Stationary meteorological satellite rainfall intensity estimation method and related equipment

Abstract

The invention belongs to the technical field of rainfall prediction, and relates to a static meteorological satellite rainfall intensity estimation method and related equipment, and the method comprises the steps: firstly, carrying out the preprocessing of the infrared channel information of a FY-4 B star and a dual-frequency rain measurement radar product, and carrying out the time-space matching of the two parts due to the temporal-spatial resolution of the two parts; secondly, establishing a rainfall detection model based on an Attention-Unet model by introducing auxiliary information such as latitude and longitude, elevation and the like, and predicting whether rainfall exists in each pixel point or not; then, extracting space structure information of the rainfall cloud cluster according to the pixel points with rain; and finally, introducing the infrared channel information, the latitude and longitude information, the elevation data and the spatial structure information of the rain cluster into an Attention-Unet model, and constructing a rainfall intensity estimation model based on the spatial structure of the rain cluster to carry out rainfall estimation. According to the invention, the rainfall area extraction capability can be enhanced; meanwhile, the capability of capturing rainfall details is enhanced, and the model efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of rainfall prediction, which is applicable to the agricultural or electric power fields, and in particular to a method for estimating rainfall intensity via a geostationary meteorological satellite and related equipment. Background Art

[0002] Precipitation is the most important driver of the terrestrial hydrological cycle and the main factor in the uncertainty of hydrological flux and state prediction. Therefore, accurate rainfall observation is crucial for water level prediction, flood forecasting, drought monitoring, and water resources management. Traditional rainfall observation is mainly based on ground-based observation, and the data obtained have problems such as low temporal and spatial resolution. Among them, ground-based rainfall measurement has extremely high measurement accuracy at the point scale, but due to the sparse distribution of stations and high network density, it cannot accurately reflect rainfall at the surface scale. Ground-based radar observations can provide the temporal and spatial distribution of rainfall within a radius of 300 kilometers, but its coverage cannot be extended to the global scale, especially in the ocean, polar regions, mountainous areas and undeveloped areas. Compared with ground-based observations, satellite observations make up for these shortcomings to a certain extent by providing high-temporal and spatial resolution image information with uniform global coverage, especially in uninhabited areas, sea areas and other areas where ground-based observations are lacking.

[0003] The new generation of geostationary meteorological satellites are equipped with visible light, infrared and water vapor sensors, with high temporal and spatial resolution, and can provide infrared information on various types of clouds and rainfall activities, and can well capture rapidly changing weather phenomena in a short period of time. However, when using infrared spectrum to obtain cloud information, satellites can only detect the top information of the cloud, and cannot penetrate the cloud itself, causing the cloud to become a "black body". It can be seen that the accuracy of traditional rainfall observations based on geostationary meteorological satellites is low.

[0004] As a classic convolutional neural network structure, Unet is widely used in the field of image segmentation for its efficient feature extraction and multi-scale representation capabilities in rainfall intensity estimation tasks. However, its structural design is relatively simple, mainly based on an interlaced upsampling and downsampling process, which leads to certain limitations in processing complex textures and details. Specifically, the resolution bottleneck of Unet limits its performance in capturing small rainfall features, and the compression of the encoder module may cause edge information to be gradually lost during the decoding process, thereby affecting the accuracy of the prediction. Summary of the invention

[0005] The purpose of the embodiments of the present application is to propose a method for estimating rainfall intensity using a geostationary meteorological satellite and related equipment to solve the problem of low accuracy of traditional rainfall observations based on geostationary meteorological satellites.

[0006] In order to solve the above technical problems, the embodiment of the present application provides a method for estimating rainfall intensity from a geostationary meteorological satellite, which adopts the following technical solution: Obtaining geostationary satellite observation data, dual-frequency rainfall radar products, and elevation data of the target area, and preprocessing the geostationary satellite observation data to obtain infrared brightness temperature data; the target area is the geostationary satellite full disk area; The time and space resolutions of the infrared brightness temperature data and the dual-frequency rainfall radar product are unified by using time and space matching technology; The infrared brightness temperature data, the longitude and latitude information, and the elevation data are input into a rainfall detection model to detect whether rainfall has occurred, and a rainfall detection result of whether rainfall has occurred at a pixel point is obtained, wherein the rainfall detection model is an Attention-Unet model; According to the rainfall detection result, a spatial structure information extraction operation is performed on the pixel points where rain is determined to occur, so as to obtain the spatial structure information of the rainfall cloud; Inputting the infrared brightness temperature data, the longitude and latitude information, the elevation data and the spatial structure information of the rainfall cloud into a rainfall intensity estimation model to perform a rainfall intensity estimation operation to obtain a rainfall prediction result, wherein the rainfall intensity estimation model is an Attention-Unet model; The rainfall prediction result is outputted.

