GFS and GNSS-based large-altitude-difference region ZTD forecasting method

Abstract

The invention provides a large height difference region ZTD forecasting method based on GFS and GNSS. The method comprises the following steps: firstly, acquiring GFS turbulence mixing delay and GNSS turbulence mixing delay at a GNSS observation station position based on historical GFS forecasting data; secondly, using an XGBoost method to construct a nonlinear mapping relation between the GFS turbulence mixing delay and the GNSS turbulence mixing delay; and finally, the trained XGBoost method is used to correct GFS data at the forecasting moment, and high-precision forecasting of the ZTD in the large-altitude-difference region is realized. According to the method provided by the invention, the participation of real-time GNSS ZTD is not needed, and only time, position and GFS forecast data are needed, so that a high-precision ZTD forecast value can be obtained through the constructed XGBoost model, and the beneficial effects of the method are fully embodied.

Description

Technical Field

[0001] The invention relates to the field of GNSS precision positioning, and in particular to a ZTD prediction method for a large elevation difference area based on GFS and GNSS. Background Art

[0002] Tropospheric delay is one of the important error sources of global navigation satellite systems (GNSS). Zenith tropospheric delay (ZTD) in the zenith direction consists of two parts: zenith hydrostatic delay (ZHD) and zenith wet delay (ZWD). ZHD can be accurately calculated based on the Saastamoinen model using air pressure. For ZWD, high-precision and high-spatial-resolution ZWD estimation is difficult to achieve due to the temporal and spatial differences of water vapor. In GNSS precise point positioning (PPP) technology, empirical models are usually used to calculate ZHD, and ZWD or its unmodeled quantity is estimated as an unknown parameter. However, in areas with large height differences, the strong correlation between ZTD and height inevitably increases the convergence time of GNSS data processing, limiting the high-precision application of GNSS under near-real-time or real-time conditions.

[0003] At present, the most convenient way to obtain ZTD is to directly apply empirical models based on measured meteorological parameters, such as the Hopfield model, the Saastamoinen model, and the Black model. These models are usually constructed based on the ideal gas state equation and related assumptions, and the ZHD and ZWD are modeled separately. By inputting the measured meteorological parameters, the accuracy of the calculated ZTD is between decimeters and centimeters. However, due to the spatiotemporal variation of water vapor, the accuracy of the ZWD model in the empirical model based on measured meteorological parameters is usually limited. For GNSS stations that lack historical data sets of direct meteorological observations or do not have co-located meteorological sensors, it is difficult to obtain measured meteorological parameters for ZTD estimation. Therefore, the input values ​​of empirical models based on measured meteorological parameters are generally the outputs of empirical meteorological parameter models such as GPT2w and GPT3, which will lead to a decrease in the accuracy of the estimated ZTD. In order to reduce the dependence on measured meteorological parameters, scholars have developed ZTD empirical models in the form of grids and spherical harmonics based on reanalysis data and sounding data, such as the IGGtrop series model, the GZTD series model, and the RGZTD model. The advantage of these models is that only longitude, latitude, altitude and time parameters need to be input to obtain the ZTD at a specified location. However, the ZTD empirical model is an approximation of the original data, which inevitably leads to a decrease in accuracy. In addition, relying solely on historical data without incorporating new observations limits the ability of the ZTD empirical model to capture the detailed characteristics of tropospheric delay changes.

