Method and apparatus for constructing ionospheric mapping function model, device, and storage medium

Abstract

Disclosed in the present invention are a method and apparatus for constructing an ionospheric mapping function model, a device, and a storage medium. The method comprises: acquiring historical slant total electron content data of an ionosphere; in the historical slant total electron content data, taking, as a corresponding historical vertical total electron content value, a historical slant total electron content value corresponding to a satellite elevation angle greater than a preset angle, and calculating a corresponding historical mapping function value; acquiring a corresponding Modified Julian Day, local time, satellite elevation angle and azimuth angle of an ionospheric pierce point; and on the basis of the historical mapping function value, the Modified Julian Day, the local time, the satellite elevation angle, and the azimuth angle of the ionospheric pierce point, training a preset LSTM model by taking the Modified Julian Day, the local time, the satellite elevation angle and the azimuth angle of the ionospheric pierce point as inputs and taking the historical mapping function value as an output, so as to obtain an ionospheric mapping function model. The present invention can improve the accuracy of ionospheric mapping functions.

Description

A method and device for constructing an ionospheric projection function model, and a storage medium TECHNICAL FIELD

[0001] The present application relates to the field of GNSS precise data processing, and in particular to a method and device for constructing an ionospheric projection function model, and a storage medium. BACKGROUND

[0002] The ionosphere is an important part of the space environment between the earth and the sun. Monitoring and researching various phenomena in the ionosphere, and then revealing its spatiotemporal variation and physical mechanism, not only helps to promote the research of the ionosphere theory and the cross-discipline of earth science, but also helps the development of space, aviation and communication applications. Among them, the projection function (MF) is used to realize the mutual conversion between the vertical total electron content (VTEC) and the slant total electron content (STEC), and is crucial to the application of ionospheric products.

[0003] In the past few decades, a variety of projection functions have been proposed and widely used. The most commonly used projection function is the single-layer MF, which is based on the assumption that the ionospheric electron density is spherically symmetric and uniformly distributed. It establishes a trigonometric projection relationship based on the receiver-to-satellite elevation angle and the ionospheric thin layer height. In addition, there is the Klobuchar MF, which is only related to the elevation angle from the station to the satellite at a fixed height. In addition, the MSLMF projection function is also widely used. With the rapid development of deep learning technology, the long short-term memory (LSTM) model has also been widely used in ionospheric modeling and prediction. Many scholars have carried out VTEC prediction research based on the LSTM model, and the LSTM model has good performance in predicting solar indices such as sunspot number and Kp index, which creates good conditions for the construction of projection functions. However, these projection functions only consider the influence of ionospheric thin layer height and signal elevation angle, and do not consider the influence of ionospheric spatiotemporal variation and azimuth angle, resulting in low accuracy of existing ionospheric projection functions. SUMMARY

[0004] The present application provides a method and device for constructing an ionospheric projection function model, and a storage medium, to solve the technical problem that existing projection functions only consider the influence of ionospheric thin layer height and signal elevation angle, and do not consider the influence of ionospheric spatiotemporal variation and azimuth angle, resulting in low accuracy.

[0005] To solve the above technical problems, the application provides a method for constructing an ionosphere projection function model, comprising the following steps:

[0006] obtaining historical total electron content data of ionosphere tilt; wherein the historical total electron content data of ionosphere tilt comprises historical total electron content values of each ionosphere ray;

[0007] taking the historical total electron content values of the historical total electron content data of ionosphere tilt with a satellite elevation angle greater than a preset angle as target historical total electron content values, and taking the target historical total electron content values as corresponding historical vertical total electron content values, and then calculating corresponding historical projection function values according to the historical total electron content values and the historical vertical total electron content values;

[0008] obtaining the simplified Julian date, local time, satellite elevation angle and azimuth angle of the ionosphere piercing point corresponding to the historical total electron content data of ionosphere tilt;

[0009] training a preset LSTM model according to the historical projection function values, simplified Julian date, local time, satellite elevation angle and azimuth angle of the ionosphere piercing point, taking the simplified Julian date, local time, satellite elevation angle and azimuth angle of the ionosphere piercing point as input and the corresponding historical projection function values as output, to obtain a corresponding ionosphere projection function model.