[0007] Furthermore, the preprocessing of the geostationary satellite observation data includes: Perform radiation calibration on geostationary satellites to convert the DN value of the infrared channel of geostationary satellites into meaningful radiation brightness temperature values; The nominal projection of the geostationary satellite is converted into vector data through the latitude and longitude lookup correction method to obtain the infrared brightness temperature data.

[0008] Furthermore, the time and space resolutions of the geostationary satellite infrared brightness temperature image and the dual-frequency rainfall radar product obtained above are unified by using the time and space matching technology, including: According to the scanning time of the global rainfall radar, the infrared brightness temperature data of the geostationary satellite is time-matched with the dual-frequency rainfall radar products in the same time range; The infrared brightness temperature data from the geostationary satellite and the dual-frequency rainfall radar products are linearly interpolated onto a 0.05°*0.05° grid to achieve spatial matching.

[0009] Furthermore, after the step of inputting the infrared brightness temperature data, longitude and latitude information, and elevation data into the rainfall detection model to detect whether rainfall has occurred and obtaining the detection result of whether rainfall has occurred at the pixel point, the following steps are also included: The rainfall detection result is evaluated according to the hit rate index POD, the false alarm rate index FAR and the critical success index CSI to obtain the rainfall detection capability evaluation result of the rainfall detection model.

[0010] Furthermore, the hit rate indicator It is expressed as: The false alarm rate indicator It is expressed as: The key success index It is expressed as: in, Indicates that both the predicted data and the observed data are positive; Indicates that the predicted data is negative and the observed data is positive; Indicates that the predicted data is positive and the observed data is negative.

[0011] Furthermore, after the step of inputting the infrared brightness temperature data, the longitude and latitude information, the elevation data and the spatial structure information of the rainfall cloud into the rainfall intensity estimation model to perform a rainfall intensity estimation operation to obtain a rainfall prediction result, the following steps are also included: The rainfall prediction result is evaluated according to the root mean square error and the correlation coefficient to obtain the rainfall prediction ability evaluation result of the rainfall intensity estimation model, wherein the root mean square error It is expressed as: in, Indicates The actual rainfall amount at each pixel, Indicates The predicted rainfall at each pixel, N represents the number of pixels; The correlation coefficient It is expressed as: in, Indicates The actual rainfall amount at each pixel, Indicates The predicted rainfall at each pixel, represents the average value of the actual rainfall, represents the average value of the predicted rainfall, represents the standard deviation of the predicted rainfall, represents the standard deviation of the actual rainfall, and N represents the number of pixels.

[0012] In order to solve the above technical problems, the embodiment of the present application further provides a device for estimating rainfall intensity of a geostationary meteorological satellite, which adopts the following technical solution: A data acquisition module is used to acquire geostationary satellite observation data, dual-frequency rainfall radar products, and elevation data of the target area, and pre-process the geostationary satellite observation data to obtain infrared brightness temperature data; the target area is the geostationary satellite full disk area; A data matching module, used to unify the time resolution and spatial resolution of the infrared brightness temperature data and the dual-frequency rainfall radar product by using a time-space matching technology; A rainfall detection module is used to input the infrared brightness temperature data, longitude and latitude information, and elevation data into a rainfall detection model to detect whether rainfall has occurred, and obtain a rainfall detection result of whether rainfall has occurred at a pixel point, wherein the rainfall detection model is an Attention-Unet model; A rainfall cloud spatial structure information extraction module is used to perform a spatial structure information extraction operation on the pixel points determined to have rain according to the rainfall detection result to obtain the spatial structure information of the rainfall cloud; A rainfall intensity estimation module, used for inputting the infrared brightness temperature data, the longitude and latitude information, the elevation data and the spatial structure information of the rainfall cloud into a rainfall intensity estimation model to perform a rainfall intensity estimation operation to obtain a rainfall prediction result, wherein the rainfall intensity estimation model is an Attention-Unet model; The result output module is used to output the rainfall prediction result.

[0013] Furthermore, the data acquisition module includes: The radiation calibration submodule is used to perform radiation calibration operations on geostationary satellites and convert the DN value of the infrared channel of the geostationary satellite into a meaningful radiation brightness temperature value; The projection transformation submodule is used to transform the nominal projection of the geostationary satellite into vector data through the latitude and longitude lookup correction method to obtain the infrared brightness temperature data.

[0014] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution: The invention comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the above-mentioned method for estimating rainfall intensity by a geostationary meteorological satellite when executing the computer-readable instructions.

[0015] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps of the method for estimating rainfall intensity by a geostationary meteorological satellite are implemented as described above.

