GNSS global ZTD correction method and device considering anisotropy

Abstract

The invention provides a GNSS global ZTD correction method and device considering anisotropy, and the method comprises the steps: dividing the whole world into regular windows with the same size according to a mesh generation algorithm, and obtaining a correction model training sample through a Panguu-Weather numerical weather forecast system; constructing a zenith troposphere delay correction model taking anisotropy into consideration by adopting a BP neural network, taking an annual day, the height, the latitude and the longitude of the current position, the zenith troposphere delay and the height, the latitude and the longitude of the target position as input layer data, and taking the zenith troposphere delay of the target position as output layer data; based on the zenith troposphere delay correction model considering anisotropy, a user can obtain correction information of zenith troposphere delay only by providing the annual day, the height and longitude and latitude of the current position, zenith troposphere delay and the height and longitude and latitude of the target position and retrieving the corresponding model, and the precision of GNSS meteorological monitoring and environment monitoring is improved.

Description

Technical Field

[0001] The present invention relates to the field of satellite navigation and positioning technology, and more particularly to a GNSS global ZTD correction method and device that takes anisotropy into account. Background Art

[0002] Global Navigation Satellite System (GNSS) signals are affected by time delay and bending effects when passing through the atmosphere, resulting in tropospheric delay. Accurate zenith tropospheric delay information can effectively improve GNSS positioning accuracy. The currently commonly used zenith tropospheric delay (ZTD) correction models mainly rely on mathematical methods such as bilinear interpolation and trigonometric interpolation, and have not yet taken into account the latitude and longitude change rates, making it difficult to meet the needs of high-precision GNSS meteorological monitoring, environmental monitoring and other application scenarios. Therefore, the development of a GNSS global ZTD correction method and equipment that takes anisotropy into account can effectively overcome the defects in the above-mentioned related technologies, which has become a technical problem that needs to be urgently solved in the industry. Summary of the Invention

[0003] In view of the above problems existing in the prior art, embodiments of the present invention provide a GNSS global ZTD correction method and device that takes anisotropy into consideration.

[0004] In a first aspect, an embodiment of the present invention provides a GNSS global ZTD correction method that takes anisotropy into account, including: using the artificial intelligence numerical weather forecast system Pangu-Weather, dividing the global range into regular windows of equal size according to a grid partitioning algorithm, and obtaining correction model training samples; using a BP neural network, using the annual accumulated days, the altitude, longitude and latitude of the user's current location, and the zenith tropospheric delay ZTD, as well as the altitude and longitude and latitude of the user's target location as input layer data, and the zenith tropospheric delay ZTD of the target location as output layer data, using ERA5 as the Pangu-Weather initial field, predicting real-time meteorological parameters and calculating the initial zenith tropospheric delay ZTD, and constructing a zenith tropospheric delay ZTD correction model that takes anisotropy into account; based on the zenith tropospheric delay ZTD correction model that takes anisotropy into account, according to the annual accumulated days, the altitude, longitude and latitude of the user's current location, and the zenith tropospheric delay ZTD, as well as the altitude and longitude and latitude of the user's target location provided by the user, obtaining correction information of the zenith tropospheric delay ZTD, thereby improving the accuracy of GNSS meteorological monitoring and environmental monitoring.

[0005] Based on the contents of the above method embodiments, the GNSS global ZTD correction method taking into account anisotropy is provided in the embodiments of the present invention. The real-time meteorological parameters predicted by the artificial intelligence-based numerical weather forecast system Pangu-Weather have a temporal resolution of 1 hour and a spatial resolution of 0.25°×0.25°, and both the resolution accuracy and resolution speed are higher than those of the numerical weather forecast method.

[0006] Based on the contents of the above method embodiments, the GNSS global ZTD correction method taking into account anisotropy is provided in the embodiments of the present invention. In the grid partitioning algorithm, the grid window size is determined based on the integer number of partitions and the continuity of the window to ensure that the divided regular windows can be used as training samples for the correction model.

