Rainfall inversion method and device based on GNSS PWV-assisted meteorological satellite remote sensing

Abstract

The invention discloses a rainfall inversion method and device based on GNSS PWV-assisted meteorological satellite remote sensing. The method comprises the steps of obtaining PWV data, cloud top brightness temperature data and brightness temperature difference data in a rainfall period; and inputting the PWV data, the cloud top brightness temperature data and the brightness temperature difference data of the rainfall period into a trained multilayer neural network model, and outputting the rainfall of the corresponding period. According to the method, atmospheric water vapor content information (PWV data) calculated in real time by combining GNSS observation data is combined, the defect of satellite remote sensing in cloud bottom water vapor observation is overcome, the GNSS observation data and meteorological satellite data are fused, and the accuracy of precipitation inversion is improved. Meanwhile, a trained multilayer neural network model is introduced to automatically extract features in complex data, and high-time and high-precision rainfall inversion is realized.

Description

Technical Field

[0001] The invention relates to the field of rainfall inversion, and in particular to a method and a device for rainfall inversion using GNSS PWV-assisted meteorological satellite remote sensing. Background Art

[0002] There are three main methods of rainfall monitoring at present, including: (1) based on rain gauge observation; (2) based on ground weather radar inversion; (3) based on meteorological satellite inversion. Among them, the disadvantages of rain gauge observation are poor representativeness and limited observation range; the disadvantages of ground weather radar are small coverage, high cost, and large interference factors; the method of meteorological satellite inversion has the advantages of wide coverage and continuous observation, but the disadvantage is limited accuracy.

[0003] Meteorological satellites can obtain the brightness temperature information of rain clouds by observing the cloud layer, and can invert the rainfall amount through the cloud top brightness temperature and brightness temperature difference. However, water vapor is an important source of rainfall, and it is difficult to obtain information on atmospheric water vapor content due to the shortcoming that infrared channels cannot penetrate clouds. Summary of the invention

[0004] In order to overcome the deficiencies of the above-mentioned prior art, the present invention provides a GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion method and device, which calculates the atmospheric water vapor content (i.e., precipitable water volume PWV) based on GNSS, and assists satellite remote sensing methods to achieve high-precision real-time rainfall inversion.

[0005] According to one aspect of the present invention, a method for retrieving rainfall using GNSS PWV-assisted meteorological satellite remote sensing is provided, comprising: Obtain PWV data, cloud top brightness temperature data and brightness temperature difference data during the rainfall period; The PWV data, cloud top brightness temperature data and brightness temperature difference data of the rainfall period are input into the trained multi-layer neural network model, and the rainfall amount of the corresponding period is output; wherein the training of the multi-layer neural network model includes: Obtain long-term series of measured rainfall and multi-channel cloud top brightness temperature data, and calculate the brightness temperature difference between the infrared channel and the water vapor channel; Obtain GNSS observation data for the same period, and calculate atmospheric precipitable water (PWV) based on the GNSS observation data; A sample data set was constructed based on the measured rainfall, cloud top brightness temperature data, brightness temperature difference and atmospheric precipitable water volume (PWV). Constructing a multi-layer neural network model, wherein the input layer of the multi-layer neural network model is a PWV sequence, a brightness temperature image sequence, and a brightness temperature difference image sequence within a time window, and the output layer is the rainfall in the corresponding time period; The constructed multi-layer neural network model is trained using the sample data set to obtain a trained model.

[0006] As a further technical solution, a sample data set is constructed, including: According to the preset time window, the PWV sequence, brightness temperature image sequence, brightness temperature difference image sequence and rainfall sequence within the time window are obtained to obtain the sample data set.

[0007] As a further technical solution, the method further includes: A training set and a validation set are randomly selected from the sample data set, the training set is used to train the constructed multi-layer neural network model, and the validation set is used to validate the trained multi-layer neural network model.

