An ionospheric disturbance prediction method and device, a terminal device and a storage medium
By combining a GNSS receiver with a trained ionospheric disturbance prediction model, the problem of high cost of high-frequency receiver equipment was solved, achieving accurate prediction of ionospheric disturbances and cost reduction.
Patent Information
- Application Number
- CN202511160229.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-19
- Publication Date
- 2025-11-21
AI Technical Summary
Existing technologies rely too heavily on high-frequency receiver equipment, resulting in high costs.
Observational data is acquired through a GNSS receiver, and a trained ionospheric disturbance prediction model is used to predict future ionospheric disturbances. High-frequency receiver data is used during model training, but the model relies solely on GNSS receiver data during actual use.
It enables accurate prediction of ionospheric disturbances without relying on high-frequency receivers, thus reducing equipment costs.
Smart Images
Figure CN120994940A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of ionospheric environment measurement, and in particular to an ionospheric disturbance prediction method and device, a terminal device and a storage medium. BACKGROUND
[0002] In modern communication and navigation technology, the ionosphere plays a crucial role, affecting the propagation of radio waves and having a significant impact on the signal propagation and positioning accuracy of satellite navigation systems such as the Global Positioning System (GPS). Ionospheric disturbances, such as traveling ionospheric disturbances and equatorial ionospheric bubbles, change the electron density distribution of the ionosphere, causing interference to radio communication and navigation systems.
[0003] Existing ionospheric monitoring techniques rely on high-frequency receiver equipment. The data obtained by high-frequency receiver equipment has higher observation frequency, lower noise influence and higher data quality compared to the data obtained by ordinary GNSS receivers, but high-frequency receiver equipment is expensive. SUMMARY
[0004] The present application provides an ionospheric disturbance prediction method, device, terminal device and storage medium, which can solve the problem of excessive dependence on high-frequency receiver equipment in the prior art.
[0005] An embodiment of the present application provides an ionospheric disturbance prediction method, comprising:
[0006] obtaining to-be-predicted observation data by a GNSS receiver;
[0007] determining target data according to the to-be-predicted observation data; wherein the target data comprises receiver identification, satellite identification, ionospheric piercing point position information and ionospheric delay;
[0008] delaying input of the target data to a trained ionospheric disturbance prediction model, so that the ionospheric disturbance prediction model predicts ionospheric disturbance at a future time according to the target data;
[0009] wherein the training process of the ionospheric disturbance prediction model comprises:
[0010] obtaining a plurality of first observation sequence samples by a GNSS receiver, and a second observation sequence sample corresponding to each first observation sequence sample by a high-frequency receiver; wherein the receiver position coordinates of the first observation sequence sample and the corresponding second observation sequence sample are the same, the sequence coverage periods are the same, and the satellite identifications are the same;
[0011] For each second observation sequence sample, according to the second observation sequence sample, an ionospheric total electron content rate of change index of each time point in the second observation sequence sample is calculated; according to the ionospheric total electron content rate of change index, an ionospheric disturbance condition of each time point in the second observation sequence sample is determined.
[0012] For each first observation data sample of each time point in the first observation sequence sample, an ionospheric disturbance condition of a next time point in the corresponding second observation sequence sample is taken as a label of the first observation data sample; according to the first observation data sample, a target data sample is determined; the target data sample and the corresponding label are input into an ionospheric disturbance prediction model, so that the ionospheric disturbance prediction model performs prediction according to the target data sample, and outputs a prediction result; according to the prediction result and the label, a loss function value is calculated; according to the loss function value, parameters in the ionospheric disturbance prediction model are adjusted.
[0013] Further, determining the ionospheric delay according to the to-be-predicted observation data comprises:
[0014] According to the to-be-predicted observation data, a distance from a GNSS receiver to a satellite, a pseudo-range observation value and a phase observation value are determined;
[0015] According to the distance from the receiver to the satellite, the pseudo-range observation value and the phase observation value, an observation model taking the ionospheric delay as an unknown parameter is constructed;
[0016] The observation model is solved by a non-difference non-combination method to obtain the ionospheric delay.
[0017] Further, the ionospheric disturbance condition is an ionospheric disturbance level; the ionospheric disturbance level comprises: a no-disturbance level, a slight-disturbance level, a light-disturbance level, a moderate-disturbance level, a severe-disturbance level and an extremely severe-disturbance level.
[0018] The ionospheric disturbance condition of each time point in the second observation sequence sample is determined according to the ionospheric total electron content rate of change index, comprising:
[0019] If the ionospheric total electron content rate index at the time is not more than a preset first rate threshold, the ionospheric disturbance level at the time is determined as a non-disturbance level; if the ionospheric total electron content rate index at the time is more than the first rate threshold and not more than a preset second rate threshold, the ionospheric disturbance level at the time is determined as a slight disturbance level; if the ionospheric total electron content rate index at the time is more than the second rate threshold and not more than a preset third rate threshold, the ionospheric disturbance level at the time is determined as a mild disturbance level; if the ionospheric total electron content rate index at the time is more than the third rate threshold and not more than a preset fourth rate threshold, the ionospheric disturbance level at the time is determined as a moderate disturbance level; if the ionospheric total electron content rate index at the time is more than the fourth rate threshold and not more than a preset fifth rate threshold, the ionospheric disturbance level at the time is determined as a severe disturbance level; if the ionospheric total electron content rate index at the time is more than the fifth rate threshold, the ionospheric disturbance level at the time is determined as an extremely severe disturbance level.