[0010] As a preferred scheme, the method for constructing the ionosphere projection function model further comprises the following steps:

[0011] obtaining current total electron content data of ionosphere tilt, and obtaining the simplified Julian date, local time, satellite elevation angle and azimuth angle of the ionosphere piercing point corresponding to the current total electron content data of ionosphere tilt;

[0012] inputting the simplified Julian date, local time, satellite elevation angle and azimuth angle of the ionosphere piercing point corresponding to the current total electron content data of ionosphere tilt into the ionosphere projection function model, so that the ionosphere projection function model calculates a current ionosphere projection function corresponding to the current total electron content data of ionosphere tilt according to the simplified Julian date, local time, satellite elevation angle and azimuth angle of the ionosphere piercing point corresponding to the current total electron content data of ionosphere tilt, and outputs a corresponding current ionosphere projection function.

[0013] As a preferred scheme, before taking the historical total electron content values of the historical total electron content data of ionosphere tilt with a satellite elevation angle greater than a preset angle as target historical total electron content values, the method further comprises the following steps:

[0014] preprocessing the historical total electron content data of ionosphere tilt; wherein the preprocessing comprises data down-sampling processing.

[0015] As a preferred solution, the local time is calculated by the following formula:

[0016] wherein h, m and s are the hour, minute and second corresponding to the historical oblique total electron content data respectively, λ IPP is the longitude of the ionospheric pierce point.

[0017] As a preferred solution, the LSTM model comprises an input layer, a hidden layer, a full connection layer and an output layer.

[0018] wherein the input features of the input layer are the simplified Julian date, the local time, the satellite elevation angle and the azimuth angle of the ionospheric pierce point; the hidden layer comprises two LSTM layers; the full connection layer linearly transforms the output of the output layer and outputs the linearly transformed result to the output layer.

[0019] As a preferred solution, the corresponding historical projection function value is calculated according to the following formula: MF = VTEC / STEC.

[0020] wherein MF is the historical projection function value, VTEC is the historical vertical total electron content value and STEC is the historical oblique vertical total electron content value.

[0021] As a preferred solution, the method for constructing the ionospheric projection function model further comprises:

[0022] inputting the simplified Julian date, the local time, the satellite elevation angle and the azimuth angle of the ionospheric pierce point corresponding to the historical oblique total electron content data to the ionospheric projection function model, so that the ionospheric projection function model calculates the corresponding projection function value according to the inputted simplified Julian date, the local time, the satellite elevation angle and the azimuth angle of the ionospheric pierce point, and outputs the corresponding first historical projection function value;

[0023] calculating the corresponding first historical vertical total electron content value according to the first historical projection function value and the historical oblique total electron content;

[0024] performing interpolation processing on the first historical vertical total electron content value, and then calculating the corresponding first historical oblique total electron content value according to the first historical vertical total electron content value after interpolation processing and the first historical projection function value;

[0025] verifying the accuracy of the ionospheric projection function model according to the first historical oblique total electron content value.

[0026] On the basis of the above-mentioned embodiments, another embodiment of the present application provides a construction device of an ionosphere projection function model, comprising: a first data acquisition module, a projection function value calculation module, a second data acquisition module, and an ionosphere projection function model construction module.

[0027] The first data acquisition module is configured to acquire historical total electron content data of ionosphere tilt; wherein the historical total electron content data of ionosphere tilt comprises historical total electron content values of each ionosphere ray;

[0028] The projection function value calculation module is configured to take the historical total electron content value of ionosphere tilt with a satellite elevation angle greater than a preset angle in the historical total electron content data as a target historical total electron content value, take the target historical total electron content value as a corresponding historical vertical total electron content value, and then calculate a corresponding historical projection function value according to the historical total electron content value and the historical vertical total electron content value;

[0029] The second data acquisition module is configured to acquire a simplified Julian date, a local time, a satellite elevation angle, and an azimuth angle of an ionosphere piercing point corresponding to the historical total electron content data of ionosphere tilt;

[0030] The ionosphere projection function model construction module is configured to train a preset LSTM model according to the historical projection function value, the simplified Julian date, the local time, the satellite elevation angle, and the azimuth angle of the ionosphere piercing point, take the simplified Julian date, the local time, the satellite elevation angle, and the azimuth angle of the ionosphere piercing point as inputs, take the corresponding historical projection function value as an output, and obtain a corresponding ionosphere projection function model.