[0008] As a further technical solution, the multi-layer neural network model is a back-propagation neural network model including three hidden layers.

[0009] According to one aspect of the present invention, a GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion device is provided, comprising: A data acquisition module is used to obtain PWV data, cloud top brightness temperature data and brightness temperature difference data during the rainfall period; The rainfall inversion module is used to input the PWV data, cloud top brightness temperature data and brightness temperature difference data of the rainfall period into the trained multi-layer neural network model, and output the rainfall of the corresponding period; wherein the training of the multi-layer neural network model includes: Obtain long-term series of measured rainfall and multi-channel cloud top brightness temperature data, and calculate the brightness temperature difference between the infrared channel and the water vapor channel; Obtain GNSS observation data for the same period, and calculate atmospheric precipitable water (PWV) based on the GNSS observation data; A sample data set was constructed based on the measured rainfall, cloud top brightness temperature data, brightness temperature difference and atmospheric precipitable water volume (PWV). Constructing a multi-layer neural network model, wherein the input layer of the multi-layer neural network model is a PWV sequence, a brightness temperature image sequence, and a brightness temperature difference image sequence within a time window, and the output layer is the rainfall in the corresponding time period; The constructed multi-layer neural network model is trained using the sample data set to obtain a trained model.

[0010] According to one aspect of the present invention, a computing device is provided, including a processor and a memory, wherein the memory stores program instructions executed by the processor, and the processor calls the program instructions to execute the steps of the GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion method.

[0011] According to one aspect of the present specification, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores computer instructions, wherein the computer instructions enable the computer to execute the steps of the GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion method.

[0012] According to one aspect of the present invention, a computer program product is provided, comprising computer program instructions, wherein the computer program instructions enable the computer to execute the steps of the GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion method.

[0013] Compared with the prior art, the present invention has the following beneficial effects: (1) The present invention combines the atmospheric water vapor content information that can be calculated in real time by GNSS, supplements the deficiency of satellite remote sensing in cloud base water vapor observation, and integrates GNSS with meteorological satellite data to improve the accuracy of precipitation inversion.

[0014] (2) By introducing deep learning technology, the present invention can automatically extract features from complex data, optimize the precipitation estimation process, and achieve real-time and high-precision rainfall inversion to meet the needs of rainfall monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief introduction is given below to the drawings used in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 A schematic flow chart of a method for GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion provided in an embodiment of the present invention.

[0017] Figure 2 A schematic diagram of the training process of a multi-layer neural network model provided in an embodiment of the present invention.

[0018] Figure 3 A schematic structural diagram of a GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In view of the problem that it is difficult to obtain atmospheric water vapor content when inverting rainfall based on meteorological satellites, resulting in limited accuracy of the inverted rainfall, the present invention designs a method for inverting rainfall using atmospheric water vapor content to assist meteorological satellite remote sensing data. By introducing GNSS to calculate atmospheric water vapor content (i.e., precipitable water volume PWV), the satellite remote sensing method is assisted to achieve high-precision real-time rainfall inversion.

[0020] It should be noted that unless otherwise specified, the technologies mentioned in the specification of the present invention are all well-known technologies.

[0021] The terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions, for example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to the steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0022] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. In addition, the technical features in the various embodiments or single embodiments provided by the present invention are arbitrarily combined with each other to form a new technical solution. This combination is not restricted by the sequence of steps and / or the structural composition mode, but must be based on the ability of ordinary technicians in this field to achieve. When the combination of technical solutions is contradictory or cannot be achieved, it should be considered that this combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0023] The embodiment of the present invention provides a GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion method, such as Figure 1 As shown, it includes: obtaining PWV data, cloud top brightness temperature data and brightness temperature difference data during the rainfall period; inputting the PWV data, cloud top brightness temperature data and brightness temperature difference data during the rainfall period into the trained multi-layer neural network model, and outputting the rainfall in the corresponding period.