[0016] The present application provides a method for estimating rainfall intensity of a geostationary meteorological satellite, comprising: obtaining geostationary satellite observation data, dual-frequency rain measuring radar products, and elevation data of a target area, and preprocessing the geostationary satellite observation data to obtain infrared brightness temperature data; the target area is the full disk area of ​​the geostationary satellite; using time-space matching technology to unify the time resolution and spatial resolution of the infrared brightness temperature data and the dual-frequency rain measuring radar product; inputting the infrared brightness temperature data, longitude and latitude information, and the elevation data into a rainfall detection model to detect whether rainfall has occurred, and obtaining a rainfall detection result of whether rainfall has occurred on a pixel point, wherein the rainfall detection model is an Attention-Unet model; performing a spatial structure information extraction operation on a pixel point determined to have rain according to the rainfall detection result, and obtaining spatial structure information of a rainfall cloud group; inputting the infrared brightness temperature data, the longitude and latitude information, the elevation data, and the spatial structure information of the rainfall cloud group into a rainfall intensity estimation model to perform a rainfall intensity estimation operation, and obtaining a rainfall prediction result, wherein the rainfall intensity estimation model is an Attention-Unet model; and outputting the rainfall prediction result. Compared with the existing technology, this application constructs the spatial structure information of rain clusters and effectively introduces the physical characteristics related to rainfall intensity into the deep learning model. By combining physical information with the deep learning model, it strengthens the ability to capture fine rainfall while enhancing the ability to predict rainfall areas, thereby improving the accuracy and physical interpretability of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 is an exemplary system architecture diagram to which the present application may be applied; Figure 2 is a flow chart for implementing a method for estimating rainfall intensity using a geostationary meteorological satellite provided in an embodiment of the present application; Figure 3 It is a near-surface rainfall rate map of a dual-frequency rain measuring radar product and an infrared brightness temperature map of the Fengyun-4B satellite obtained by applying the time-space matching method provided in an embodiment of the present application; Figure 4 It is a schematic diagram of the structure of the Attention-Unet network provided in an embodiment of the present application; Figure 5 A spatial structure information diagram of a rainfall cloud map provided in an embodiment of the present application; Figure 6It is a structural schematic diagram of a device for estimating rainfall intensity of a geostationary meteorological satellite provided in an embodiment of the present application; Figure 7 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0020] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0021] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0022] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0023] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0024] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to the laptop computer 1011, the tablet computer 1012 or the mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0025] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0026] It should be noted that the geostationary meteorological satellite rainfall intensity estimation method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the geostationary meteorological satellite rainfall intensity estimation device is generally arranged in the server / terminal device.

[0027] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0028] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for estimating rainfall intensity by a geostationary meteorological satellite according to the present application. The method for estimating rainfall intensity by a geostationary meteorological satellite comprises: step S201, step S202, step S203, step S204, step S205 and step S206.

[0029] In step S201, geostationary satellite observation data, dual-frequency rainfall radar products, and elevation data of the target area are obtained, and the geostationary satellite observation data are preprocessed to obtain infrared brightness temperature data.

[0030] In an embodiment of the present application, data of a specific area and time are obtained, including observation data of the FY-4B orbital radiation imager, dual-frequency rain measuring radar products, and elevation data.

[0031] In the embodiment of the present application, the Advanced Geostationary Radiation Imager (AGRI) is one of the main payloads of the Fengyun-4B satellite, with a total of 15 observation channels, including 3 visible light channels, 4 near-infrared channels, and 8 infrared channels. The spatial resolution is 4km, and the minimum can reach 0.5~2km.

[0032] In the embodiment of the present application, the dual-frequency rainfall radar product is a second-generation satellite-borne rainfall radar carried by the Global Precipitation Measurement Satellite (GPM), which is a dual-frequency rainfall radar that combines the 13.6 GHz Ku-band radar (KuPR) and the 35.5 GHz Ka-band radar (KaPR). The data has a scanning width of 245km each time, a detection height of 22km from the surface, a horizontal resolution of about 5km, and a vertical resolution of about 250m.

[0033] In this embodiment of the present application, the elevation data is data provided by the National Earth System Science Data Center covering the entire world in 2023, including land elevation and ocean depth.

[0034] In an embodiment of the present application, the preprocessing of the geostationary satellite observation data includes: performing a radiation calibration operation on the geostationary satellite to convert the DN value of the infrared channel into a radiation brightness value; and converting the nominal projection of the geostationary satellite into vector data through a longitude and latitude lookup correction method, that is, converting the row and column numbers of the observation data into longitude and latitude.

[0035] In the embodiment of the present application, the target area is the entire disk area of ​​the geostationary satellite.

[0036] In step S202, the temporal resolution and spatial resolution of the infrared brightness temperature data and the dual-frequency rainfall radar product are unified using the time-space matching technology; In the embodiment of the present application, the observation image of the FY-4B satellite is time-matched with the dual-frequency rain radar product of the global rain radar in the same time range according to the scanning time of the global rain radar. According to the result of time matching, the longitude and latitude range of the target area is determined, and the infrared brightness temperature data of the FY-4B satellite and the dual-frequency rain radar product are linearly interpolated to a grid of 0.05°*0.05° to achieve spatial matching. The matching result example is shown in the figure below. Figure 3 shown.