[0031] On the basis of the above-mentioned embodiments, still another embodiment of the present application provides an electronic device, which comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the construction method of the ionosphere projection function model according to the above-mentioned embodiments when executing the computer program.

[0032] On the basis of the above-mentioned embodiments, still another embodiment of the present application provides a storage medium, which comprises a stored computer program, wherein the storage medium controls a device where the storage medium is located to execute the construction method of the ionosphere projection function model according to the above-mentioned embodiments when the computer program runs.

[0033] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0034] The application provides a method for constructing an ionosphere projection function model, historical inclined total electron content data of the ionosphere is acquired; a historical inclined total electron content value in the historical inclined total electron content data, which is above a preset satellite elevation angle, is taken as a target historical inclined total electron content value, and the target historical inclined total electron content value is taken as a corresponding historical vertical total electron content value, then a corresponding historical projection function value is calculated according to the historical inclined total electron content value and the historical vertical total electron content value; a simplified Julian day, a local time, a satellite elevation angle and an azimuth of an ionosphere piercing point corresponding to the historical inclined total electron content data are acquired; a preset LSTM model is trained according to the historical projection function value, the simplified Julian day, the local time, the satellite elevation angle and the azimuth of the ionosphere piercing point, with the simplified Julian day, the local time, the satellite elevation angle and the azimuth of the ionosphere piercing point as inputs and the corresponding historical projection function value as output, so that a corresponding ionosphere projection function model is obtained. The application uses the simplified Julian day, the local time, the satellite elevation angle and the azimuth of the ionosphere piercing point as inputs and the projection function value corresponding to the historical inclined total electron content data as output, trains the LSTM model, and finally obtains the corresponding ionosphere projection function model. Since the simplified Julian day, the local time and the azimuth are used as input parameters, the influence of the ionosphere space-time change and the azimuth is considered, and the precision of the ionosphere projection function can be effectively improved. BRIEF DESCRIPTION OF DRAWINGS

[0035] Fig. 1 is a flowchart of a method for constructing an ionosphere projection function model according to an embodiment of the application;

[0036] Fig. 2 is a structure diagram of an LSTM model according to the application;

[0037] Fig. 3 is a structure diagram of a device for constructing an ionosphere projection function model according to an embodiment of the application. DETAILED DESCRIPTION

[0038] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of this application; the use of the terms "including," "comprising," or "having" and variations thereof herein is intended to be broad and encompass the terms "consisting of" and "consisting essentially of" and variations thereof. Unless otherwise required by context, singular terms shall include pluralities and vice versa. Unless otherwise required by context, the use herein of the singular is also to be construed as a use of the plural and vice versa.

[0040] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise explicitly and specifically limited.

[0041] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearance of the phrase in various places in the specification is not necessarily all referring to the same embodiment, or to a particular embodiment, or to a particular set of embodiments. It will be explicitly understood by those of ordinary skill in the art that the embodiments described herein can be combined with other embodiments.

[0042] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " in this paper generally represents that the front and rear associated objects are a "or" relationship.

[0043] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two), and similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0044] In the description of the embodiments of the present application, unless otherwise explicitly specified and limited, the technical terms "mounting", "connecting", "connecting", "fixing" and the like should be understood in a broad sense, for example, it can be fixedly connected, or it can be detachably connected, or it can be integrated; it can be mechanical connection, or it can be electrical connection; it can be directly connected, or it can be indirectly connected through an intermediate medium; it can be the internal communication of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meaning of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0045] Embodiment one

[0046] Please refer to Figure 1, which is a flowchart of a method for constructing an ionospheric projection function model according to an embodiment of the present application, comprising the following steps:

[0047] S1, obtaining historical slant total electron content data of the ionosphere; wherein the historical slant total electron content data comprises historical slant total electron content values on each ray of the ionosphere;

[0048] Preferably, before the historical slant total electron content values with satellite elevation angles above a preset angle in the historical slant total electron content data are taken as target historical slant total electron content values, the method further comprises: preprocessing the historical slant total electron content data; wherein the preprocessing comprises data down-sampling processing.

[0049] Specifically, the method for constructing the ionospheric projection function model comprises the following steps:

[0050] 1. Data acquisition and preprocessing:

[0051] The historical slant total electron content (STEC) products provided by the MIT / Haystack Observatory platform are collected in advance, and the data is down-sampled to reduce the time resolution to 10 minutes; wherein the STEC product is the STEC value on each ray, and the product website is http: / / cedar.openmadrigal.org / single / .