[0024] The embodiment of the present invention combines the atmospheric water vapor content information (PWV data) calculated in real time by GNSS observation data, supplements the deficiency of satellite remote sensing in cloud bottom water vapor observation, integrates GNSS observation data with meteorological satellite data, and improves the accuracy of precipitation inversion. At the same time, a trained multi-layer neural network model is introduced to automatically extract features from complex data, achieving high-time and high-precision rainfall inversion.

[0025] In the embodiment of the present invention, the training of the multi-layer neural network model is as follows: Figure 2 As shown, including: Obtain long-term series of measured rainfall and multi-channel cloud top brightness temperature data, and calculate the brightness temperature difference between the infrared channel and the water vapor channel; The GNSS observation data of the same period are obtained, and the atmospheric precipitable water PWV is calculated based on the GNSS observation data.

[0026] A sample data set was constructed based on the measured rainfall, cloud top brightness temperature data, brightness temperature difference and atmospheric precipitable water volume (PWV). Constructing a multi-layer neural network model, wherein the input layer of the multi-layer neural network model is a PWV sequence, a brightness temperature image sequence, and a brightness temperature difference image sequence within a time window, and the output layer is the rainfall in the corresponding time period; The constructed multi-layer neural network model is trained using the sample data set to obtain a trained model.

[0027] As a preferred embodiment, the present invention introduces an embodiment of rainfall inversion based on a back-propagation neural network using GNSS PWV-assisted meteorological satellite remote sensing data, comprising the following steps: (1) Download the rainfall data for Guangzhou from June to September 2023 and the multi-channel cloud top temperature real-time products observed by the FY4B satellite, and calculate the brightness temperature difference between the infrared channel and the water vapor channel.

[0028] (2) Obtain GNSS observation data within the same period and calculate the precipitable water volume (PWV).

[0029] (3) Preprocessing the data: Taking a 6-hour time window, obtain the PWV sequence, brightness temperature image sequence, brightness temperature difference image sequence, and Guangzhou rainfall sequence within the time window to obtain a sample data set.

[0030] (4) Randomly select the training set and validation set from the processed PWV, brightness temperature, brightness temperature difference and rainfall data sets (the data set ratio is set to 8:2 here).

[0031] (5) A back propagation neural network (BPNN) model with three hidden layers was constructed. The input layer was the PWV, cloud top brightness temperature and brightness temperature difference image sequence, and the output layer was the rainfall in the corresponding time period.

[0032] (6) Input the training set and validation set data into the BPNN model, train the model until convergence, and save the model parameters.

[0033] (7) Invert rainfall based on the trained model. First, obtain the GNSS PWV and multi-channel cloud top brightness temperature and brightness temperature difference observed by satellite remote sensing during the rainfall period, substitute them into the trained neural network model, and obtain the rainfall during the period.

[0034] The implementation basis of each embodiment of the present invention is to implement programmed processing through a device with a processor function. Therefore, in engineering practice, the technical solutions and functions of each embodiment of the present invention are encapsulated into various modules. Based on this reality, on the basis of the above embodiments, an embodiment of the present invention provides a GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion device, which is used to execute the GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion method in the above method embodiment.

[0035] See also Figure 3 The device comprises: a data acquisition module, which is used to acquire PWV data, cloud top brightness temperature data and brightness temperature difference data during a rainfall period; a rainfall inversion module, which is used to input the PWV data, cloud top brightness temperature data and brightness temperature difference data during the rainfall period into a trained multi-layer neural network model, and output the rainfall during the corresponding period; wherein the training of the multi-layer neural network model comprises: acquiring a long-term series of measured rainfall and multi-channel cloud top brightness temperature data, and calculating the brightness temperature difference between the infrared channel and the water vapor channel; acquiring GNSS observation data during the same period, and calculating the atmospheric precipitable water PWV based on the GNSS observation data; constructing a sample data set according to the acquired measured rainfall, cloud top brightness temperature data, brightness temperature difference and atmospheric precipitable water PWV; constructing a multi-layer neural network model, wherein the input layer of the multi-layer neural network model is a PWV sequence, a brightness temperature image sequence and a brightness temperature difference image sequence within a time window, and the output layer is the rainfall during the corresponding time period; and the constructed multi-layer neural network model is trained using the sample data set to obtain a trained model.