[0037] In step S203, the infrared brightness temperature data, longitude and latitude information, and elevation data are input into a rainfall detection model to detect whether rainfall has occurred, and a rainfall detection result of whether rainfall has occurred at a pixel point is obtained, wherein the rainfall detection model is an Attention-Unet model.

[0038] In the embodiment of the present application, the Attention-Unet model effectively enhances the model's attention to the rainfall area by introducing the attention gate mechanism, significantly improves the ability to extract detailed features, and improves the prediction speed of the model. Based on the Unet network, an attention submodule is added to each decoder layer. This submodule uses the attention gate network to automatically model the foreground and background, and calculates the weights that should be assigned to pixels at different positions, so that the model can focus more on and pay attention to the rainfall area, while keenly capturing detailed information such as the edge of the cloud and the distribution of small rainfall. Specific details are as follows Figure 4 As shown, the encoder downsamples the feature map of the same layer , size is ,go through After convolution, we get , the feature map of the previous layer in upsampling is , size is ,go through After convolution, we get ,Will and After adding, the ReLU activation function is processed to obtain , and then after After convolution calculation, we get , and finally After sigmoid activation processing, the final attention score can be obtained .Will and The calculated attention coefficient is again Multiply them together to get .

[0039] In step S204, a spatial structure information extraction operation is performed on the pixel points determined to have rain according to the rainfall detection result to obtain the spatial structure information of the rainfall cloud.

[0040] In the embodiment of the present application, the spatial structure information of the rain cluster is constructed, and the spatial structure information of the pixel points determined to have rain can be extracted according to the result of rainfall detection, thereby improving the ability to estimate the rainfall intensity.

[0041] In the embodiment of the present application, the spatial structure information extraction operation is based on the results of rainfall detection, combined with the infrared brightness temperature change conditions to determine the occurrence intensity mechanism of the rainfall cloud, extract information including the center position of the rainfall cloud (the minimum value of the infrared brightness temperature in the 10.8μm band), the distance from the rain pixel to the cloud boundary, the distance from the rain pixel to the cloud center, and the change direction of the rainfall cloud, to fully describe the internal spatial structure of the rain cluster and the possible rainfall intensity. The specific spatial structure information diagram of the rainfall cloud map is as follows: Figure 5 shown.

[0042] In step S205, the infrared brightness temperature data, longitude and latitude information, elevation data and spatial structure information of rainfall clouds are input into a rainfall intensity estimation model to perform a rainfall intensity estimation operation to obtain a rainfall prediction result, wherein the rainfall intensity estimation model is an Attention-Unet model.

[0043] In the embodiment of the present application, the occurrence of rainfall is not only related to terrain conditions and cloud microphysical parameters, but the spatial structure of rainfall clouds not only affects the distribution of rainfall, but also reveals the physical process of rainfall and its spatiotemporal characteristics. In order to comprehensively consider the impact of multiple factors on the occurrence of rainfall, by introducing infrared brightness temperature data, longitude and latitude information, elevation data, and spatial structure information of rain clusters into the Attention-Unet model, a rainfall intensity estimation model based on the spatial structure of rain clusters is constructed to estimate rainfall intensity. This model takes into account the new idea of ​​integrating rainfall events and rainfall, constructs rainfall estimation supported by the spatial structure of rainfall clouds, enhances the ability to extract rainfall areas, and enhances the interpretability of the model to a certain extent; at the same time, by introducing an attention mechanism module based on the Unet model, the model's attention to highly relevant features of rainfall is improved, which complements the boundaries of rainfall clouds well, enhances the ability to capture rainfall details, and improves model efficiency.

[0044] In step S206, the rainfall prediction result is output.

[0045] In an embodiment of the present application, the observation data of the FY-4B satellite is first preprocessed, and the infrared brightness temperature data of the FY-4B satellite is spatiotemporally matched with the dual-frequency rain measuring radar product by using the spatiotemporal matching technology to construct a sample data set; secondly, an Attention-Unet model is constructed by introducing an attention mechanism module, and auxiliary information such as infrared brightness temperature data, longitude and latitude information, and elevation data are introduced into the model to construct a rainfall detection model; then, according to the rainfall detection results, the spatial structure information of rainfall clouds is extracted based on rainy pixels; finally, the infrared brightness temperature data, longitude and latitude information, elevation data and spatial structure information of rainfall clouds of the FY satellite are input into the Attention-Unet network to construct a rainfall intensity estimation model to achieve accurate estimation of rainfall intensity.