[0052] S2, taking the historical slant total electron content values with satellite elevation angles above a preset angle in the historical slant total electron content data as target historical slant total electron content values, and taking the target historical slant total electron content values as corresponding historical vertical total electron content values, and then calculating corresponding historical projection function values according to the historical slant total electron content values and the historical vertical total electron content values;

[0053] Preferably, the corresponding historical projection function values are calculated according to the following formula: MF=VTEC / STEC.

[0054] Wherein, MF is the historical projection function value, VTEC is the historical vertical total electron content value, and STEC is the historical slant vertical total electron content value.

[0055] 2. Generation of training samples:

[0056] (a) First, select STEC data with satellite elevation angles above 85°, and take them as VTEC values, because according to the SLMF function:

[0057] In the formula, R represents the radius of the earth, H represents the height of the ionospheric layer, and E is the satellite elevation angle. When the layer height is selected as 350 km and the satellite elevation angle is 85°, the value of SLMF is 0.9966, and the difference between STEC and VTEC can be ignored at this time;

[0058] (b) selecting a ray with a time interval of VTEC in (a) of no more than 5 minutes and the longitude and latitude of the ionospheric pierce point (IPP) of no more than 0.5°. The specified cutoff elevation angle is 20°, so as to obtain the STEC corresponding to VTEC;

[0059] (c) calculating the projection function value: MF = VTEC / STEC.

[0060] S3, acquiring the modified Julian day, local time, satellite elevation angle and azimuth angle of the ionospheric pierce point corresponding to the historical oblique total electron content data;

[0061] Preferably, the local time is calculated by the following formula:

[0062] Wherein, h, m and s respectively represent the hour, minute and second corresponding to the historical oblique total electron content data, λ IPP represents the longitude of the ionospheric pierce point.

[0063] (d) The input features of the projection function (mapping function, MF) model selected in the application are the modified Julian day (Modified Julian Day, MJD), local time (Local time, LT), satellite elevation angle and azimuth angle of IPP, and the output is the MF value, wherein the LT is calculated as follows:

[0064] Wherein, h, m and s respectively represent the hour, minute and second of the data, λ IPP represents the longitude of the ionospheric pierce point.

[0065] And the elevation angle of IPP can be calculated by the following formula:

[0066] S4, according to the historical projection function value, modified Julian day, local time, satellite elevation angle and azimuth angle of the ionospheric pierce point, a preset LSTM model is trained with the modified Julian day, local time, satellite elevation angle and azimuth angle of the ionospheric pierce point as input and the corresponding historical projection function value as output, to obtain the corresponding ionospheric projection function model.

[0067] Preferably, the LSTM model comprises an input layer, a hidden layer, a full connection layer and an output layer; wherein the input features of the input layer are simplified Julian date, local time, satellite elevation angle and azimuth angle of ionospheric piercing point; the hidden layer comprises two LSTM layers; the full connection layer linearly transforms the output of the output layer and outputs the linearly transformed result to the output layer.

[0068] 3. Construction of ionospheric projection function model:

[0069] A recurrent neural network (RNN) is a deep learning model with memory function, which can remember previous time series and add them to the output calculation, and it is widely used in time series prediction. LSTM is a RNN architecture used to model time series and long-term dependencies, and has stronger learning and information selection ability than RNN. Please refer to FIG. 2 for the structure diagram of the LSTM model used in the present application. The model comprises four layers: an input layer, a hidden layer, a full connection layer and an output layer. The input layer uses the MJD, LT, elevation angle and azimuth angle of IPP as input features, and the hidden layer comprises two LSTM layers. The LSTM layer outputs the result to the full connection layer, and the full connection layer linearly transforms the output layer; finally, the corresponding MF value is output as a label.

[0070] Then, the projection function value, simplified Julian date, local time, satellite elevation angle and azimuth angle of ionospheric piercing point are taken as the training samples of the LSTM model, the simplified Julian date, local time, satellite elevation angle and azimuth angle of ionospheric piercing point are taken as the input, and the corresponding projection function value is taken as the output, and a predetermined LSTM model is trained to obtain the corresponding ionospheric projection function model.

