation event.

[0119] Specifically, in an embodiment, the judgment module is specifically configured to:

[0120] estimate the precipitation of the target region based on the several frequency polarization channel brightness temperature data and the infrared channel brightness temperature data based on a preset precipitation estimation model to obtain a precipitation estimation value of the target region.

[0121] Specifically, in an embodiment, the polar orbit satellite and the geosynchronous orbit satellite are respectively FY3-D satellite and GOES satellite, and the acquisition module is specifically configured to:

[0122] acquire, based on the FY3-D satellite, the several frequency polarization channel brightness temperature data of the target region; wherein the several frequency polarization channel brightness temperature data comprise polarization channel brightness temperature data of the FY3-D satellite at 10.65 GHz, 18.7 GHz, 23.8 GHz, 36.5 GHz and 89 GHz frequencies.

[0123] acquire, based on the GOES satellite, the infrared channel brightness temperature data of the target region; wherein the infrared channel brightness temperature data comprise brightness temperature data of the GOES satellite at 10.8 μm channel, and the water vapor channel brightness temperature data is brightness temperature data of the GOES satellite at 6.7 μm channel.

[0124] Specifically, in an embodiment, the screening module is specifically configured to:

[0125] In the case that it is determined that the target area has a precipitation event, if the sea-land classification result of the target area indicates that the target area is a sea area, polarized channel brightness temperature data of the FY3-D satellite at 23.8 GHz, 36.5 GHz and 89 GHz frequencies is determined as the target polarized channel brightness temperature data;

[0126] If the sea-land classification result of the target area indicates that the target area is a land area, polarized channel brightness temperature data of the FY3-D satellite at 18.7 GHz, 23.8 GHz and 36.5 GHz frequencies is determined as the target polarized channel brightness temperature data.

[0127] Specifically, in an embodiment, the prediction module is specifically configured to:

[0128] When the sea-land classification result of the target area indicates that the target area is a sea area, a preset sea precipitation prediction model is used to determine a precipitation prediction result of the target area according to the polarized channel brightness temperature data of the FY3-D satellite at 23.8 GHz, 36.5 GHz and 89 GHz frequencies and the infrared channel brightness temperature data.

[0129] When the sea-land classification result of the target area indicates that the target area is a land area, a preset land precipitation prediction model is used to determine a precipitation prediction result of the target area according to the polarized channel brightness temperature data of the FY3-D satellite at 18.7 GHz, 23.8 GHz and 36.5 GHz frequencies and the infrared channel brightness temperature data.

[0130] Optionally, the device further comprises:

[0131] The classification module is configured to determine a rainfall prediction range according to scanning footprints of the FY3-D satellite and the GOES satellite, divide a plurality of rainfall prediction grid points in the rainfall prediction range, and determine a target rainfall prediction grid point corresponding to the target area; each rainfall prediction grid point is provided with a sea-land mark; and the sea-land classification result of the target area is determined according to the sea-land mark of the target rainfall prediction grid point.

[0132] As to the precipitation prediction device in the embodiment, the specific manners in which the modules perform operations have been described in detail in the embodiments of the method, and thus will not be described in detail here.

[0133] The precipitation prediction device provided by the embodiments of the present application is used to perform the precipitation prediction method provided by the above embodiments, and has the same implementation manner and principle, which will not be described in detail.

[0134] The embodiments of the present application provide an electronic device for executing the precipitation prediction method provided by the above embodiments.

[0135] As Figure 6 shown, a structural schematic diagram of an electronic device provided by an embodiment of the present application is provided. The electronic device 60 comprises at least one processor 61 and a memory 62.

[0136] The memory stores computer execution instructions; the at least one processor executes the computer execution instructions stored by the memory, so that the at least one processor executes the precipitation prediction method provided by the above embodiment.

[0137] The electronic device provided by an embodiment of the present application is used to execute the precipitation prediction method provided by the above embodiment, and the implementation manner is the same as the principle, and will not be repeated.

[0138] The computer readable storage medium provided by an embodiment of the present application stores computer execution instructions, when the processor executes the computer execution instructions, the precipitation prediction method provided by any one of the above embodiments is realized.

[0139] The storage medium provided by an embodiment of the present application contains computer executable instructions, which can be used to store the computer execution instructions of the precipitation prediction method provided in the above embodiment, and the implementation manner is the same as the principle, and will not be repeated.

[0140] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiment described above is only schematic, for example, the division of the unit is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be through some interface, device or unit indirect coupling or communication connection, which can be electrical, mechanical or other forms.

[0141] The unit described as a separate component can be or can not be physically separated, and the component displayed as a unit can be or can not be a physical unit, that is, it can be located in one place, or can be distributed to a plurality of network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the embodiment scheme.

[0142] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The above integrated unit can be realized in the form of hardware or in the form of hardware plus software functional unit.

[0143] The integrated unit implemented in the form of the software function unit can be stored in a computer readable storage medium. The software function unit is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute part of steps of the method described in each embodiment of the present application. The foregoing storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0144] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional module is taken as an example, and in actual application, the above-mentioned functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the device described above can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0145] Finally, it should be pointed out that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A precipitation prediction method characterized by, include: Brightness temperature data of several frequency polarization channels and infrared channels of the target area are obtained based on polar-orbiting satellites and geostationary satellites. The infrared channel brightness temperature data includes water vapor channel brightness temperature data. Based on the brightness temperature data of the aforementioned frequency polarization channels and the brightness temperature data of the infrared channels, it is determined whether a precipitation event exists in the target area; If it is determined that there is a precipitation event in the target area, target frequency polarization channel brightness temperature data is selected from the several frequency polarization channel brightness temperature data according to the land-sea classification results of the target area. Based on the target frequency polarization channel brightness temperature data and the infrared channel brightness temperature data, the precipitation prediction result for the target area is determined.