[0007] Based on the content of the above method embodiment, the GNSS global ZTD correction method taking into account anisotropy is provided in the embodiment of the present invention. The BP neural network fits any complex nonlinear function and learns the corresponding features from the training data without manual intervention.

[0008] Based on the content of the above method embodiments, the GNSS global ZTD correction method taking into account anisotropy is provided in the embodiments of the present invention. The BP neural network is applied to supervised learning tasks of classification and regression, and can continue to work when errors occur in a predetermined number of neurons.

[0009] Based on the contents of the above method embodiments, in the embodiment of the present invention, the GNSS global ZTD correction method taking into account anisotropy is provided. The network structure of the BP neural network is adjusted according to the complexity of constructing the anisotropic zenith tropospheric delay ZTD correction model to meet the corresponding task requirements.

[0010] Based on the contents of the above-mentioned method embodiment, the embodiment of the present invention provides a GNSS global ZTD correction method that takes anisotropy into account. The method retrieves the corresponding model to obtain correction information of the zenith tropospheric delay ZTD, including: according to the position information of the target point, retrieving the nearest gridded correction model, and providing the user with correction information of the zenith tropospheric delay ZTD with a predetermined accuracy.

[0011] In the second aspect, an embodiment of the present invention provides a GNSS global ZTD correction device that takes into account anisotropy, including: a first main module for implementing the numerical weather forecast system Pangu-Weather using artificial intelligence, dividing the global range into regular windows of equal size according to the grid partitioning algorithm, and obtaining correction model training samples; a second main module for implementing the use of a BP neural network, using the annual cumulative day, the altitude, longitude and latitude of the user's current location and the zenith tropospheric delay ZTD and the altitude and longitude and latitude of the user's target location as input layer data, and using the zenith tropospheric delay ZTD of the target location as the input layer data. As the output layer data, ERA5 is used as the Pangu-Weather initial field to predict real-time meteorological parameters and calculate the initial zenith tropospheric delay ZTD, and construct a zenith tropospheric delay ZTD correction model that takes into account anisotropy; the third main module is used to implement the zenith tropospheric delay ZTD correction model based on the anisotropy-taking-in-account zenith tropospheric delay ZTD, and obtain the correction information of the zenith tropospheric delay ZTD based on the annual accumulated days provided by the user, the altitude, longitude and latitude of the user's current location and the zenith tropospheric delay ZTD, and the altitude and longitude and latitude of the user's target location, thereby improving the accuracy of GNSS meteorological monitoring and environmental monitoring.

[0012] In a third aspect, an embodiment of the present invention provides an electronic device, including:

[0013] At least one processor, at least one memory and a communication interface; wherein,

[0014] The processor, memory and communication interface communicate with each other;

[0015] The memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the GNSS global ZTD correction method taking anisotropy into account provided by any one of the various implementations of the first aspect.

[0016] In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions enable a computer to execute the GNSS global ZTD correction method taking into account anisotropy provided by any one of the various implementation methods of the first aspect.

[0017] The embodiments of the present invention provide a GNSS global ZTD correction method and device that takes anisotropy into account. By using ERA5 as the Pangu-Weather initial field, real-time meteorological parameters are predicted and the initial ZTD is calculated. A BP neural network is used for training and a gridding algorithm is introduced to divide the window. A high-precision ZTD correction model that takes anisotropy into account is established. Only the annual cumulative day, the altitude, longitude and latitude of the current location, and the ZTD, as well as the altitude and longitude and latitude of the target location are required. Based on the target point location information, the nearest gridded correction model is automatically retrieved to obtain tropospheric delay correction information, thereby ensuring the accuracy of tropospheric delay atmospheric services and improving the monitoring accuracy of GNSS meteorological monitoring and environmental monitoring applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use 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.