[0004] With the development of GNSS, regional ZTD estimation can also be based on the real-time PPP ZTD estimation of surrounding GNSS stations, through methods such as inverse distance weighting and spline interpolation. This method has high requirements on the distribution of surrounding GNSS stations. In areas with large elevation differences, the calculated ZTD may be affected by the elevation difference of the station, resulting in large deviations. Forecast data based on numerical weather models (NWM) have good spatial coverage and service continuity, and can provide good data supplement for areas with sparse GNSS stations. The Global Forecast System (GFS) is a global numerical weather prediction model developed and operated by the National Center for Environmental Prediction (NCEP) of the United States, providing global atmospheric and wave forecasts at a latitude and longitude grid resolution of 0.25°×0.25°. GFS runs forecasts at 00:00, 06:00, 12:00 and 18:00 UTC every day, producing 120 hours of hourly forecast output. Since the time delay for uploading forecast data is about 3 to 5 hours, using 6 to 11 hours of GFS forecast data can fully simulate the actual situation. This meets the requirements of using GFS for real-time ZTD estimation in areas with large elevation differences. Previous studies have shown that combining GNSS and GFS data for regional ZTD estimation is an effective strategy. However, these methods usually require obtaining real-time GNSS ZTD estimates at the corresponding time. For areas with large elevation differences, the distribution of GNSS stations is relatively sparse and uneven, and regional real-time GNSS ZTD services also have the risk of unauthorized or data flow failure. Therefore, it is necessary to construct a GFS correction model without the participation of real-time GNSS ZTD to achieve accurate ZTD prediction in areas with large elevation differences.

[0005] In view of the complexity of the spatiotemporal changes of ZTD in areas with large elevation differences and the sparse distribution of GNSS stations, how to achieve high-precision and high-spatial-resolution ZTD accurate forecasts through GNSS historical data and GFS forecast products is a key issue that needs to be solved urgently. It has important theoretical research and practical application significance for real-time high-precision applications of GNSS. Summary of the invention

[0006] In order to improve the effectiveness of GNSS real-time high-precision application in areas with large elevation differences, the present invention proposes a ZTD prediction method for areas with large elevation differences based on GFS and GNSS, which solves the problem that real-time GNSS ZTD is required to participate in regional ZTD estimation in previous methods, and can also be applied to areas with sparse GNSS stations. The present invention provides the following technical solutions: A ZTD prediction method for large elevation difference areas based on GFS and GNSS, comprising the following steps: S1, calculate the historical data of GNSS ZTD and GFS layered ZTD at all GNSS station locations in the study area; S2, based on the GFS layered ZTD, obtain the GNSS turbulence mixing delay and GFS turbulence mixing delay at the GNSS station location; S3, based on XGBoost, builds a mapping model from GFS turbulent mixing delay to GNSS turbulent mixing delay, and predicts the ZTD of the specified location and altitude through the GFS vertical stratified delay at the forecast time and the trained XGBoost model.

[0007] Preferably, step S1 specifically comprises: S11, calculate the GNSS ZTD at all GNSS station locations by precise point positioning PPP; S12, calculate the GFS ZTD values ​​of all pressure layers below 10 km at all grid point locations in the historical GFS forecast data in the study area; S13, according to the GFS ZTD values ​​of the four GFS grid points closest to the GNSS station location, the GFS ZTD values ​​of all pressure layers below 10 km at the GNSS station location are calculated using the inverse distance weighted method to obtain the GFS layered ZTD.

[0008] Preferably, the calculation method of the GFS ZTD value in S12 is as follows: Calculation of ZTD at the highest pressure layer of the GFS using the Saastamoinen model top , the water vapor content at the highest pressure layer of the GFS is assumed to be zero:

[0009] Where P top and h top They are the air pressure of the highest atmospheric layer and the earth's height. φ is the latitude of the grid point; The ZTD between the top layer and other layers is calculated using the hierarchical integration method:

[0010]

[0011] In the formula, k 1 , k 2 and k 3 is the atmospheric refractive index constant, e i,ave , T i,ave and rh i,aveis the average water vapor pressure, temperature and relative humidity between the i-th layer and the i+1-th layer; ds is the thickness between the i-th layer and the i+1-th layer, and ZTD top and ZTD part Add them together to get the ZTD of the specified pressure layer.

[0012] Preferably, step S2 specifically comprises: S21, using the exponential function model to describe the vertical change of ZTD:

[0013] Where ZTD α , TD α and ZTD α0 They are α The tropospheric delay, turbulent mixing delay and vertical stratification delay at the height of 0m are ε is the unmodeled residual, β are the model coefficients, is the vertical stratified delay component; based on the GFS stratified ZTD, the exponential function model is used to estimate the turbulent mixing delay TD using the least squares method α and model coefficients β , thereby obtaining the GFS vertical stratification delay and GFS turbulent mixing delay at the GNSS station location; S22, subtract the GNSS ZTD from the GFS vertical stratified delay at the corresponding position to obtain the GNSS turbulent mixing delay.