2. The method of claim 1, wherein, The step of determining whether a precipitation event exists in the target area based on the brightness temperature data of the plurality of frequency polarization channels and the brightness temperature data of the infrared channel includes: Based on the brightness temperature data of the aforementioned frequency polarization channels and infrared channel, the precipitation in the target area is estimated, and the estimated precipitation value of the target area is obtained. When the estimated precipitation reaches a preset threshold, it is determined that a precipitation event exists in the target area.

3. The method of claim 2, wherein, The step of estimating the precipitation in the target area based on the brightness temperature data of the plurality of frequency polarization channels and the brightness temperature data of the infrared channel, and obtaining the estimated precipitation value of the target area, includes: Based on a preset precipitation prediction model, the precipitation in the target area is predicted according to the brightness temperature data of the several frequency polarization channels and the brightness temperature data of the infrared channel, so as to obtain the precipitation prediction value of the target area.

4. The method of claim 1, wherein, The polar-orbiting satellite and the geostationary orbit satellite are respectively the FY3-D satellite and the GOES satellite. The acquisition of brightness temperature data for several frequency polarization channels and infrared channels of the target area based on the polar-orbiting satellite and the geostationary orbit satellite includes: Based on the FY3-D satellite, brightness temperature data of several frequency polarization channels in the target area are obtained; wherein, the brightness temperature data of several frequency polarization channels includes brightness temperature data of polarization channels of the FY3-D satellite in the frequencies of 10.65 GHz, 18.7 GHz, 23.8 GHz, 36.5 GHz and 89 GHz. Based on the GOES satellite, infrared channel brightness temperature data of the target area is acquired; wherein, the infrared channel brightness temperature data includes the brightness temperature data of the GOES satellite in the 10.8μm channel, and the water vapor channel brightness temperature data is the brightness temperature data of the GOES satellite in the 6.7μm channel.

5. The method of claim 4, wherein, When it is determined that a precipitation event exists in the target area, the process of selecting target frequency polarization channel brightness temperature data from the plurality of frequency polarization channel brightness temperature data based on the land-sea classification results of the target area includes: If a precipitation event is confirmed in the target area, and the land-sea classification result of the target area indicates that the target area is an ocean area, the polarization channel brightness temperature data of the FY3-D satellite in the frequencies of 23.8 GHz, 36.5 GHz and 89 GHz will be determined as the target polarization channel brightness temperature data. If the sea-land classification result of the target region represents that the target region is a land region, the polarized channel brightness temperature data of the FY3-D satellite at 18.7 GHz, 23.8 GHz and 36.5 GHz frequencies is determined as the target polarized channel brightness temperature data.

6. The method of claim 5, wherein, The determination of the precipitation prediction result of the target region according to the target frequency polarized channel brightness temperature data and the infrared channel brightness temperature data comprises: When the sea-land classification result of the target region represents that the target region is a sea region, the precipitation prediction result of the target region is determined according to the polarized brightness temperature data and the infrared channel brightness temperature data of the FY3-D satellite at 23.8 GHz, 36.5 GHz and 89 GHz frequencies based on a preset sea precipitation prediction model; When the sea-land classification result of the target region represents that the target region is a land region, the precipitation prediction result of the target region is determined according to the polarized channel brightness temperature data and the infrared channel brightness temperature data of the FY3-D satellite at 18.7 GHz, 23.8 GHz and 36.5 GHz frequencies based on a preset land precipitation prediction model.

7. The method of claim 4, wherein, Further comprising: determining a rainfall prediction range according to the scanning footprints of the FY3-D satellite and the GOES satellite; dividing a plurality of rainfall prediction grid points in the rainfall prediction range, and determining a target rainfall prediction grid point corresponding to the target region; wherein each of the rainfall prediction grid points is provided with a sea-land mark; determining the sea-land classification result of the target region according to the sea-land mark of the target rainfall prediction grid point.

8. A precipitation prediction device characterized by comprising: Comprise: an acquisition module configured to acquire a plurality of frequency polarized channel brightness temperature data and infrared channel brightness temperature data of a target region based on a polar orbit satellite and a geosynchronous orbit satellite, wherein the infrared channel brightness temperature data comprises water vapor channel brightness temperature data; a judgment module configured to determine whether a precipitation event exists in the target region according to the plurality of frequency polarized channel brightness temperature data and the infrared channel brightness temperature data; a screening module configured to screen target frequency polarized channel brightness temperature data from the plurality of frequency polarized channel brightness temperature data according to a sea-land classification result of the target region in a case where it is determined that the target region has a precipitation event; a prediction module configured to determine a precipitation prediction result of the target region according to the target frequency polarized channel brightness temperature data and the infrared channel brightness temperature data.

9. An electronic device, comprising: Comprise: at least one processor and a memory; the memory stores computer execution instructions; the at least one processor executes the computer execution instructions stored in the memory, so that the at least one processor executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer execution instructions, and when the processor executes the computer execution instructions, the method according to any one of claims 1 to 7 is realized.

Images