[0071] Preferably, the method for constructing the ionospheric projection function model further comprises: inputting the simplified Julian date, local time, satellite elevation angle and azimuth angle of ionospheric piercing point corresponding to the historical inclined total electron content data into the ionospheric projection function model, so that the ionospheric projection function model calculates the corresponding projection function value according to the input simplified Julian date, local time, satellite elevation angle and azimuth angle of ionospheric piercing point, and outputs the corresponding first historical projection function value; calculates the corresponding first historical vertical total electron content value according to the first historical projection function value and the historical inclined total electron content; performs interpolation processing on the first historical vertical total electron content value, and then calculates the corresponding first historical inclined total electron content value according to the first historical vertical total electron content value after interpolation processing and the first historical projection function value; and verifies the accuracy of the ionospheric projection function model according to the first historical inclined total electron content value.

[0072] Preferably, the method for constructing the ionospheric projection function model further comprises: obtaining current oblique total electron content data, and obtaining corresponding simplified Julian day, local time, satellite elevation angle and azimuth angle of ionospheric piercing point according to the current oblique total electron content data; inputting the simplified Julian day, local time, satellite elevation angle and azimuth angle of ionospheric piercing point corresponding to the current oblique total electron content data into the ionospheric projection function model, so that the ionospheric projection function model calculates the current ionospheric projection function corresponding to the current oblique total electron content data according to the simplified Julian day, local time, satellite elevation angle and azimuth angle of ionospheric piercing point corresponding to the current oblique total electron content data, and outputs the corresponding current ionospheric projection function.

[0073] 4. Model verification:

[0074] Ionospheric grid product generation: Ionospheric products are usually published in grid form for ease of use. In the process of constructing the ionospheric projection function model, STEC with an elevation angle greater than 85° is taken as VTEC, and STEC data with a time interval of no more than 5 minutes and IPP longitude and latitude of no more than 0.5° is selected. In the training sample of the present application, 40% of the data is not used for training, 20% is used to generate VTEC, and 20% is used to verify VTEC. The 20% of STEC data not used in the training, verification and testing of the LSTM model is interpolated to obtain an ionospheric grid product VTEC model with a spatial resolution of 1°x1° and a time resolution of 10 minutes, and another 20% of STEC data is used to verify the accuracy of the ionospheric grid product. Specifically:

[0075] Input the simplified Julian day, local time, satellite elevation angle and azimuth angle of ionospheric piercing point into the ionospheric projection function model, so that the ionospheric projection function model calculates the projection function value according to the simplified Julian day, local time, satellite elevation angle and azimuth angle of ionospheric piercing point, and outputs the corresponding first projection function value; calculate the corresponding first oblique total electron content value according to the first projection function value and the vertical total electron content; interpolate the first oblique total electron content value, and then calculate the corresponding first vertical total electron content value according to the interpolated first oblique total electron content value and the first projection function value; verify the accuracy of the ionospheric projection function model according to the first vertical total electron content value.

[0076] 5. VTEC product release:

[0077] (a) 20% of STEC data that is not used to train, validate and test the LSTM-MF model is selected to produce the VTEC product. The MJD, LT, elevation and azimuth of the IPP corresponding to the STEC data are input into the LSTM-MF model, and the model outputs the MF value;

[0078] (b) VTEC data is calculated according to the STEC data and the MF value of (a), and interpolation is performed to obtain the Model VTEC product;

[0079] (c) Another 20% of STEC data that is not used to train, validate and test the LSTM-MF model is selected to validate the VTEC model product. The VTEC of a certain point is interpolated based on the Model VTEC product, the VTEC is projected onto the STEC by the MF value output by the LSTM-MF model, and the accuracy of the STEC obtained by the Model VTEC product is evaluated.

[0080] 6. Application of ionospheric projection function model

[0081] Obtain current total electron content data, and obtain corresponding simplified Julian date, local time, satellite elevation angle and azimuth of the ionospheric piercing point according to the current total electron content data; input the simplified Julian date, local time, satellite elevation angle and azimuth of the ionospheric piercing point corresponding to the current total electron content data into the ionospheric projection function model, so that the ionospheric projection function model calculates the current ionospheric projection function corresponding to the current total electron content data according to the simplified Julian date, local time, satellite elevation angle and azimuth of the ionospheric piercing point corresponding to the current total electron content data, and outputs the corresponding current ionospheric projection function.