[0020] The first rate threshold is less than the second rate threshold; the second rate threshold is less than the third rate threshold; the third rate threshold is less than the fourth rate threshold; and the fourth rate threshold is less than the fifth rate threshold.
[0021] Further, the ionospheric piercing point position information is position information of a grid where the ionospheric piercing point is located.
[0022] Another embodiment of the present application further provides an ionospheric disturbance prediction device, comprising a data acquisition module and an ionospheric disturbance prediction module.
[0023] The data acquisition module is configured to acquire to-be-predicted observation data through a GNSS receiver.
[0024] The ionospheric disturbance prediction module is configured to determine target data according to the to-be-predicted observation data; wherein the target data comprises a receiver identifier, a satellite identifier, ionospheric piercing point position information and ionospheric delay; and input the target data to a trained ionospheric disturbance prediction model in a delayed manner, so that the ionospheric disturbance prediction model predicts ionospheric disturbance at a future time according to the target data.
[0025] The training process of the ionospheric disturbance prediction model comprises:
[0026] A plurality of first observation sequence samples are obtained by a GNSS receiver, and a second observation sequence sample corresponding to each of the first observation sequence samples is obtained by a high-frequency receiver; wherein the first observation sequence sample and the corresponding second observation sequence sample have the same receiver position coordinates, the same sequence coverage period, and the same satellite identifier;
[0027] For each second observation sequence sample, an ionospheric total electron content rate of change index at each time in the second observation sequence sample is calculated according to the second observation sequence sample, and an ionospheric disturbance condition at each time in the second observation sequence sample is determined according to the ionospheric total electron content rate of change index.
[0028] For each first observation data sample at each time in the first observation sequence sample, an ionospheric disturbance condition at the next time in the corresponding second observation sequence sample is taken as a label of the first observation data sample, a target data sample is determined according to the first observation data sample, the target data sample and the corresponding label are input into an ionospheric disturbance prediction model, the ionospheric disturbance prediction model is caused to perform prediction according to the target data sample, a prediction result is output, a loss function value is calculated according to the prediction result and the label, and parameters in the ionospheric disturbance prediction model are adjusted according to the loss function value.
[0029] Further, determining the ionospheric delay according to the to-be-predicted observation data comprises:
[0030] Determining a distance from a GNSS receiver to a satellite, a pseudo-range observation value, and a phase observation value according to the to-be-predicted observation data;
[0031] Constructing an observation model taking the ionospheric delay as an unknown parameter according to the distance from the receiver to the satellite, the pseudo-range observation value, and the phase observation value;
[0032] Solving the observation model by a non-difference non-combination method to obtain the ionospheric delay.
[0033] Further, the ionospheric disturbance condition is an ionospheric disturbance level, and the ionospheric disturbance level comprises a non-disturbance level, a slight disturbance level, a light disturbance level, a moderate disturbance level, a severe disturbance level, and an extremely severe disturbance level.
[0034] The determination of the ionospheric disturbance condition at each time in the second observation sequence sample according to the ionospheric total electron content rate of change index comprises:
[0035] For each moment in the second observation sequence sample, if the ionospheric total electron content rate index of the moment does not exceed a preset first rate threshold, the ionospheric disturbance level of the moment is determined as a non-disturbance level; if the ionospheric total electron content rate index of the moment exceeds the first rate threshold and does not exceed a preset second rate threshold, the ionospheric disturbance level of the moment is determined as a slight disturbance level; if the ionospheric total electron content rate index of the moment exceeds the second rate threshold and does not exceed a preset third rate threshold, the ionospheric disturbance level of the moment is determined as a mild disturbance level; if the ionospheric total electron content rate index of the moment exceeds the third rate threshold and does not exceed a preset fourth rate threshold, the ionospheric disturbance level of the moment is determined as a moderate disturbance level; if the ionospheric total electron content rate index of the moment exceeds the fourth rate threshold and does not exceed a preset fifth rate threshold, the ionospheric disturbance level of the moment is determined as a severe disturbance level; if the ionospheric total electron content rate index of the moment exceeds the fifth rate threshold, the ionospheric disturbance level of the moment is determined as an extremely severe disturbance level.
[0036] The first rate threshold is less than the second rate threshold; the second rate threshold is less than the third rate threshold; the third rate threshold is less than the fourth rate threshold; and the fourth rate threshold is less than the fifth rate threshold.
[0037] Further, the ionospheric piercing point position information is position information of a grid where the ionospheric piercing point is located.
[0038] Another embodiment of the present application also provides a terminal device, which comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the computer program is executed by the processor, the steps of the ionospheric disturbance prediction method of the present application are implemented.