[0046] In an embodiment of the present application, a method for estimating rainfall intensity from a geostationary meteorological satellite is provided, including: acquiring geostationary satellite observation data, dual-frequency rain measuring radar products, and elevation data of a target area, and preprocessing the geostationary satellite observation data to obtain infrared brightness temperature data; unifying the temporal resolution and spatial resolution of the infrared brightness temperature data and the dual-frequency rain measuring radar products using a time-space matching technique; inputting the infrared brightness temperature data, longitude and latitude information, and elevation data into a rainfall detection model to detect whether rainfall has occurred, and obtaining a rainfall detection result of whether rainfall has occurred at a pixel point, wherein the rainfall detection model is an Attention-Unet model; performing a spatial structure information extraction operation on a pixel point determined to have rain according to the rainfall detection result, and obtaining spatial structure information of a rainfall cloud group; inputting the infrared brightness temperature data, longitude and latitude information, elevation data, and spatial structure information of a rainfall cloud group into a rainfall intensity estimation model to perform a rainfall intensity estimation operation, and obtaining a rainfall prediction result, wherein the rainfall intensity estimation model is an Attention-Unet model; and outputting the rainfall prediction result. Compared with the existing technology, this application constructs the spatial structure information of rain clusters and effectively introduces the physical characteristics related to rainfall intensity into the deep learning model. By combining physical information with the deep learning model, it strengthens the ability to capture fine rainfall while enhancing the ability to predict rainfall areas, thereby improving the accuracy and physical interpretability of the model.

[0047] In some optional implementations of the embodiments of the present application, the above-mentioned preprocessing of the geostationary satellite observation data includes: Perform radiation calibration on geostationary satellites to convert the DN value of the infrared channel of geostationary satellites into meaningful radiation brightness temperature values; Through the latitude and longitude correction method, the nominal projection of the geostationary satellite is converted into vector data to obtain infrared brightness temperature data.

[0048] In some optional implementations of the embodiments of the present application, the time resolution and spatial resolution of the geostationary satellite infrared brightness temperature image and the dual-frequency rainfall radar product obtained above are unified by using the time-space matching technology, including: According to the scanning time of the global rainfall radar, the infrared brightness temperature data of the geostationary satellite is time-matched with the dual-frequency rainfall radar products in the same time range; The infrared brightness temperature data from the geostationary satellite and the dual-frequency rainfall radar products are linearly interpolated onto a 0.05°*0.05° grid to achieve spatial matching.

[0049] In some optional implementations of the embodiments of the present application, after inputting the infrared brightness temperature data, the latitude and longitude information, and the elevation data into the rainfall detection model to perform a rainfall detection operation and obtaining a rainfall detection result of whether rainfall has occurred at the pixel point, the following steps are also included: The rainfall detection results are evaluated according to the hit rate index POD, the false alarm rate index FAR and the key success index CSI to obtain the rainfall detection ability evaluation result of the rainfall detection model.

[0050] In some optional implementations of the embodiments of the present application, the above hit rate indicator It is expressed as: False Positive Rate Indicator It is expressed as: Success rate indicators It is expressed as: in, Indicates that both the predicted data and the observed data are positive; Indicates that the predicted data is negative and the observed data is positive; Indicates that the predicted data is positive and the observed data is negative.

[0051] In the embodiment of the present application, the time-space matching technology refers to the time-space matching of the observation image of Fengyun-4B with the dual-frequency rain-measuring radar product carried by the global rain-measuring satellite. Fengyun-4B realizes a full disk scan every 15 minutes, and the global rain-measuring satellite realizes a polar orbit scanning observation of the earth approximately every 92.6 minutes. The start time and the number of scanning lines of the global rain-measuring satellite scan can be roughly inferred from the time range of the global rain-measuring satellite passing over Fengyun-4B, thereby realizing the time matching of the observation image of Fengyun-4B with the dual-frequency rain-measuring radar product. According to the results of time matching, the longitude and latitude range of the target area is determined, and the infrared brightness temperature data of Fengyun-4B and the dual-frequency rain-measuring radar product are linearly interpolated to a grid of 0.05°*0.05° to achieve spatial matching.

[0052] In the embodiment of the present application, the present invention uses three scoring indexes to evaluate the rainfall detection capability, namely, Probability of Detection (POD), False Alarm Ratio (FAR) and Critical Success Index (CSI), and their optimal values ​​are 1, 0, and 1, respectively. These indicators are calculated based on the binary confusion matrix, as shown in Table 1. The calculation formula is as follows: Predicted as positive class Predicted as negative class Observation is positive True Positive (TP) False Negative (FN) Observation is negative False Positive (FP) True Negative (TN) Table 1 Binary classification confusion matrix In some optional implementations of the embodiments of the present application, after the step of inputting the infrared brightness temperature data, the latitude and longitude information, the elevation data and the spatial structure information of the rainfall cloud into the rainfall intensity estimation model to perform the rainfall intensity estimation operation and obtain the rainfall prediction result, the following steps are also included: The rainfall prediction results were evaluated based on the root mean square error and correlation coefficient to obtain the rainfall prediction ability evaluation results of the rainfall intensity estimation model. It is expressed as: in, Indicates The actual rainfall amount at each pixel, Indicates The predicted rainfall at each pixel, N represents the number of pixels; The correlation coefficient CC is expressed as: in, Indicates The actual rainfall amount at each pixel, Indicates The predicted rainfall at each pixel, represents the average value of the actual rainfall, represents the average value of the predicted rainfall, represents the standard deviation of the predicted rainfall, represents the standard deviation of the actual rainfall, and N represents the number of pixels.