[0082] Embodiment two

[0083] Please refer to FIG. 3, which is a structural schematic diagram of an ionospheric projection function model construction device provided by an embodiment of the present application. The device comprises a first data acquisition module, a projection function value calculation module, a second data acquisition module and an ionospheric projection function model construction module.

[0084] The first data acquisition module is configured to acquire historical total electron content data of the ionosphere; wherein the historical total electron content data comprises historical total electron content values on each ray of the ionosphere.

[0085] The projection function value calculation module is configured to take a historical oblique total electron content value corresponding to a satellite elevation angle greater than a preset angle in the historical oblique total electron content data as a target historical oblique total electron content value, take the target historical oblique total electron content value as a corresponding historical vertical total electron content value, and then calculate a corresponding historical projection function value according to the historical oblique total electron content value and the historical vertical total electron content value.

[0086] The second data acquisition module is configured to acquire a simplified Julian date, a local time, a satellite elevation angle, and an azimuth angle of an ionospheric piercing point corresponding to the historical oblique total electron content data.

[0087] The ionospheric projection function model construction module is configured to train a preset LSTM model according to the historical projection function value, the simplified Julian date, the local time, the satellite elevation angle, and the azimuth angle of the ionospheric piercing point, take the simplified Julian date, the local time, the satellite elevation angle, and the azimuth angle of the ionospheric piercing point as inputs, and take the corresponding historical projection function value as an output, to obtain a corresponding ionospheric projection function model.

[0088] It should be noted that the apparatus embodiments described above are only schematic and that the units as described separately can or can not be physically separate, and the components as shown as units can or can not be physical components, i.e., can be located in one place or distributed over multiple network components. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment. In addition, the connection relationship between the modules in the apparatus embodiments provided by the present application indicates that there is a communication connection between them, which can be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement it without creative labor.

[0089] Those skilled in the art can clearly understand that, for the convenience and brevity, the specific working process of the apparatus described above can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0090] Embodiment three

[0091] Correspondingly, the present embodiment provides an electronic device, the device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the construction method of the ionospheric projection function model when executing the computer program.

[0092] The electronic device can be a desktop computer, a notebook computer, a palm computer, a cloud server, and other computing devices. The device can include but is not limited to a processor and a memory.

[0093] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor or the like, and is a control center of the device that connects all parts of the device through various interfaces and lines.

[0094] Embodiment four

[0095] Correspondingly, the embodiment of the present application provides a storage medium, which comprises a stored computer program, wherein the computer program controls a device where the storage medium is located to perform the method for constructing the ionosphere projection function model when the computer program is running.

[0096] The memory can be used to store the computer program, and the processor realizes various functions of the device by running or executing the computer program stored in the memory and calling data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required by a function, etc.; and the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory devices.

[0097] The storage medium is a computer readable storage medium, and the computer program is stored in the computer readable storage medium. When the computer program is executed by a processor, steps of each method embodiment described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0098] The above is the preferred embodiment of the present application. It should be noted that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, which are also considered within the scope of protection of the present application.

Claims

1. A method for constructing an ionospheric projection function model, characterized in that, The method comprises the following steps: obtaining historical total electron content data of ionosphere tilt; wherein the historical total electron content data of ionosphere tilt comprises historical total electron content values of each ionosphere ray; taking the historical total electron content value of the satellite elevation angle above the preset angle in the historical total electron content data as a target historical total electron content value, and taking the target historical total electron content value as a corresponding historical vertical total electron content value, and then calculating a corresponding historical projection function value according to the historical total electron content value and the historical vertical total electron content value; obtaining the simplified Julian date, local time, satellite elevation angle and azimuth angle of the ionosphere piercing point corresponding to the historical total electron content data; training a preset LSTM model according to the historical projection function value, the simplified Julian date, the local time, the satellite elevation angle and the azimuth angle of the ionosphere piercing point, taking the simplified Julian date, the local time, the satellite elevation angle and the azimuth angle of the ionosphere piercing point as input and the corresponding historical projection function value as output, to obtain a corresponding ionosphere projection function model.