[0036] The embodiment of the present invention provides a method for solving the problem that it is difficult to obtain atmospheric water vapor content when inverting rainfall based on meteorological satellites, resulting in limited accuracy of the inverted rainfall. Figure 3 In several modules, GNSS is introduced to calculate the atmospheric water vapor content (i.e., precipitable water volume PWV) to assist satellite remote sensing methods in achieving high-precision real-time rainfall inversion.

[0037] It should be noted that the device embodiments provided by the present invention are used to implement the methods in the above method embodiments as well as the methods in other method embodiments provided by the present invention. The only difference is that the corresponding functional modules are set, and the principle is basically the same as the principle of the above device embodiments provided by the present invention. As long as the technical personnel in the field refer to the specific technical solutions in other method embodiments on the basis of the above device embodiments, obtain the corresponding technical means and the technical solutions composed of these technical means by combining the technical features, and on the premise of ensuring the practicality of the technical solutions, improve the modules in the above device embodiments to obtain the corresponding device class embodiments, which are used to implement the methods in other method class embodiments. For example: Based on the content of the above device embodiment, as a preferred embodiment, in a GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion device provided in an embodiment of the present invention, constructing a sample data set also includes: According to the preset time window, the PWV sequence, brightness temperature image sequence, brightness temperature difference image sequence and rainfall sequence within the time window are obtained to obtain the sample data set.

[0038] Based on the content of the above device embodiment, as a preferred embodiment, in a GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion device provided in an embodiment of the present invention, constructing a sample data set also includes: A training set and a validation set are randomly selected from the sample data set, the training set is used to train the constructed multi-layer neural network model, and the validation set is used to validate the trained multi-layer neural network model.

[0039] Based on the contents of the above-mentioned device embodiments, as a preferred embodiment, in a GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion device provided in an embodiment of the present invention, the multi-layer neural network model is a back-propagation neural network model including three hidden layers.

[0040] The method of the embodiment of the present invention is implemented by relying on a computing device, so it is necessary to introduce the relevant computing device. Based on this purpose, the embodiment of the present invention provides a computing device, including a processor and a memory, the memory stores program instructions executed by the processor, and the processor calls the program instructions to execute the steps of the GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion method, specifically: Obtain PWV data, cloud top brightness temperature data and brightness temperature difference data during the rainfall period; The PWV data, cloud top brightness temperature data and brightness temperature difference data of the rainfall period are input into the trained multi-layer neural network model, and the rainfall amount of the corresponding period is output; wherein the training of the multi-layer neural network model includes: Obtain long-term series of measured rainfall and multi-channel cloud top brightness temperature data, and calculate the brightness temperature difference between the infrared channel and the water vapor channel; Obtain GNSS observation data for the same period, and calculate atmospheric precipitable water (PWV) based on the GNSS observation data; A sample data set was constructed based on the measured rainfall, cloud top brightness temperature data, brightness temperature difference and atmospheric precipitable water volume (PWV). Constructing a multi-layer neural network model, wherein the input layer of the multi-layer neural network model is a PWV sequence, a brightness temperature image sequence, and a brightness temperature difference image sequence within a time window, and the output layer is the rainfall in the corresponding time period; The constructed multi-layer neural network model is trained using the sample data set to obtain a trained model.

[0041] It should be noted that the processor in the embodiment of the present invention may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method embodiment may be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiment of the present invention may be directly embodied as being executed by a hardware decoding processor, or may be executed by a combination of hardware and software modules in a decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in conjunction with its hardware.