[0014] Preferably, step S3 specifically comprises: S31, construct the XGBoost model framework, take the annual accumulated day, hour, longitude, latitude and GFS turbulence mixing delay of historical data as input, and GNSS turbulence mixing delay as output for model training. GNSS turbulence mixing delay is used to correct the accuracy of GFS turbulence mixing delay, and obtain the trained XGBoost_TD model; S32, obtain the GFS forecast data of the specified location and altitude, calculate the GFS turbulent mixing delay and GFS vertical stratification delay of the specified location and altitude according to the GFS forecast data at the forecast time using the formula of S21, use the annual accumulated day, hour, longitude, latitude and GFS turbulent mixing delay at the forecast time as the input of the trained XGBoost_TD model, obtain the corrected GFS turbulent mixing delay, add the GFS vertical stratification delay and the corrected GFS turbulent mixing delay at the forecast time, and obtain the ZTD forecast value.

[0015] Preferably, the XGBoost model input data is in the form of a two-dimensional matrix of sample×5, and the output data is a vector of sample×1, where sample is the number of samples of historical data.

[0016] Preferably, a five-fold cross-validation method is used to determine the optimal parameters of the XGBoost model. The data set is divided into five parts, four of which are used as training data and the remaining one is used as validation data. The model finally trained is the model corresponding to the parameter set that minimizes the root mean square error of all validation data.

[0017] Compared with the prior art, the beneficial effects achieved by the present invention are: by separating the vertical stratification delay and the turbulent mixing delay, the adaptability of the XGBoost model to areas with large elevation differences and sparse GNSS stations is improved; the trained XGBoost model does not require the participation of real-time GNSS ZTD and has better adaptability, which is of great significance for the high-precision prediction of ZTD in areas with large elevation differences. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is the overall flow chart of the method of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of 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.

[0020] In order to make the above-mentioned objects, features and effects of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] Example 1: A ZTD prediction method for large elevation difference areas based on GFS and GNSS, such as Figure 1 As shown, the following steps are included: S1, calculate the historical data of GNSS ZTD and GFS layered ZTD at all GNSS stations in the study area. Specifically: S11, calculate the GNSS ZTD values ​​at all GNSS station locations using precise point positioning PPP y ZTDs .

[0022] S12, calculate the GFS ZTD values ​​of all pressure layers below 10 km at all grid points in the historical GFS forecast data in the study area; the calculation method of GFS ZTD values ​​is as follows: Calculation of ZTD at the highest pressure layer of the GFS using the Saastamoinen model top , the water vapor content at the highest pressure layer of the GFS is assumed to be zero:

[0023] Where P top and h top They are the air pressure of the highest atmospheric layer and the earth's height. φ is the latitude of the grid point; The ZTD between the top layer and other layers is calculated using the hierarchical integration method:

[0024]

[0025] In the formula, k 1 , k 2 and k 3 is the atmospheric refractive index constant, e i,ave , T i,ave and rh i,ave is the average water vapor pressure, temperature and relative humidity between the i-th layer and the i+1-th layer; ds is the thickness between the i-th layer and the i+1-th layer, and ZTD top and ZTD part Add them together to get the ZTD of the specified pressure layer.

[0026] S13, according to the GFS ZTD values ​​of the four GFS grid points closest to the GNSS station location, the GFS ZTD values ​​of all pressure layers below 10 km at the GNSS station location are calculated using the inverse distance weighted method to obtain the GFS layered ZTD.

[0027] S2, based on the GFS layered ZTD, obtain the GNSS turbulence mixing delay and the GFS turbulence mixing delay at the GNSS station location. Step S2 is specifically as follows: S21, using the exponential function model to describe the vertical change of ZTD:

[0028] Where ZTD α , TD α and ZTD α0 They are α The tropospheric delay, turbulent mixing delay and vertical stratification delay at the height of 0m are εis the unmodeled residual, β are the model coefficients, is the vertical stratified delay component; based on the GFS stratified ZTD, the exponential function model is used to estimate the turbulent mixing delay TD using the least squares method α and model coefficients β , thereby obtaining the GFS vertical layered delay at the GNSS station location y SDg and GFS turbulence mixing delay y TDg ; S22, GNSS ZTD value y ZTDs The vertical layered delay of GFS at the corresponding location y SDg Subtract and get the GNSS turbulence mixing delay y TDs .