2. The method of claim 1, wherein, The method further comprises the following steps: obtaining current total electron content data, and obtaining the simplified Julian date, the local time, the satellite elevation angle and the azimuth angle of the ionosphere piercing point corresponding to the current total electron content data; inputting the simplified Julian date, the local time, the satellite elevation angle and the azimuth angle of the ionosphere piercing point corresponding to the current total electron content data into the ionosphere projection function model, so that the ionosphere projection function model calculates a current ionosphere projection function corresponding to the current total electron content data according to the simplified Julian date, the local time, the satellite elevation angle and the azimuth angle of the ionosphere piercing point corresponding to the current total electron content data, and outputs a corresponding current ionosphere projection function.

3. The method of claim 1, wherein the ionospheric projection function model is constructed by: Before taking the historical total electron content value of the satellite elevation angle above the preset angle in the historical total electron content data as a target historical total electron content value, the method further comprises the following steps: preprocessing the historical total electron content data; wherein the preprocessing comprises data down-sampling processing.

4. The method of constructing an ionospheric projection function model of claim 3, wherein, The local time is calculated by the following equation: where h, m and s are the hour, minute and second, respectively, corresponding to the historical total electron content data of the inclination, λ IPP is the longitude of the ionospheric pierce point.

5. The method of constructing an ionospheric projection function model of claim 1, wherein, The LSTM model comprises an input layer, a hidden layer, a full connection layer and an output layer; wherein the input features of the input layer are the simplified Julian date, the local time, the satellite elevation angle and the azimuth angle of the ionosphere piercing point; the hidden layer comprises two LSTM layers; the full connection layer linearly transforms the output of the output layer and outputs the linearly transformed result to the output layer.

6. The method of constructing an ionospheric projection function model of claim 1, wherein, The corresponding historical projection function value is calculated according to the following formula: MF=VTEC / STEC; wherein MF is the historical projection function value, VTEC is the historical vertical total electron content value, and STEC is the historical total electron content value.

7. The method of constructing an ionospheric projection function model of claim 1, wherein, The method further comprises the following steps: input the simplified Julian date, local time, satellite elevation angle and azimuth angle of the ionospheric piercing point corresponding to the historical total electron content data of the inclination to the ionospheric projection function model, so that the ionospheric projection function model calculates the corresponding projection function value according to the input simplified Julian date, local time, satellite elevation angle and azimuth angle of the ionospheric piercing point, and outputs the corresponding first historical projection function value; According to the first historical projection function value and the historical total electron content of the inclination, the first historical vertical total electron content value corresponding to the first historical projection function value is calculated; The first historical vertical total electron content value is interpolated, and then the first historical vertical total electron content value after interpolation and the first historical projection function value are calculated to obtain the first historical total electron content value of the inclination; According to the first historical total electron content value of the inclination, the accuracy of the ionospheric projection function model is verified.

8. A device for constructing an ionospheric projection function model, characterized by, It includes: First data acquisition module, projection function value calculation module, second data acquisition module and ionospheric projection function model construction module; The first data acquisition module is used for acquiring historical total electron content data of the ionosphere of the inclination; wherein the historical total electron content data of the ionosphere of the inclination includes: historical total electron content value of the ionosphere on each ray of the inclination; The projection function value calculation module is used for taking the historical total electron content value of the satellite elevation angle above the preset angle in the historical total electron content data of the inclination as the target historical total electron content value, taking the target historical total electron content value as the corresponding historical vertical total electron content value, and then calculating the corresponding historical projection function value according to the historical total electron content value and the historical vertical total electron content value; The second data acquisition module is used for acquiring the simplified Julian date, local time, satellite elevation angle and azimuth angle of the ionospheric piercing point corresponding to the historical total electron content data of the inclination; The ionospheric projection function model construction module is used for training a preset LSTM model according to the historical projection function value, simplified Julian date, local time, satellite elevation angle and azimuth angle of the ionospheric piercing point, taking the simplified Julian date, local time, satellite elevation angle and azimuth angle of the ionospheric piercing point as input, and taking the corresponding historical projection function value as output, to obtain the corresponding ionospheric projection function model.

9. An electronic device, comprising: The storage medium includes a stored computer program, wherein when the computer program runs, the device where the storage medium is located executes the construction method of the ionospheric projection function model as claimed in any one of claims 1 to 7.

10. A storage medium, characterized by The storage medium includes a stored computer program, wherein when the computer program runs, the device where the storage medium is located executes the construction method of the ionospheric projection function model as claimed in any one of claims 1 to 7.

Images