[0039] Another embodiment of the present application also provides a computer readable storage medium item, which comprises a stored computer program, and when the computer program is run, the device where the computer readable storage medium is located is controlled to execute the steps of the ionospheric disturbance prediction method of the present application.
[0040] By implementing the present application, the following beneficial effects are achieved:
[0041] The GNSS receiver is used to obtain observation data to be predicted; the receiver identifier, the satellite identifier, the ionospheric piercing point position information and the ionospheric delay are extracted from the observation data to be predicted and input to the trained ionospheric disturbance prediction model, so that the ionospheric disturbance prediction model predicts the ionospheric disturbance at a future moment;
[0042] The ionospheric disturbance prediction model is obtained by training according to data obtained by a GNSS receiver and a high-frequency receiver.
[0043] The ionospheric disturbance prediction model only uses data collected by the high-frequency receiver in the training process, and only needs to collect data by the GNSS receiver in the use process. The ionospheric disturbance prediction model of the present application is free from dependence on the high-frequency receiver in the use process, and solves the problem that the prior art excessively depends on the high-frequency receiver. BRIEF DESCRIPTION OF DRAWINGS
[0044] In order to more clearly illustrate the technical solutions of the present application, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.
[0045] Figure 1 is a flow diagram of an ionospheric disturbance prediction method provided by an embodiment of the present application;
[0046] Figure 2 is a structural diagram of an ionospheric disturbance prediction device provided by an embodiment of the present application. DETAILED DESCRIPTION
[0047] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be clearly and completely described in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some 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 labor are within the scope of protection of the present application.
[0048] 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 the present application belongs; the terms used herein are only for the purpose of describing specific embodiments of the present application, and are not intended to limit the present application; the terms "comprise" and any variations thereof in the specification and claims of the present application and the above description of drawings are intended to cover non-exclusive inclusion.
[0049] 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.
[0050] Reference herein to "embodiments" means that the particular features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily all refer to the same embodiment, nor is it necessarily independent or alternative to other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.
[0051] Reference herein to "embodiments" means that the particular features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily all refer to the same embodiment, nor is it necessarily independent or alternative to other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments. Figure 1 To solve the problem of excessive dependence on high-frequency receiver equipment in the prior art, an ionospheric disturbance prediction method provided by an embodiment of the present application comprises:
[0052] S1, obtaining to-be-predicted observation data by a GNSS receiver.
[0053] It should be noted that a plurality of GNSS receivers and a plurality of satellites are arranged in the research area of the present application.
[0054] In step S1, a certain GNSS receiver collects to-be-predicted observation data emitted from a certain satellite, and obtains the to-be-predicted observation data.
[0055] S2, determining target data according to the to-be-predicted observation data; wherein the target data comprises receiver identification, satellite identification, ionospheric piercing point position information and ionospheric delay.
[0056] In step S2, receiver identification and satellite identification are extracted from the to-be-predicted observation data, and ionospheric piercing point position information and ionospheric delay are obtained by performing ionospheric piercing point and ionospheric delay related calculation according to the to-be-predicted observation data.
[0057] In a preferred embodiment, determining ionospheric delay according to the to-be-predicted observation data comprises:
[0058] Determining the distance from the GNSS receiver to the satellite, the pseudo-range observation value and the phase observation value according to the to-be-predicted observation data;
[0059] According to the distance from the receiver to the satellite, the pseudo-range observation value and the phase observation value, an observation model taking ionospheric delay as an unknown parameter is constructed;
[0060] The ionospheric delay is obtained by solving the observation model by a non-difference non-combination method.
[0061] In the embodiment, in order to simplify the construction of the observation model, the orbit error, the troposphere error, the relativistic effect, the multipath error and the like are combined, and the obtained observation model is:
[0062]
[0063] In the formula, φi represents the pseudo-range observation value of the receiver observing the satellite at the i-th frequency; φi represents the pseudo-range observation value of the receiver observing the satellite at the i-th frequency; φi represents the pseudo-range observation value of the receiver observing the satellite at the i-th frequency; r φi represents the pseudo-range observation value of the receiver observing the satellite at the i-th frequency; s φi represents the pseudo-range observation value of the receiver observing the satellite at the i-th frequency; φi represents the pseudo-range observation value of the receiver observing the satellite at the i-th frequency; r,i φi represents the pseudo-range observation value of the receiver observing the satellite at the i-th frequency; φi represents the pseudo-range observation value of the receiver observing the satellite at the i-th frequency; φi represents the pseudo-range observation value of the receiver observing the satellite at the i-th frequency; φi represents the pseudo-range observation value of the receiver observing the satellite at the i-th frequency; φi represents the pseudo-range observation value of the receiver observing the satellite at the i-th frequency; φi represents the pseudo-range observation value of the receiver observing the satellite at the i-th frequency;
[0064] It should be noted that in satellite navigation and observation, two different frequency carrier signals, i.e., the frequency signal i1 and the frequency signal i2, can be simultaneously emitted by the satellite signal for the ground receiver to receive and process. Different satellite systems have different dual-frequency combinations, and common dual-frequency combinations include:
[0065] (1) GPS satellite: i1=1575.42 MHz, i2=1227.60 MHz;
[0066] (2) Beidou (BDS) satellite: i1=1561.098 MHz, i2=1207.140 MHz;
[0067] (3) Galileo satellite: i1=1575.42 MHz, i2=1207.140 MHz.