[0029] S3, based on XGBoost, build a mapping model from GFS turbulent mixing delay to GNSS turbulent mixing delay, and predict the ZTD of the specified location and height through the GFS vertical layered delay at the forecast time and the trained XGBoost model. Step S3 is specifically as follows: S31, build the XGBoost model framework, and delay the annual accumulation of historical data by day, hour, longitude, latitude and GFS turbulence. y TDg As input, the GNSS turbulence mixing delay y TDs As the output for model training, the GNSS turbulent mixing delay is used to correct the accuracy of the GFS turbulent mixing delay to obtain the trained XGBoost model. Because the accuracy of the GNSS turbulent mixing delay at the same location is better, the accuracy of the GFS turbulent mixing delay is lower. The trained model is a mapping of the GFS turbulent mixing delay to the GNSS turbulent mixing delay. During use, when the GFS turbulent mixing delay at other locations is input, the output of the trained XGBoost model becomes a correction value, which is equivalent to improving the accuracy of the GFS turbulent mixing delay.

[0030] The XGBoost model input data is in the form of a two-dimensional matrix of sample×5, and the output data is a vector of sample×1, where sample is the number of samples of historical data. The five-fold cross-validation method is used to determine the optimal parameters of the XGBoost model. The data set is divided into five parts, with four parts as training data and the remaining one as validation data. The model that is finally trained is the model corresponding to the parameter set that minimizes the root mean square error of all validation data.

[0031] S32, obtain the GFS forecast data of the specified location and altitude, calculate the GFS turbulent mixing delay and GFS vertical stratification delay of the specified location and altitude according to the GFS forecast data at the forecast time using the S21 formula, use the annual accumulated day, hour, longitude, latitude and GFS turbulent mixing delay at the forecast time as the input of the trained XGBoost model, obtain the corrected GFS turbulent mixing delay, add the GFS vertical stratification delay and the corrected GFS turbulent mixing delay at the forecast time to obtain the ZTD forecast value.

[0032] Example 2: In order to evaluate the performance of the proposed ZTD estimation method in areas with large elevation differences, Yunnan Province of China is regarded as a typical area with large elevation differences, and the model is trained and verified using GNSS and GFS data. The GNSS historical data are ZTD products generated by 26 GNSS stations in the China Crustal Movement Observation Network from 2016 to 2022; the GFS data are GFS 6-hour and 9-hour forecast data with a resolution of 0.25°×0.25° downloaded from the NCEP GFS 0.25° Global Forecast Grid Historical Archive (https: / / rda.ucar.edu / datasets / d084001 / ). By combining the GFS 6-hour and 9-hour forecast data, the GFS forecast data with a time interval of 3 hours from 2016 to 2022 are formed. Based on the GNSS historical data and the GFS historical data, the GNSS turbulent mixing delay time series and the GFS turbulent mixing delay time series at the locations of the 26 GNSS stations are calculated. After quality control, the input data of the XGBoost model is a two-dimensional matrix of 427079×5, and the output data is a vector matrix of 427079×1. The five-fold cross-validation method is used to determine the optimal parameters of the XGBoost model to obtain the trained XGBoost_TD model.

[0033] In terms of accuracy verification, the observation data from 130 GNSS stations in the continuously operating reference station network in Yunnan Province, China from September 17 to December 21, 2023 were processed using the post-PPP strategy, and the obtained GNSS ZTD data were used as the reference truth value for verification. At the same time, the XGBoost_ZTD model (the annual accumulated day, hour, longitude, latitude, altitude, and GFS ZTD of historical data were used as input, and GNSS ZTD was used as output) and the GRNN model (the longitude, latitude and GFS turbulent mixing delay at the forecast time were used as input, and the GNSS turbulent mixing delay was used as output) were constructed for comparison. The specific experimental scheme is as follows: (1) original GFSZTD forecast value; (2) XGBoost_ZTD model; (3) GRNN model; (4) XGBoost_TD model. It should be stated that the experimental platform of this embodiment is Python3.8 software under the Windows operating system. The analysis results of this embodiment are not affected by the operating system and Python software version. Table 1 gives the statistical data of the experimental results.