[0019] Figure 1 A schematic flow chart of a GNSS global ZTD correction method taking into account anisotropy provided in an embodiment of the present invention;

[0020] Figure 2 A schematic diagram of the structure of a GNSS global ZTD correction device that takes into account anisotropy provided by an embodiment of the present invention;

[0021] Figure 3 A schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION 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 making 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 can be combined with each other arbitrarily to form a feasible technical solution. This combination is not subject to the constraints of the sequence of steps and / or structural composition mode, but must be based on the ability of ordinary technicians in this field to implement it. When the combination of technical solutions is mutually contradictory or cannot be implemented, 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. If there are step numbers in the following embodiments, they are only set for the convenience of explanation and description, and the order between the steps is not limited in any way. The execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0022] The embodiment of the present invention provides a GNSS global ZTD correction method taking into account anisotropy, see Figure 1 The method includes: using the artificial intelligence numerical weather forecast system Pangu-Weather, dividing the global area into regular windows of equal size according to a gridding algorithm, and obtaining correction model training samples; using a BP neural network, taking the annual accumulated days, the altitude, longitude and latitude of the user's current location, and the zenith tropospheric delay ZTD, as well as the altitude and longitude and latitude of the user's target location as input layer data, and taking the zenith tropospheric delay ZTD of the target location as output layer data, using ERA5 as the Pangu-Weather initial field, predicting real-time meteorological parameters and calculating the initial zenith tropospheric delay ZTD, and constructing a zenith tropospheric delay ZTD correction model that takes into account anisotropy; based on the zenith tropospheric delay ZTD correction model that takes into account anisotropy, obtaining zenith tropospheric delay ZTD correction information according to the annual accumulated days, the altitude, longitude and latitude of the user's current location, and the zenith tropospheric delay ZTD, as well as the altitude and longitude and latitude of the user's target location provided by the user, thereby improving the accuracy of GNSS meteorological monitoring and environmental monitoring.

[0023] Based on the content of the above method embodiment, as an optional embodiment, the GNSS global ZTD correction method taking into account anisotropy is provided in the embodiment of the present invention. The real-time meteorological parameters predicted by the artificial intelligence-based numerical weather forecast system Pangu-Weather have a temporal resolution of 1 hour and a spatial resolution of 0.25°×0.25°, and the resolution accuracy and resolution speed are both higher than those of the numerical weather forecast method.

[0024] Based on the content of the above method embodiment, as an optional embodiment, the GNSS global ZTD correction method taking into account anisotropy is provided in the embodiment of the present invention. In the grid partitioning algorithm, the grid window size is determined based on the integer number of partitions and the continuity of the window to ensure that the divided regular windows can be used as training samples for the correction model.

[0025] Based on the content of the above method embodiment, as an optional embodiment, the GNSS global ZTD correction method taking into account anisotropy is provided in the embodiment of the present invention, and the BP neural network fits arbitrarily complex nonlinear functions and learns corresponding features from training data without manual intervention.

[0026] Based on the content of the above method embodiment, as an optional embodiment, the GNSS global ZTD correction method taking into account anisotropy is provided in the embodiment of the present invention. The BP neural network is applied to supervised learning tasks of classification and regression, and can continue to work when errors occur in a predetermined number of neurons.

[0027] Based on the content of the above method embodiment, as an optional embodiment, the GNSS global ZTD correction method taking into account anisotropy is provided in the embodiment of the present invention. The network structure of the BP neural network is adjusted according to the complexity of constructing the zenith tropospheric delay ZTD correction model taking into account anisotropy to meet the corresponding task requirements.

[0028] Based on the content of the above method embodiment, as an optional embodiment, the GNSS global ZTD correction method that takes into account anisotropy is provided in the embodiment of the present invention, and the retrieval of the corresponding model to obtain the correction information of the zenith tropospheric delay ZTD includes: according to the position information of the target point, retrieving the nearest gridded correction model, and providing the user with the correction information of the zenith tropospheric delay ZTD of a predetermined accuracy.

[0029] The embodiment of the present invention provides a GNSS global ZTD correction method that takes anisotropy into account. By using ERA5 as the Pangu-Weather initial field, real-time meteorological parameters are predicted and the initial zenith tropospheric delay ZTD is calculated. A BP neural network is used for training and a gridding algorithm is introduced to divide the window. A high-precision ZTD correction model that takes anisotropy into account is established. Only the annual accumulated day, the altitude, longitude and latitude of the current position, and the ZTD, as well as the altitude and longitude and latitude of the target position are required. Based on the target point position information, the nearest gridded correction model is automatically retrieved to obtain the tropospheric delay correction information, thereby ensuring the accuracy of the tropospheric delay atmospheric service and improving the monitoring accuracy of GNSS meteorological monitoring and environmental monitoring applications.