[0068] When solving the observation model by the non-difference non-combination method, the precise satellite clock error product released by IGS is used for correction. However, the IGS released value is solved based on ionosphere-free pseudo-range and phase observation value, so that the satellite hardware delay bias is contained in the satellite clock error, and the expression of the satellite clock error is as follows:
[0069]
[0070] In the formula, DCB represents the true value of the satellite clock error; dt s represents the IGS released value of the satellite clock error; and represent the frequency values of two different frequency signals; and represent the satellite end hardware delays of two frequencies;
[0071] In the non-difference non-combination model, the satellite hardware delay bias cannot be offset in the pseudo-range observation value, but can be absorbed by the ionosphere parameter; in the phase observation value, it can be absorbed by the ionosphere parameter and the ambiguity parameter. The above expression of the satellite clock error is substituted into the observation model, and the parameters are reorganized to obtain a new observation model:
[0072]
[0073] In the formula, DCB represents the reorganized receiver clock error; represents the reorganized satellite clock error; represents the ionosphere delay containing the receiver and satellite hardware bias on the receiver-to-satellite observation path at frequency signal i; represents the floating point ambiguity containing the satellite phase hardware bias at frequency signal i;
[0074] The specific expression of each parameter in the new observation model is as follows:
[0075]
[0076] In the formula, DCB r,i represents the differential code bias of the receiver at frequency signal i; represents the differential code bias of the satellite at frequency signal i; γ represents a proportional coefficient;
[0077] The is estimated as a parameter, and the ionosphere delay on the slant path can be solved, that is, the ionosphere measured observation value is obtained.
[0078] Then, the ionospheric mapping function is calculated using the following projection function (MSLM, Modified Single Layer Model) on the basis of the ionospheric thin layer assumption, and then the ionospheric delay of the oblique path is converted to the ionospheric delay in the vertical direction;
[0079] The ionospheric mapping function is:
[0080]
[0081] In the formula, MF(z) represents the ionospheric mapping function; z represents the zenith angle, that is, the angle between the receiver-to-satellite direction and the zenith; R represents the radius of the earth; and H represents the ionospheric thin layer height, which is assumed to be concentrated at a single reference height.
[0082] In a preferred embodiment, the ionospheric pierce point position information is the position information of the grid where the ionospheric pierce point is located.
[0083] It should be noted that the present application divides the research area into a 1°*1° grid, and sequentially numbers each grid, and the position information of the grid where the ionospheric pierce point is located can be represented as the number of the grid.
[0084] S3, inputting the target data delay into the trained ionospheric disturbance prediction model, so that the ionospheric disturbance prediction model predicts the ionospheric disturbance at a future time according to the target data;
[0085] The training process of the ionospheric disturbance prediction model comprises:
[0086] A plurality of first observation sequence samples are obtained by a GNSS receiver, and a second observation sequence sample corresponding to each first observation sequence sample is obtained by a high-frequency receiver; wherein the first observation sequence sample and the corresponding second observation sequence sample have the same receiver position coordinates, the same sequence coverage period, and the same satellite identifier;
[0087] For each second observation sequence sample, the ionospheric total electron content rate index at each time in the second observation sequence sample is calculated according to the second observation sequence sample, and the ionospheric disturbance at each time in the second observation sequence sample is determined according to the ionospheric total electron content rate index;
[0088] For each first observation data sample at each time in the first observation sequence sample, the ionospheric disturbance at the next time in the corresponding second observation sequence sample is taken as the label of the first observation data sample; according to the first observation data sample, a target data sample is determined; the target data sample and the corresponding label are input into an ionospheric disturbance prediction model, so that the ionospheric disturbance prediction model performs prediction according to the target data sample, and outputs a prediction result; according to the prediction result and the label, a loss function value is calculated; and according to the loss function value, parameters in the ionospheric disturbance prediction model are adjusted.
[0089] It should be noted that the observation sequence includes observation data at several continuous times, and the observation data forms a sequence in the order of time. The first observation sequence sample is collected by a GNSS receiver, and the second observation sequence sample is collected by a high-frequency receiver. The sequence coverage time period of the first observation sequence sample and the corresponding second observation sequence sample is the same, which means that the collection time period corresponding to the first observation sequence sample and the collection time period corresponding to the second observation sequence sample are the same. The satellite identifiers of the first observation sequence sample and the corresponding second observation sequence sample are the same, which means that the satellite corresponding to the first observation sequence sample and the satellite corresponding to the second observation sequence sample are the same satellite.