[0053] The root mean square error evaluates the error between the actual rainfall and the predicted rainfall. The value range is greater than 0. The smaller the value, the better the performance of the model. The correlation coefficient is used to reflect the correlation between the actual rainfall and the predicted rainfall. The value range is [-1, 1]. The larger the absolute value, the stronger the correlation.

[0054] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0055] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0056] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0057] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0058] Further references Figure 6 , as a response to the above Figure 2 The present application provides an embodiment of a device for estimating rainfall intensity of a geostationary meteorological satellite. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0059] like Figure 6 As shown, the geostationary meteorological satellite rainfall intensity estimation device 200 of the embodiment of the present application includes: The data acquisition module 210 is used to acquire geostationary satellite observation data, dual-frequency rainfall radar products, and elevation data of the target area, and pre-process the geostationary satellite observation data to obtain infrared brightness temperature data; The data matching module 220 is used to unify the time resolution and spatial resolution of the infrared brightness temperature data and the dual-frequency rainfall radar product by using the time-space matching technology; The rainfall detection module 230 is used to input the infrared brightness temperature data, longitude and latitude information, and elevation data into the rainfall detection model to detect whether rainfall has occurred, and obtain a rainfall detection result of whether rainfall has occurred at the pixel point, wherein the rainfall detection model is an Attention-Unet model; A rainfall cloud spatial structure information extraction module 240 is used to extract spatial structure information of pixels determined to have rain according to the rainfall detection result, so as to obtain spatial structure information of the rainfall cloud; The rainfall intensity estimation module 250 is used to input infrared brightness temperature data, longitude and latitude information, elevation data and spatial structure information of rainfall clouds into a rainfall intensity estimation model to perform a rainfall intensity estimation operation to obtain a rainfall prediction result, wherein the rainfall intensity estimation model is an Attention-Unet model; The result output module 260 is used to output the rainfall prediction result.

[0060] In an embodiment of the present application, a geostationary meteorological satellite rainfall intensity estimation device 200 is provided, including: a data acquisition module 210, which is used to acquire geostationary satellite observation data, dual-frequency rainfall radar products, and elevation data of a target area, and pre-process the geostationary satellite observation data to obtain infrared brightness temperature data; a data matching module 220, which is used to unify the time resolution and spatial resolution of the infrared brightness temperature data and the dual-frequency rainfall radar products by using time-space matching technology; a rainfall detection module 230, which is used to input the infrared brightness temperature data, longitude and latitude information, and elevation data into a rainfall detection model to detect whether rainfall has occurred, and obtain a rainfall detection model of whether rainfall has occurred at a pixel point. Results, wherein the rainfall detection model is the Attention-Unet model; the rainfall cloud spatial structure information extraction module 240 is used to perform spatial structure information extraction operations on the pixels determined to have rain according to the rainfall detection results to obtain the spatial structure information of the rainfall cloud; the rainfall intensity estimation module 250 is used to input the infrared brightness temperature data, longitude and latitude information, elevation data and the spatial structure information of the rainfall cloud into the rainfall intensity estimation model to perform rainfall intensity estimation operations to obtain the rainfall prediction results, wherein the rainfall intensity estimation model is the Attention-Unet model; the result output module 260 is used to output the rainfall prediction results. Compared with the prior art, the present application constructs the spatial structure information of the rain cluster, effectively introduces the physical characteristics related to the intensity of rainfall into the deep learning model, and by combining physical information with the deep learning model, while strengthening the ability to capture fine rainfall, it also strengthens the ability to predict the rainfall area, thereby improving the accuracy and physical interpretability of the model.

[0061] In some optional implementations of the embodiments of the present application, the data acquisition module 210 includes: The radiation calibration submodule is used to perform radiation calibration operations on geostationary satellites and convert the DN value of the infrared channel of the geostationary satellite into a meaningful radiation brightness temperature value; The projection transformation submodule is used to transform the nominal projection of the geostationary satellite into vector data through the latitude and longitude lookup correction method to obtain infrared brightness temperature data.

[0062] In some optional implementations of the embodiments of the present application, the data matching module 220 includes: The time matching submodule is used to time match the infrared brightness temperature data of the geostationary satellite with the dual-frequency rainfall radar products in the same time range according to the scanning time of the global rainfall radar; The spatial matching submodule is used to linearly interpolate the infrared brightness temperature data of the geostationary satellite and the dual-frequency rainfall radar products to a 0.05°*0.05° grid to achieve spatial matching.