[0030] The following scientific demonstration is carried out through real data to verify the above beneficial effects.

[0031] The high-precision ZTD correction model that takes into account anisotropy improves the accuracy of global tropospheric delay correction by a percentage compared to the bilinear interpolation method. Compared with the existing technology, the present invention uses ERA5 as the Pangu-Weather initial field for GNSS atmospheric services to predict real-time meteorological parameters and calculate the initial zenith tropospheric delay ZTD. It adopts BP neural network for training and introduces grid partitioning algorithm to divide the window, and establishes a high-precision ZTD correction model that takes into account anisotropy. The user only needs to provide the annual day, the altitude, longitude and latitude and ZTD of the current location, and the altitude and longitude and latitude of the target location. The system automatically retrieves the nearest gridded correction model based on the target point location information to obtain the tropospheric delay correction information, thereby ensuring the accuracy of tropospheric delay atmospheric services. It has potential value for application scenarios such as GNSS meteorological monitoring and environmental monitoring.

[0032] The implementation basis of each embodiment of the present invention is to implement programmed processing through a device with processor functions. Therefore, in engineering practice, the technical solutions and functions of each embodiment of the present invention can be encapsulated into various modules. Based on this reality, on the basis of the above embodiments, an embodiment of the present invention provides a GNSS global ZTD correction device that takes into account anisotropy. The device is used to execute the GNSS global ZTD correction method that takes into account anisotropy in the above method embodiment. Figure 2 The device includes: a first main module for implementing the artificial intelligence numerical weather forecast system Pangu-Weather, dividing the global area into regular windows of equal size according to a gridding algorithm, and obtaining correction model training samples; a second main module for implementing a BP neural network, using the annual cumulative day, the altitude, longitude and latitude of the user's current location, and the zenith tropospheric delay (ZTD), as well as the altitude and longitude and latitude of the user's target location as input layer data, and the zenith tropospheric delay (ZTD) of the target location as output layer data, using ERA5 as the Pangu-Weather initial field, predicting real-time meteorological parameters and calculating the initial zenith tropospheric delay (ZTD), and constructing a zenith tropospheric delay (ZTD) correction model that takes into account anisotropy; and a third main module for implementing the zenith tropospheric delay (ZTD) correction model based on the anisotropy-taking-in-account zenith tropospheric delay (ZTD), obtaining zenith tropospheric delay (ZTD) correction information based on the annual cumulative day, the altitude, longitude and latitude of the user's current location, and the zenith tropospheric delay (ZTD), as well as the altitude and longitude and latitude of the user's target location, thereby improving the accuracy of GNSS meteorological and environmental monitoring.

[0033] The GNSS global ZTD correction device taking into account anisotropy provided by the embodiment of the present invention adopts Figure 2Several modules in it use ERA5 as the Pangu-Weather initial field to predict real-time meteorological parameters and calculate the initial zenith tropospheric delay ZTD. BP neural network is used for training and a gridding algorithm is introduced to divide the window. A high-precision ZTD correction model that takes into account anisotropy is established. Only the annual accumulated day, the altitude, longitude and latitude of the current position and ZTD, and the altitude and longitude and latitude of the target position are required. According to the target point position information, the nearest gridded correction model is automatically retrieved to obtain the tropospheric delay correction information, which ensures the accuracy of the tropospheric delay atmospheric service and improves the monitoring accuracy of GNSS meteorological monitoring and environmental monitoring applications.