[0090] In the research area of the application, several GNSS receivers, several high-frequency receivers and several satellites are arranged. Each GNSS receiver corresponds to a high-frequency receiver with the same coordinate position. A certain GNSS receiver receives a first observation sequence sample from a certain satellite at a certain time, and a high-frequency receiver at the same coordinate position as the GNSS receiver receives a second observation sequence sample from the same satellite at the same time, so that the first observation sequence sample and the second observation sequence sample collected are in a corresponding relationship. In this way, several groups of first observation sequence samples and corresponding second observation sequence samples are obtained as training data.
[0091] In step S3, according to the second observation sequence sample, the ionospheric total electron content rate index at each time in the second observation sequence sample is calculated, including:
[0092] According to the second observation sequence sample, the ionospheric total electron content at each time in the second observation sequence sample is determined;
[0093] For each time point in the second observation sequence sample, according to the ionospheric total electron content at the current time point and the last time point, the ionospheric total electron content rate at the current time point is calculated; according to the ionospheric total electron content rates at several time points before and after the current time point, the standard deviation of the ionospheric total electron content rate is calculated, and the standard deviation is taken as the ionospheric total electron content rate index at the current time point.
[0094] The calculation formula of the ionospheric total electron content rate is:
[0095]
[0096] In the formula, ROT t represents the ionospheric total electron content rate index at the current time point; TEC t represents the ionospheric total electron content at the current time point; TEC t-1 represents the ionospheric total electron content at the last time point; and Δt represents the time interval between time points.
[0097] In the model training process, the input of the ionospheric disturbance prediction model is the receiver identifier sample, the satellite identifier sample, the ionospheric piercing point position information sample, the ionospheric delay sample, and the corresponding label, which is the ionospheric disturbance at the next time point in the second observation sequence sample corresponding to the other input data. Assuming that the input data is the receiver identifier sample, the satellite identifier sample, and the ionospheric piercing point position information sample extracted from the data at the ath time point in the first observation sequence sample, the label is the ionospheric disturbance at the a+1th time point in the second observation sequence sample corresponding to the first observation sequence sample. The ionospheric disturbance prediction model predicts according to the receiver identifier sample, the satellite identifier sample, the ionospheric piercing point position information sample, and the ionospheric delay sample, calculates the loss function value between the label and the prediction result, and adjusts the parameters in the ionospheric disturbance prediction model according to the loss function value. The ionospheric disturbance prediction model trained in this way can realize the function of predicting the ionospheric disturbance at the next time point according to the input data at a certain time point.
[0098] In the model use process, the input of the ionospheric disturbance prediction model is the receiver identifier, the satellite identifier, the ionospheric piercing point position information, and the ionospheric delay, and the output is the ionospheric disturbance at the future time point.
[0099] The future time point can be the next future time point or a future time point after a period of time. The model can predict the ionospheric disturbance at the next future time point, and then continue to predict the next time point according to the prediction result of the next future time point, and so on. The ionospheric disturbance at a future time point after a period of time can be predicted.
[0100] It should be noted that the ionospheric disturbance prediction model only uses the data collected by the high frequency receiver, i.e., the second observation sequence sample, in the training process. In the use process, the input data of the ionospheric disturbance prediction model is based on the GNSS receiver and does not need to rely on the high frequency receiver. That is, once the model is trained, the dependence on the high frequency receiver can be eliminated, and only the GNSS receiver is needed.
[0101] In a preferred embodiment, the ionospheric disturbance condition is an ionospheric disturbance level; the ionospheric disturbance level includes: a non-disturbance level, a slight disturbance level, a light disturbance level, a moderate disturbance level, a severe disturbance level, and an extremely severe disturbance level.
[0102] The ionospheric disturbance condition of each time point in the second observation sequence sample is determined according to the ionospheric total electron content rate index, including:
[0103] For each time point in the second observation sequence sample, if the ionospheric total electron content rate index of the time point does not exceed a preset first rate threshold, it is determined that the ionospheric disturbance level of the time point is a non-disturbance level; if the ionospheric total electron content rate index of the time point exceeds the first rate threshold and does not exceed a preset second rate threshold, it is determined that the ionospheric disturbance level of the time point is a slight disturbance level; if the ionospheric total electron content rate index of the time point exceeds the second rate threshold and does not exceed a preset third rate threshold, it is determined that the ionospheric disturbance level of the time point is a light disturbance level; if the ionospheric total electron content rate index of the time point exceeds the third rate threshold and does not exceed a preset fourth rate threshold, it is determined that the ionospheric disturbance level of the time point is a moderate disturbance level; if the ionospheric total electron content rate index of the time point exceeds the fourth rate threshold and does not exceed a preset fifth rate threshold, it is determined that the ionospheric disturbance level of the time point is a severe disturbance level; if the ionospheric total electron content rate index of the time point exceeds the fifth rate threshold, it is determined that the ionospheric disturbance level of the time point is an extremely severe disturbance level.
[0104] The first rate threshold is less than the second rate threshold; the second rate threshold is less than the third rate threshold; the third rate threshold is less than the fourth rate threshold; and the fourth rate threshold is less than the fifth rate threshold.