[0034] Table 1

[0035] The experimental results show that the average deviations of the original GFS ZTD forecast, XGBoost_ZTD model, GRNN model and XGBoost_TD model are −22.76mm, 22.85mm, −4.10mm and 1.11mm, respectively, and the root mean square errors (RMS) are 27.17mm, 36.55mm, 18.03mm and 16.46mm, respectively. Among the four schemes, the XGBoost_ZTD model not only fails to improve the accuracy of the GFSZTD forecast, but also introduces significant outliers. This is mainly because the XGBoost_ZTD model does not separate the vertical variation characteristics of ZTD, resulting in the lack of representativeness of its training results in areas with large elevation differences. Compared with the original GFS ZTD forecast, the accuracy of the GRNN model is improved by about 33.64%. However, from the statistical results of the extreme values, it can be found that the error range of the GRNN model exceeds the error range of the original GFS ZTD forecast. This is because the GNSS stations involved in the training are sparsely distributed, and the GRNN model has only one hyperparameter, which easily leads to model overfitting.

[0036] Compared with the original GFS ZTD forecast, XGBoost_ZTD model and GRNN model, the accuracy of XGBoost_TD model is improved by about 39.42%, 54.96% and 8.71% respectively. XGBoost_TD model not only uses exponential function to separate the vertical stratified delay component of ZTD, but also adjusts the model parameters through a large amount of historical data, reducing the local optimal risk caused by the sparse distribution of GNSS stations involved in training, thereby obtaining the most accurate ZTD forecast.

[0037] In summary, the ZTD prediction method for large elevation difference areas based on GFS and GNSS proposed in this invention has good performance. By separating the vertical stratification delay and the turbulent mixing delay, the adaptability of the XGBoost model to large elevation difference areas and sparse GNSS station areas is improved. The trained XGBoost model does not require the participation of real-time GNSS ZTD and has better adaptability, which is of great significance for the high-precision prediction of ZTD in large elevation difference areas.

[0038] Embodiment 3: The computer-readable storage medium of this embodiment stores a computer program thereon, and when the program is executed by a processor, the steps of the ZTD prediction method for large elevation difference areas based on GFS and GNSS in embodiment 1 are implemented.

[0039] The computer-readable storage medium of this embodiment may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal; the computer-readable storage medium of this embodiment may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card, a secure digital card, a flash memory card, etc. equipped on the terminal; further, the computer-readable storage medium may also include both an internal storage unit of the terminal and an external storage device.

[0040] The computer-readable storage medium of this embodiment is used to store computer programs and other programs and data required by the terminal. The computer-readable storage medium can also be used to temporarily store data that has been output or is to be output.

[0041] Embodiment 4: The computer device of this embodiment includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of a method for ZTD prediction in large elevation difference areas based on GFS and GNSS in embodiment 1 are implemented.

[0042] In this embodiment, the processor may be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, readily available programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0043] Those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, or of course by hardware. Based on this understanding, the above technical solution can be essentially or in other words, the part that contributes to the prior art can be embodied in the form of a software product, which 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 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.

[0044] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention is described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A ZTD prediction method for large elevation difference areas based on GFS and GNSS, characterized in that: The following steps are involved: S1, calculate the historical data of GNSS ZTD and GFS layered ZTD at all GNSS station locations in the study area; S2, based on the GFS layered ZTD, obtain the GNSS turbulence mixing delay and GFS turbulence mixing delay at the GNSS station location; S3, based on XGBoost, builds a mapping model from GFS turbulent mixing delay to GNSS turbulent mixing delay, and predicts the ZTD of the specified location and altitude through the GFS vertical stratified delay at the forecast time and the trained XGBoost model.