[0034] It should be noted that the device in the device embodiment provided by the present invention can be used to implement the method in the above-mentioned method embodiment as well as the method in other method embodiments provided by the present invention. The only difference is that the corresponding functional modules are set. The principle is basically the same as the principle of the above-mentioned device embodiment provided by the present invention. As long as those skilled in the art refer to the specific technical solutions in other method embodiments on the basis of the above-mentioned device embodiment, obtain the corresponding technical means and the technical solutions composed of these technical means by combining technical features, and ensure the practicality of the technical solutions, they can improve the device in the above-mentioned device embodiment to obtain the corresponding device class embodiment, thereby obtaining the corresponding device class embodiment for implementing the methods in other method class embodiments. For example:

[0035] Based on the content of the above-mentioned device embodiment, as an optional embodiment, the GNSS global ZTD correction device taking into account anisotropy provided in the embodiment of the present invention also includes: a first sub-module, used to realize the temporal resolution of the real-time meteorological parameters predicted by the artificial intelligence-based numerical weather forecast system Pangu-Weather is 1 hour, and the spatial resolution is 0.25°×0.25°, and the resolution accuracy and resolution speed are both higher than the numerical weather forecast method.

[0036] Based on the content of the above-mentioned device embodiment, as an optional embodiment, the GNSS global ZTD correction device taking into account anisotropy provided in the embodiment of the present invention also includes: a second sub-module, which is used to implement the grid partitioning algorithm, and determine the grid window size according to the integerness of the partitioning number and the continuity of the window, to ensure that the divided regular window can be used as a correction model training sample.

[0037] Based on the content of the above-mentioned device embodiment, as an optional embodiment, the GNSS global ZTD correction device taking into account anisotropy provided in the embodiment of the present invention also includes: a third submodule, which is used to realize the BP neural network fitting of arbitrarily complex nonlinear functions and learn corresponding features from training data without manual intervention.

[0038] Based on the content of the above-mentioned device embodiment, as an optional embodiment, the GNSS global ZTD correction device taking into account anisotropy provided in the embodiment of the present invention also includes: a fourth sub-module, which is used to implement the BP neural network for supervised learning tasks of classification and regression, and can continue to work when errors occur in a predetermined number of neurons.

[0039] Based on the content of the above-mentioned device embodiment, as an optional embodiment, the GNSS global ZTD correction device taking into account anisotropy provided in the embodiment of the present invention also includes: a fifth sub-module, which is used to implement the network structure of the BP neural network, and adjust it according to the complexity of constructing the zenith tropospheric delay ZTD correction model taking into account anisotropy to meet the corresponding task requirements.

[0040] Based on the content of the above-mentioned device embodiment, as an optional embodiment, the GNSS global ZTD correction device taking into account anisotropy provided in the embodiment of the present invention further includes: a sixth sub-module, used to implement the retrieval of the corresponding model to obtain the correction information of the zenith tropospheric delay ZTD, including: according to the target point position information, retrieving the nearest gridded correction model, and providing the user with the correction information of the zenith tropospheric delay ZTD of a predetermined accuracy.

[0041] The method of the embodiment of the present invention is implemented by electronic devices, so it is necessary to introduce the relevant electronic devices. Based on this purpose, the embodiment of the present invention provides an electronic device, such as Figure 3 As shown, the electronic device includes: at least one processor, a communications interface, at least one memory, and a communications bus, wherein the at least one processor, the communications interface, and the at least one memory communicate with each other via the communications bus. The at least one processor can call logic instructions in the at least one memory to execute all or part of the steps of the methods provided in the aforementioned method embodiments.

[0042] In addition, the logic instructions in the at least one memory mentioned above can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each method embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0043] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0044] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiment.

[0045] The flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present invention. Based on this understanding, each box in the flowchart or block diagram can represent a module, program segment or part of the code, and the module, program segment or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, or sometimes in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0046] It should be noted that the terms "include", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "include..." do not exclude the presence of other identical elements in the process, method, article or device that includes the elements. Any "predetermined threshold", "preset threshold" or similar expressions that do not indicate a specific value can be determined by a person of ordinary skill in the art through simple experiments or corresponding debugging.