[0105] In this embodiment, the ionospheric total electron content rate index (ROTI) is used to determine the ionospheric disturbance condition. ROTI reflects the fluctuation degree of the ionospheric total electron content rate, and a higher ROTI value usually indicates the activity of the ionospheric irregular structure.
[0106] The ionospheric disturbance condition refers to an ionospheric disturbance level, and there are totally six ionospheric disturbance levels, namely, no disturbance level, slight disturbance level, light disturbance level, moderate disturbance level, severe disturbance level and extremely severe disturbance level.
[0107]
[0108] Table 1
[0109] It should be noted that the first change rate threshold value is 0.1; the second change rate threshold value is 0.3; the third change rate threshold value is 0.5; the fourth change rate threshold value is 1.0; and the fifth change rate threshold value is 2.0.
[0110] As shown in the above method embodiment, an embodiment of the present application provides an ionospheric disturbance prediction device, which comprises a data acquisition module and an ionospheric disturbance prediction module. Figure 2
[0111] The data acquisition module is configured to acquire the to-be-predicted observation data through a GNSS receiver.
[0112] The ionospheric disturbance prediction module is configured to determine target data according to the to-be-predicted observation data, wherein the target data comprises a receiver identifier, a satellite identifier, ionospheric piercing point position information and ionospheric delay; and input the target data into a trained ionospheric disturbance prediction model in a delayed manner, so that the ionospheric disturbance prediction model predicts the ionospheric disturbance condition at a future time according to the target data.
[0113] The training process of the ionospheric disturbance prediction model comprises:
[0114] A plurality of first observation sequence samples are acquired through a GNSS receiver, and a second observation sequence sample corresponding to each first observation sequence sample is acquired through a high-frequency receiver; wherein the first observation sequence sample and the corresponding second observation sequence sample have the same receiver position coordinates, the same sequence coverage period and the same satellite identifier.
[0115] For each second observation sequence sample, an ionospheric total electron content change rate index at each time in the second observation sequence sample is calculated according to the second observation sequence sample; and an ionospheric disturbance condition at each time in the second observation sequence sample is determined according to the ionospheric total electron content change rate index.
[0116] For each first observation data sample at each time of the first observation sequence sample, an ionospheric disturbance at a next time in a corresponding second observation sequence sample is taken as a label of the first observation data sample; a target data sample is determined according to the first observation data sample; the target data sample and a corresponding label are input into an ionospheric disturbance prediction model, so that the ionospheric disturbance prediction model performs prediction according to the target data sample, and outputs a prediction result; a loss function value is calculated according to the prediction result and the label; and parameters in the ionospheric disturbance prediction model are adjusted according to the loss function value.
[0117] In a preferred embodiment, determining ionospheric delay according to the observation data to be predicted comprises:
[0118] According to the observation data to be predicted, a distance from a GNSS receiver to a satellite, a pseudo-range observation value and a phase observation value are determined;
[0119] According to the distance from the receiver to the satellite, the pseudo-range observation value and the phase observation value, an observation model with ionospheric delay as an unknown parameter is constructed;
[0120] The observation model is solved by a non-difference non-combination method to obtain the ionospheric delay.
[0121] In a preferred embodiment, the ionospheric disturbance is an ionospheric disturbance level; the ionospheric disturbance level comprises: a non-disturbance level, a slight disturbance level, a light disturbance level, a moderate disturbance level, a severe disturbance level and an extremely severe disturbance level;
[0122] The ionospheric disturbance at each time in the second observation sequence sample is determined according to the ionospheric total electron content rate index, comprising:
[0123] For each time point in the second observation sequence sample, if the ionospheric total electron content rate of change index at the time point does not exceed a preset first rate threshold, the ionospheric disturbance level at the time point is determined as a non-disturbance level; if the ionospheric total electron content rate of change index at the time point exceeds the first rate threshold and does not exceed a preset second rate threshold, the ionospheric disturbance level at the time point is determined as a slight disturbance level; if the ionospheric total electron content rate of change index at the time point exceeds the second rate threshold and does not exceed a preset third rate threshold, the ionospheric disturbance level at the time point is determined as a mild disturbance level; if the ionospheric total electron content rate of change index at the time point exceeds the third rate threshold and does not exceed a preset fourth rate threshold, the ionospheric disturbance level at the time point is determined as a moderate disturbance level; if the ionospheric total electron content rate of change index at the time point exceeds the fourth rate threshold and does not exceed a preset fifth rate threshold, the ionospheric disturbance level at the time point is determined as a severe disturbance level; if the ionospheric total electron content rate of change index at the time point exceeds the fifth rate threshold, the ionospheric disturbance level at the time point is determined as an extremely severe disturbance level.
[0124] The first rate threshold is less than the second rate threshold; the second rate threshold is less than the third rate threshold; the third rate threshold is less than the fourth rate threshold; and the fourth rate threshold is less than the fifth rate threshold.
[0125] In a preferred embodiment, the ionospheric piercing point position information is position information of a grid in which the ionospheric piercing point is located.