[0063] In some optional implementations of the embodiments of the present application, the above-mentioned geostationary meteorological satellite rainfall intensity estimation device 200 further includes: The rainfall detection capability evaluation module is used to perform rainfall detection capability evaluation operations on the rainfall detection results according to the hit rate index POD, the false alarm rate index FAR and the key success index CSI to obtain the rainfall detection capability evaluation results of the rainfall detection model. Among them, the hit rate index POD is expressed as: The false alarm rate index FAR is expressed as: The critical success index CSI is expressed as: in, Indicates that both the predicted data and the observed data are positive; Indicates that the predicted data is negative and the observed data is positive; Indicates that the predicted data is positive and the observed data is negative.

[0064] In some optional implementations of the embodiments of the present application, the above-mentioned geostationary meteorological satellite rainfall intensity estimation device 200 further includes: The rainfall intensity prediction capability evaluation module is used to perform rainfall prediction capability evaluation operations on the rainfall prediction results according to the root mean square error and the correlation coefficient, and obtain the rainfall prediction capability evaluation results of the rainfall intensity estimation model. It is expressed as: in, Indicates The actual rainfall amount at each pixel, Indicates The predicted rainfall at each pixel, N represents the number of pixels; Correlation coefficient It is expressed as: in, Indicates The actual rainfall amount at each pixel, Indicates The predicted rainfall at each pixel, represents the average value of the actual rainfall, represents the average value of the predicted rainfall, represents the standard deviation of the predicted rainfall, represents the standard deviation of the actual rainfall, and N represents the number of pixels.

[0065] To solve the above technical problems, the present application also provides a computer device. Figure 7 , Figure 7 This is a basic structural block diagram of a computer device according to an embodiment of the present application.

[0066] The computer device 300 includes a memory 310, a processor 320, and a network interface 330 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 300 having components 310-330, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0067] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0068] The memory 310 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 310 can be an internal storage unit of the computer device 300, such as a hard disk or memory of the computer device 300. In other embodiments, the memory 310 can also be an external storage device of the computer device 300, such as a plug-in hard disk equipped on the computer device 300, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card, etc. Of course, the memory 310 can also include both the internal storage unit of the computer device 300 and its external storage device. In the embodiment of the present application, the memory 310 is generally used to store the operating system and various application software installed on the computer device 300, such as computer-readable instructions of the method for estimating rainfall intensity by a geostationary meteorological satellite. In addition, the memory 310 can also be used to temporarily store various data that have been output or are to be output.

[0069] The processor 320 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 320 is generally used to control the overall operation of the computer device 300. In the embodiment of the present application, the processor 320 is used to run the computer-readable instructions stored in the memory 310 or process data, such as computer-readable instructions for running the geostationary meteorological satellite rainfall intensity estimation method.

[0070] The network interface 330 may include a wireless network interface or a wired network interface. The network interface 330 is generally used to establish a communication connection between the computer device 300 and other electronic devices.

[0071] The computer device provided by this application constructs the spatial structure information of rain clusters, effectively introduces the physical characteristics related to the intensity of rainfall into the deep learning model, and by combining physical information with the deep learning model, while strengthening the ability to capture fine rainfall, it also strengthens the ability to predict the rainfall area, thereby improving the accuracy and physical interpretability of the model.

[0072] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the above-mentioned geostationary meteorological satellite rainfall intensity estimation method.

[0073] The computer-readable storage medium provided by the present application constructs the spatial structure information of rain clusters to effectively introduce the physical characteristics related to the intensity of rainfall into the deep learning model. By combining the physical information with the deep learning model, the ability to capture fine rainfall is enhanced while the ability to predict the rainfall area is enhanced, thereby improving the accuracy and physical interpretability of the model.

[0074] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0075] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for estimating rainfall intensity from a geostationary meteorological satellite, characterized in that: The steps include: Obtaining geostationary satellite observation data, dual-frequency rainfall radar products, and elevation data of the target area, and preprocessing the geostationary satellite observation data to obtain infrared brightness temperature data; the target area is the geostationary satellite full disk area; The time and space resolutions of the infrared brightness temperature data and the dual-frequency rainfall radar product are unified by using time and space matching technology; The infrared brightness temperature data, the longitude and latitude information, and the elevation data are input into a rainfall detection model to detect whether rainfall has occurred, and a rainfall detection result of whether rainfall has occurred at a pixel point is obtained, wherein the rainfall detection model is an Attention-Unet model; According to the rainfall detection result, a spatial structure information extraction operation is performed on the pixel points where rain is determined to occur, so as to obtain the spatial structure information of the rainfall cloud; Inputting the infrared brightness temperature data, the longitude and latitude information, the elevation data and the spatial structure information of the rainfall cloud into a rainfall intensity estimation model to perform a rainfall intensity estimation operation to obtain a rainfall prediction result, wherein the rainfall intensity estimation model is an Attention-Unet model; The rainfall prediction result is outputted.