2. The ZTD prediction method for large elevation difference areas based on GFS and GNSS according to claim 1, characterized in that: Step S1 is specifically as follows: S11, calculate the GNSS ZTD at all GNSS station locations by precise point positioning PPP; S12, calculate the GFS ZTD values ​​of all pressure layers below 10 km at all grid point locations in the historical GFS forecast data in the study area; S13, according to the GFS ZTD values ​​of the four GFS grid points closest to the GNSS station location, the GFS ZTD values ​​of all pressure layers below 10 km at the GNSS station location are calculated using the inverse distance weighted method to obtain the GFS layered ZTD.

3. The ZTD prediction method for large elevation difference areas based on GFS and GNSS according to claim 2, characterized in that: The calculation method of GFS ZTD value in S12 is as follows: Calculation of ZTD at the highest pressure layer of the GFS using the Saastamoinen model top , the water vapor content at the highest pressure layer of the GFS is assumed to be zero: ； Where P top and h top They are the air pressure of the highest atmospheric layer and the earth's height. φ is the latitude of the grid point; The ZTD between the top layer and other layers is calculated using the hierarchical integration method: ； ； Where k1, k2 and k3 are atmospheric refractive index constants, e i,ave , T i,ave and rh i,ave is the average water vapor pressure, temperature and relative humidity between the i-th layer and the i+1-th layer; ds is the thickness between the i-th layer and the i+1-th layer, and ZTD top and ZTD part Add them together to get the ZTD of the specified pressure layer.

4. The ZTD prediction method for large elevation difference areas based on GFS and GNSS according to claim 2, characterized in that: Step S2 is specifically as follows: S21, using the exponential function model to describe the vertical change of ZTD: ； Where ZTD α , TD α and ZTD α0 They are α The tropospheric delay, turbulent mixing delay and vertical stratification delay at the height of 0m are ε is the unmodeled residual, β are the model coefficients, is the vertical layered delay component; Based on the GFS layered ZTD, the exponential function model is used to estimate the turbulent mixing delay TD using the least squares method. α and model coefficients β , thereby obtaining the GFS vertical stratification delay and GFS turbulent mixing delay at the GNSS station location; S22, subtract the GNSS ZTD from the GFS vertical stratified delay at the corresponding position to obtain the GNSS turbulent mixing delay.

5. The ZTD prediction method for large elevation difference areas based on GFS and GNSS according to claim 4, characterized in that: Step S3 is specifically as follows: S31, construct the XGBoost model framework, take the annual accumulated day, hour, longitude, latitude and GFS turbulence mixing delay of historical data as input, and GNSS turbulence mixing delay as output for model training. GNSS turbulence mixing delay is used to correct the accuracy of GFS turbulence mixing delay, and obtain the trained XGBoost_TD model; S32, obtain the GFS forecast data of the specified location and altitude, calculate the GFS turbulent mixing delay and GFS vertical stratification delay of the specified location and altitude according to the GFS forecast data at the forecast time using the formula of S21, use the annual accumulated day, hour, longitude, latitude and GFS turbulent mixing delay at the forecast time as the input of the trained XGBoost_TD model, obtain the corrected GFS turbulent mixing delay, add the GFS vertical stratification delay and the corrected GFS turbulent mixing delay at the forecast time, and obtain the ZTD forecast value.

6. The ZTD prediction method for large elevation difference areas based on GFS and GNSS according to claim 5, characterized in that: The XGBoost model input data is in the form of a two-dimensional matrix of sample×5, and the output data is a vector of sample×1, where sample is the number of samples of historical data.

7. The ZTD prediction method for large elevation difference areas based on GFS and GNSS according to claim 6, characterized in that: The five-fold cross-validation method is used to determine the optimal parameters of the XGBoost model. The data set is divided into five parts, four of which are used as training data and the remaining one is used as validation data. The final trained model is the model corresponding to the parameter set that minimizes the root mean square error of all validation data.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of a ZTD prediction method for large elevation difference areas based on GFS and GNSS as described in any one of claims 1 to 7 are implemented.

9. A computer device comprising a processor, a memory and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the ZTD prediction method for large elevation difference areas based on GFS and GNSS are implemented as described in any one of claims 1-7.

Images