[0047] 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 make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A GNSS global ZTD correction method taking into account anisotropy, characterized by: include: Pangu-Weather, an artificial intelligence numerical weather forecasting system, divides the globe into regular windows of equal size according to a gridding algorithm to obtain training samples for a correction model. A BP neural network is used with the annual cumulative day, the altitude, longitude and latitude of the current location, and the zenith tropospheric delay (ZTD), as well as the altitude and longitude and latitude of the target location, as input layer data, and the zenith tropospheric delay (ZTD) of the target location as output layer data. Using ERA5 as the Pangu-Weather initial field, real-time meteorological parameters are predicted and the initial zenith tropospheric delay (ZTD) is calculated, thereby constructing a ZTD correction model that takes into account anisotropy. Based on the ZTD correction model that takes into account anisotropy, users only need to provide the annual cumulative day, the altitude, longitude and latitude of the current location, and the zenith tropospheric delay (ZTD), as well as the altitude and longitude and latitude of the target location, to obtain ZTD correction information for the zenith tropospheric delay, thereby improving the accuracy of GNSS meteorological and environmental monitoring.

2. The GNSS global ZTD correction method taking into account anisotropy according to claim 1, characterized in that: The real-time meteorological parameters predicted by the artificial intelligence-based numerical weather prediction system Pangu-Weather have a temporal resolution of 1 hour and a spatial resolution of 0.25°×0.25°.

3. The GNSS global ZTD correction method taking into account anisotropy according to claim 2, characterized in that: In the grid partitioning algorithm, the grid window size is determined based on the integer number of partitions and the continuity of the window, ensuring that the divided regular windows can be used as training samples for the correction model.

4. The GNSS global ZTD correction method taking into account anisotropy according to claim 3, characterized in that: The BP neural network fits any complex nonlinear function and learns corresponding features from training data without manual intervention.

5. The GNSS global ZTD correction method taking into account anisotropy according to claim 4, characterized in that: The BP neural network is applied to supervised learning tasks of classification and regression, and can continue to work even when errors occur in a predetermined number of neurons.

6. The GNSS global ZTD correction method taking into account anisotropy according to claim 5, characterized in that: The network structure of the BP neural network is adjusted according to the complexity of constructing the anisotropic zenith tropospheric delay (ZTD) correction model to meet the corresponding task requirements.

7. The GNSS global ZTD correction method taking into account anisotropy according to claim 6, characterized in that: The retrieving the corresponding model to obtain the correction information of the zenith tropospheric delay ZTD includes: retrieving the nearest gridded correction model according to the target point position information, and providing the user with the correction information of the zenith tropospheric delay ZTD with a predetermined accuracy.

8. A GNSS global ZTD correction device taking into account anisotropy, characterized in that: include: The first main module is used to implement the artificial intelligence numerical weather forecast system Pangu-Weather, which divides the global area into regular windows of equal size according to the gridding algorithm to obtain correction model training samples. The second main module is used to implement the BP neural network, using the annual cumulative day, the altitude, longitude and latitude of the current location, and the zenith tropospheric delay ZTD, as the altitude and longitude and latitude of the target location as the input layer data, and the zenith tropospheric delay ZTD of the target location as the output layer data. Using ERA5 as the Pangu-Weather initial field, it predicts real-time meteorological parameters and calculates the initial zenith tropospheric delay ZTD, and constructs a zenith tropospheric delay ZTD correction model that takes into account anisotropy. The third main module is used to implement the zenith tropospheric delay ZTD correction model based on the anisotropy-taking-into-account zenith tropospheric delay ZTD. The user only needs to provide the annual cumulative day, the altitude, longitude and latitude of the current location, and the zenith tropospheric delay ZTD, as well as the altitude and longitude and latitude of the target location, to obtain the zenith tropospheric delay ZTD correction information, thereby improving the accuracy of GNSS meteorological monitoring and environmental monitoring.

9. An electronic device, characterized in that: include: At least one processor, at least one memory and a communication interface; wherein, The processor, memory and communication interface communicate with each other; The memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that The non-transitory computer-readable storage medium stores computer instructions, which cause a computer to execute the method of any one of claims 1 to 7.

Images