2. The method for estimating rainfall intensity from a geostationary meteorological satellite according to claim 1, characterized in that: The preprocessing of the geostationary satellite observation data includes: Perform radiation calibration on geostationary satellites to convert the DN value of the infrared channel of geostationary satellites into meaningful radiation brightness temperature values; The nominal projection of the geostationary satellite is converted into vector data through the latitude and longitude lookup correction method to obtain the infrared brightness temperature data.

3. The method for estimating rainfall intensity from a geostationary meteorological satellite according to claim 1, characterized in that: The time-space matching technology is used to unify the time resolution and spatial resolution of the geostationary satellite infrared brightness temperature image and the dual-frequency rainfall radar product obtained above, including: According to the scanning time of the global rainfall radar, the infrared brightness temperature data of the geostationary satellite is time-matched with the dual-frequency rainfall radar products in the same time range; The infrared brightness temperature data from the geostationary satellite and the dual-frequency rainfall radar products are linearly interpolated onto a 0.05°*0.05° grid to achieve spatial matching.

4. The method for estimating rainfall intensity from a geostationary meteorological satellite according to claim 1, characterized in that: After the step of inputting the infrared brightness temperature data, longitude and latitude information, and elevation data into the rainfall detection model to detect whether rainfall has occurred and obtaining a detection result of whether rainfall has occurred at a pixel point, the following steps are also included: The rainfall detection result is evaluated according to the hit rate index POD, the false alarm rate index FAR and the critical success index CSI to obtain the rainfall detection capability evaluation result of the rainfall detection model.

5. The method for estimating rainfall intensity using a geostationary meteorological satellite according to claim 4, characterized in that: The hit rate indicator It is expressed as: The false alarm rate indicator It is expressed as: The key success index It is expressed as: in, Indicates that both the predicted data and the observed data are positive; Indicates that the predicted data is negative and the observed data is positive; Indicates that the predicted data is positive and the observed data is negative.

6. The method for estimating rainfall intensity from a geostationary meteorological satellite according to claim 1, characterized in that: After the step of inputting the infrared brightness temperature data, the longitude and latitude information, the elevation data and the spatial structure information of the rainfall cloud into the rainfall intensity estimation model to perform a rainfall intensity estimation operation to obtain a rainfall estimation result, the following steps are also included: The rainfall estimation result is evaluated according to the root mean square error and the correlation coefficient to obtain the rainfall prediction ability evaluation result of the rainfall intensity estimation model, wherein the root mean square error It is expressed as: in, Indicates The actual rainfall amount at each pixel, Indicates The predicted rainfall at each pixel, Indicates the number of pixels; The correlation coefficient It is expressed as: in, Indicates The actual rainfall amount at each pixel, Indicates The predicted rainfall at each pixel, represents the average value of the actual rainfall, represents the average value of the predicted rainfall, represents the standard deviation of the predicted rainfall, represents the standard deviation of the actual rainfall, Indicates the number of pixels.

7. A device for estimating rainfall intensity from a geostationary meteorological satellite, characterized in that: include: A data acquisition module is used to acquire geostationary satellite observation data, dual-frequency rainfall radar products, and elevation data of the target area, and pre-process the geostationary satellite observation data to obtain infrared brightness temperature data; the target area is the geostationary satellite full disk area; A data matching module, used to unify the time resolution and spatial resolution of the infrared brightness temperature data and the dual-frequency rainfall radar product by using a time-space matching technology; A rainfall detection module is used to input the infrared brightness temperature data, longitude and latitude information, and elevation data into a rainfall detection model to detect whether rainfall has occurred, and obtain a rainfall detection result of whether rainfall has occurred at a pixel point, wherein the rainfall detection model is an Attention-Unet model; A rainfall cloud spatial structure information extraction module is used to perform a spatial structure information extraction operation on the pixel points determined to have rain according to the rainfall detection result to obtain the spatial structure information of the rainfall cloud; A rainfall intensity estimation module, used for inputting the infrared brightness temperature data, the longitude and latitude information, the elevation data and the spatial structure information of the rainfall cloud into a rainfall intensity estimation model to perform a rainfall intensity estimation operation to obtain a rainfall prediction result, wherein the rainfall intensity estimation model is an Attention-Unet model; The result output module is used to output the rainfall prediction result.

8. The device for estimating rainfall intensity of a geostationary meteorological satellite according to claim 7, characterized in that: The data acquisition module comprises: The radiation calibration submodule is used to perform radiation calibration operations on geostationary satellites and convert the DN value of the infrared channel of the geostationary satellite into a meaningful radiation brightness temperature value; The projection transformation submodule is used to transform the nominal projection of the geostationary satellite into vector data through the latitude and longitude lookup correction method to obtain the infrared brightness temperature data.

9. A computer device comprising a memory and a processor, characterized in that: The memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the method for estimating rainfall intensity of a geostationary meteorological satellite according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the method for estimating rainfall intensity by a geostationary meteorological satellite according to any one of claims 1 to 6 are implemented.

Images