[0126] It can be understood that the above-mentioned device embodiment is corresponding to the method embodiment of the present application, and can realize the ionospheric disturbance prediction method provided by any one of the above-mentioned method embodiments.
[0127] It should be noted that the device embodiments described above are only schematic, and part or all of the modules can be selected to achieve the purpose of the present embodiment. In addition, in the device embodiment provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which can be realized as one or more communication buses or signal lines. Those skilled in the art can understand and implement it without creative labor.
[0128] On the basis of the above-mentioned method embodiment, another embodiment of the present application provides a terminal device, which comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the ionospheric disturbance prediction method of any one of the embodiments of the present application is realized.
[0129] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present application. The one or more modules can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program in the terminal device.
[0130] The terminal device can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing devices. The terminal device can include, but is not limited to, a processor and a memory.
[0131] 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 gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and connects all parts of the terminal device through various interfaces and lines.
[0132] On the basis of the above-mentioned method embodiment, another embodiment of the present application provides a computer readable storage medium, including a stored computer program, wherein when the computer program runs, the device where the computer readable storage medium is located executes the ionospheric disturbance prediction method described in any one of the above-mentioned method embodiments of the present application.
[0133] The modules / units integrated in the device / terminal equipment, if realized in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. Based on this understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of each method embodiment 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.
[0134] The above is the preferred embodiment of the present application. It should be pointed out 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 predicting ionospheric disturbances, characterized in that, include: Acquire the observation data to be predicted using a GNSS receiver; Based on the observation data to be predicted, target data is determined; wherein, the target data includes: receiver identifier, satellite identifier, ionospheric puncture point location information, and ionospheric delay; The target data is input to the trained ionospheric disturbance prediction model with a delay, so that the ionospheric disturbance prediction model can predict the ionospheric disturbance situation at future times based on the target data; The training process of the ionospheric disturbance prediction model includes: Several first observation sequence samples are acquired through a GNSS receiver, and a second observation sequence sample corresponding to each first observation sequence sample is acquired through a high-frequency receiver; wherein the receiver position coordinates, sequence coverage time periods, and satellite identifiers of the first observation sequence sample and the corresponding second observation sequence sample are the same; For each second observation sequence sample, the rate of change of total ionospheric electron content at each moment in the second observation sequence sample is calculated based on the second observation sequence sample; the ionospheric disturbance at each moment in the second observation sequence sample is determined based on the rate of change of total ionospheric electron content. For each time step of the first observation data sample in the first observation sequence sample, the ionospheric disturbance situation at the next time step in the corresponding second observation sequence sample is used as the label of the first observation data sample; based on the first observation data sample, a target data sample is determined; the target data sample and the corresponding label are input into the ionospheric disturbance prediction model, so that the ionospheric disturbance prediction model makes a prediction based on the target data sample and outputs a prediction result; based on the prediction result and the label, a loss function value is calculated; based on the loss function value, the parameters in the ionospheric disturbance prediction model are adjusted.
2. The ionospheric disturbance prediction method as described in claim 1, characterized in that, Determining the ionospheric delay based on the observation data to be predicted includes: Based on the observation data to be predicted, determine the distance, pseudorange, and phase observations from the GNSS receiver to the satellite; Based on the distance from the receiver to the satellite, the pseudorange observation value, and the phase observation value, an observation model is constructed with ionospheric delay as an unknown parameter. The observation model is solved using a non-difference and non-combination method to obtain the ionospheric delay.
3. The ionospheric disturbance prediction method as described in claim 1, characterized in that, The ionospheric disturbance is referred to as the ionospheric disturbance level; the ionospheric disturbance level includes: no disturbance level, slight disturbance level, mild disturbance level, moderate disturbance level, severe disturbance level, and extremely severe disturbance level; The step of determining the ionospheric disturbance at each moment in the second observation sequence sample based on the ionospheric total electron content change rate index includes: For each moment in the second observation sequence sample, if the rate of change of the total ionospheric electron content at that moment does not exceed a preset first rate of change threshold, then the ionospheric disturbance level at that moment is determined to be no disturbance; if the rate of change of the total ionospheric electron content at that moment exceeds the first rate of change threshold but does not exceed a preset second rate of change threshold, then the ionospheric disturbance level at that moment is determined to be slight disturbance; if the rate of change of the total ionospheric electron content at that moment exceeds the second rate of change threshold but does not exceed a preset third rate of change threshold, then the ionospheric disturbance level at that moment is determined to be significant. The ionospheric disturbance level is determined as follows: if the rate of change of the total electron content in the ionosphere at the specified time exceeds the third rate of change threshold but does not exceed the preset fourth rate of change threshold, the ionospheric disturbance level at the specified time is determined as the moderate disturbance level; if the rate of change of the total electron content in the ionosphere at the specified time exceeds the fourth rate of change threshold but does not exceed the preset fifth rate of change threshold, the ionospheric disturbance level at the specified time is determined as the severe disturbance level; if the rate of change of the total electron content in the ionosphere at the specified time exceeds the fifth rate of change threshold, the ionospheric disturbance level at the specified time is determined as the extremely severe disturbance level. Wherein, the first rate of change threshold is less than the second rate of change threshold; the second rate of change threshold is less than the third rate of change threshold; the third rate of change threshold is less than the fourth rate of change threshold; and the fourth rate of change threshold is less than the fifth rate of change threshold.