[0042] It can be understood that the memory in the embodiment of the present invention can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0043] An embodiment of the present invention further provides a computer program product, which includes: computer program instructions, which, when executed on a computer, enable the computer to execute each step or process executed in any of the above method embodiments.

[0044] An embodiment of the present invention further provides a computer-readable storage medium, which stores program code. When the program code runs on a computer, the computer executes each step or process executed in any of the above method embodiments.

[0045] In the several embodiments provided in the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0046] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. The GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion method is characterized by: include: Obtain PWV data, cloud top brightness temperature data and brightness temperature difference data during the rainfall period; The PWV data, cloud top brightness temperature data and brightness temperature difference data of the rainfall period are input into the trained multi-layer neural network model, and the rainfall amount of the corresponding period is output; wherein the training of the multi-layer neural network model includes: Obtain long-term series of measured rainfall and multi-channel cloud top brightness temperature data, and calculate the brightness temperature difference between the infrared channel and the water vapor channel; Obtain GNSS observation data for the same period, and calculate atmospheric precipitable water (PWV) based on the GNSS observation data; A sample data set was constructed based on the measured rainfall, cloud top brightness temperature data, brightness temperature difference and atmospheric precipitable water volume (PWV). Constructing a multi-layer neural network model, wherein the input layer of the multi-layer neural network model is a PWV sequence, a brightness temperature image sequence, and a brightness temperature difference image sequence within a time window, and the output layer is the rainfall in the corresponding time period; The constructed multi-layer neural network model is trained using the sample data set to obtain a trained model.

2. The GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion method according to claim 1, characterized in that: Construct a sample dataset, including: According to the preset time window, the PWV sequence, brightness temperature image sequence, brightness temperature difference image sequence and rainfall sequence within the time window are obtained to obtain the sample data set.

3. The GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion method according to claim 2, characterized in that: The method further comprises: A training set and a validation set are randomly selected from the sample data set, the training set is used to train the constructed multi-layer neural network model, and the validation set is used to validate the trained multi-layer neural network model.

4. The GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion method according to claim 1, characterized in that: The multi-layer neural network model is a back-propagation neural network model including three hidden layers.

5. GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion device, characterized in that: include: A data acquisition module is used to obtain PWV data, cloud top brightness temperature data and brightness temperature difference data during the rainfall period; The rainfall inversion module is used to input the PWV data, cloud top brightness temperature data and brightness temperature difference data of the rainfall period into the trained multi-layer neural network model, and output the rainfall of the corresponding period; wherein the training of the multi-layer neural network model includes: Obtain long-term series of measured rainfall and multi-channel cloud top brightness temperature data, and calculate the brightness temperature difference between the infrared channel and the water vapor channel; Obtain GNSS observation data for the same period, and calculate atmospheric precipitable water (PWV) based on the GNSS observation data; A sample data set was constructed based on the measured rainfall, cloud top brightness temperature data, brightness temperature difference and atmospheric precipitable water volume (PWV). Constructing a multi-layer neural network model, wherein the input layer of the multi-layer neural network model is a PWV sequence, a brightness temperature image sequence, and a brightness temperature difference image sequence within a time window, and the output layer is the rainfall in the corresponding time period; The constructed multi-layer neural network model is trained using the sample data set to obtain a trained model.

6. A computing device, characterized in that It comprises a processor and a memory, wherein the memory stores program instructions executed by the processor, and the processor calls the program instructions to execute the steps of the GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion method as described in any one of claims 1 to 4.

7. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to execute the steps of the GNSSPWV-assisted meteorological satellite remote sensing rainfall inversion method as described in any one of claims 1 to 4.

8. A computer program product, characterized in that The method comprises computer program instructions, wherein the computer program instructions enable the computer to execute the steps of the GNSS PWV-assisted meteorological satellite remote sensing rainfall inversion method as claimed in any one of claims 1 to 4.

Images