4. The ionospheric disturbance prediction method as described in claim 1, characterized in that, The ionospheric puncture point location information is the location information of the grid where the ionospheric puncture point is located.
5. An ionospheric disturbance prediction device, characterized in that, include: Data acquisition module and ionospheric disturbance prediction module; The data acquisition module is used to acquire the observation data to be predicted through a GNSS receiver; The ionospheric disturbance prediction module is used to determine target data based on the observation data to be predicted; wherein, the target data includes: receiver identifier, satellite identifier, ionospheric puncture point location information and ionospheric delay; the target data delay is input into the trained ionospheric disturbance prediction model so that the ionospheric disturbance prediction model can predict the ionospheric disturbance situation at future times based on the target data; The training process of the ionospheric disturbance prediction model includes: Several first observation sequence samples are acquired through a GNSS receiver, and a second observation sequence sample corresponding to each first observation sequence sample is acquired through a high-frequency receiver; wherein the receiver position coordinates, sequence coverage time periods, and satellite identifiers of the first observation sequence sample and the corresponding second observation sequence sample are the same; For each second observation sequence sample, the rate of change of total ionospheric electron content at each moment in the second observation sequence sample is calculated based on the second observation sequence sample; the ionospheric disturbance at each moment in the second observation sequence sample is determined based on the rate of change of total ionospheric electron content. For each time step of the first observation data sample in the first observation sequence sample, the ionospheric disturbance situation at the next time step in the corresponding second observation sequence sample is used as the label of the first observation data sample; based on the first observation data sample, a target data sample is determined; the target data sample and the corresponding label are input into the ionospheric disturbance prediction model, so that the ionospheric disturbance prediction model makes a prediction based on the target data sample and outputs a prediction result; based on the prediction result and the label, a loss function value is calculated; based on the loss function value, the parameters in the ionospheric disturbance prediction model are adjusted.
6. The ionospheric disturbance prediction device as described in claim 5, characterized in that, Determining the ionospheric delay based on the observation data to be predicted includes: Based on the observation data to be predicted, determine the distance, pseudorange, and phase observations from the GNSS receiver to the satellite; Based on the distance from the receiver to the satellite, the pseudorange observation value, and the phase observation value, an observation model is constructed with ionospheric delay as an unknown parameter. The observation model is solved using a non-difference and non-combination method to obtain the ionospheric delay.
7. The ionospheric disturbance prediction device as described in claim 5, characterized in that, The ionospheric disturbance is referred to as the ionospheric disturbance level; the ionospheric disturbance level includes: no disturbance level, slight disturbance level, mild disturbance level, moderate disturbance level, severe disturbance level, and extremely severe disturbance level; The step of determining the ionospheric disturbance at each moment in the second observation sequence sample based on the ionospheric total electron content change rate index includes: For each moment in the second observation sequence sample, if the rate of change of the total ionospheric electron content at that moment does not exceed a preset first rate of change threshold, then the ionospheric disturbance level at that moment is determined to be no disturbance; if the rate of change of the total ionospheric electron content at that moment exceeds the first rate of change threshold but does not exceed a preset second rate of change threshold, then the ionospheric disturbance level at that moment is determined to be slight disturbance; if the rate of change of the total ionospheric electron content at that moment exceeds the second rate of change threshold but does not exceed a preset third rate of change threshold, then the ionospheric disturbance level at that moment is determined to be significant. The ionospheric disturbance level is determined as follows: if the rate of change of the total electron content in the ionosphere at the specified time exceeds the third rate of change threshold but does not exceed the preset fourth rate of change threshold, the ionospheric disturbance level at the specified time is determined as the moderate disturbance level; if the rate of change of the total electron content in the ionosphere at the specified time exceeds the fourth rate of change threshold but does not exceed the preset fifth rate of change threshold, the ionospheric disturbance level at the specified time is determined as the severe disturbance level; if the rate of change of the total electron content in the ionosphere at the specified time exceeds the fifth rate of change threshold, the ionospheric disturbance level at the specified time is determined as the extremely severe disturbance level. Wherein, the first rate of change threshold is less than the second rate of change threshold; the second rate of change threshold is less than the third rate of change threshold; the third rate of change threshold is less than the fourth rate of change threshold; and the fourth rate of change threshold is less than the fifth rate of change threshold.
8. The ionospheric disturbance prediction device as described in claim 5, characterized in that, The ionospheric puncture point location information is the location information of the grid where the ionospheric puncture point is located.
9. A terminal device, characterized in that, The method includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements the ionospheric disturbance prediction method as described in any one of claims 1-4.
10. A computer-readable storage medium, characterized in that, include: A stored computer program, wherein, when the computer program is executed, it controls the device containing the computer-readable storage medium to perform the ionospheric disturbance prediction method as described in any one of claims 1-4.