Early warning method and device for extreme weather events based on Beidou navigation satellite system

By combining Beidou navigation satellite system with machine learning algorithms, an extreme weather event prediction model is built, which solves the problem of insufficient accuracy and real-time accuracy of the weather warning system under rapidly changing weather conditions in the existing technology, and achieves high-precision and real-time extremes The weather event warning improves the accuracy and efficiency of the warning.

CN119087549APending Publication Date: 2024-12-06BEIXING INST OF SPACE INFORMATION TECH (NANJING) CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411255520.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-09
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The prior art cannot achieve high-precision, real-time warning of extreme weather events under rapidly changing weather conditions, and relying on traditional observation equipment and data analysis methods leads to poor early warning effects.

Method used

Using a method based on the combination of Beidou navigation satellite system and machine learning algorithm, the target area location is obtained through Beidou satellite positioning data, and the extreme weather event prediction model is constructed, and the model is trained using convolutional neural network and recurrent neural network, and the time series analysis method is used to process it. Meteorological data, generate dynamic visual warning information and automatically adapt to terminal equipment.

Benefits of technology

It realizes high-precision and real-time warning of extreme weather events, improves the accuracy and efficiency of warnings, and avoids warning delays.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119087549A_ABST
    Figure CN119087549A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of meteorological early warning, and discloses an extreme weather event early warning method based on a Beidou navigation satellite system, and the method comprises the steps: receiving Beidou satellite positioning data of a target region based on a Beidou satellite receiver, and determining the precise position of the target region; obtaining initial meteorological data and historical meteorological data according to the accurate position of the target area; constructing an extreme weather event prediction model and performing model training by adopting a convolutional neural network algorithm and a recurrent neural network algorithm; and inputting the key meteorological features into the model to obtain a prediction result. Compared with an early warning system depending on traditional observation equipment in the prior art, the technical problem that high-precision and real-time extreme weather event early warning cannot be achieved especially under the rapidly-changing weather condition is solved, due to the fact that the Beidou navigation satellite system and the machine learning algorithm are combined for use, the early warning accuracy is improved, and the early warning efficiency is improved. According to the invention, high-precision and real-time extreme weather event early warning is realized, so that the problem of early warning delay is avoided, and the early warning accuracy and efficiency are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of meteorological early warning technology, and in particular to an extreme weather event early warning method, device, equipment and computer program product based on the Beidou navigation satellite system. Background Art

[0002] At present, the early warning mechanism of extreme weather events relies more on ground observation stations and meteorological satellites, and warnings are usually issued by collecting and analyzing data provided by these devices. Although this early warning logic meets basic usage requirements, it is insufficient in terms of real-time and accuracy under rapidly changing weather conditions. For example, when precise positioning and real-time meteorological monitoring of a specific area are required, the existing technology cannot fully meet such high-precision and real-time requirements. In addition, the weather early warning system of the existing technology mainly relies on traditional data analysis methods to predict weather changes, and lacks the ability to use advanced machine learning algorithms for high-precision predictions. However, when the real-time location and accurate meteorological data of the target area are unclear or difficult to obtain, this early warning method that relies on traditional methods will lead to the inability to guarantee the early warning effect, thereby affecting the timeliness and accuracy of the early warning. Therefore, there is an urgent need for a method that can still achieve high-precision and real-time extreme weather event early warning without relying entirely on traditional observation equipment, so as to improve the accuracy and efficiency of the early warning. Summary of the invention

[0003] In response to the above-mentioned technical deficiencies, the main purpose of the present invention is to provide an extreme weather event warning method, device, equipment and computer program product based on the Beidou navigation satellite system, aiming to solve the technical problem that the warning system in the prior art relies on traditional observation equipment and data analysis methods, especially under rapidly changing weather conditions, and cannot achieve high-precision and real-time extreme weather event warnings.

[0004] To achieve the above-mentioned purpose, the present invention provides an extreme weather event early warning method based on the Beidou navigation satellite system. The extreme weather event early warning method based on the Beidou navigation satellite system,

[0005] Preferably, the method comprises:

[0006] Step S10: receiving Beidou satellite positioning data of the target area based on the Beidou satellite receiver, and determining the precise position of the target area by analyzing the Beidou satellite positioning data;

[0007] Step S20: acquiring a current meteorological data source and a historical meteorological data source according to the precise location of the target area, and obtaining initial meteorological data and historical meteorological data respectively through standardization processing;

[0008] Step S30: construct an extreme weather event prediction model, train the model based on historical meteorological data using convolutional neural network and recurrent neural network algorithms, and evaluate and optimize the model using a cross-validation method;

[0009] Step S40: Processing the initial meteorological data by a time series analysis method to obtain key meteorological features and inputting the features into a trained extreme weather event prediction model to obtain extreme weather event prediction results, and issuing extreme weather event warning information to the terminal according to the extreme weather event prediction results.

[0010] Preferably, in step S40, the step of issuing extreme weather event warning information to a terminal according to the extreme weather event prediction result includes:

[0011] Generate dynamic visual warning information according to the type and risk level of the extreme weather event;

[0012] Different terminal devices are automatically adapted according to the dynamic visual warning information, and the best communication channel is selected to send the dynamic visual warning information to the target terminal.

[0013] Preferably, in step S40, after the step of issuing extreme weather event warning information to the terminal according to the extreme weather event prediction result, it also includes: updating the meteorological database according to the actual weather conditions, and optimizing the prediction model according to the updated database.

[0014] Preferably, the process of constructing the extreme weather event prediction model also includes correcting the impact of environmental factors such as terrain, altitude and vegetation coverage on extreme weather events.

[0015] Preferably, during the model training phase, databases between extreme weather event prediction models in different regions are shared.

[0016] Preferably, in the time series analysis method, spectrum analysis and wavelet transform methods are used to capture periodic changes and sudden anomalies in the initial meteorological data.

[0017] Preferably, the warning information is pushed to the user terminal device through an API interface, showing the area and risk level expected to be affected by the extreme weather event.

[0018] Preferably, the extreme weather event warning device based on the Beidou navigation satellite system includes:

[0019] A positioning module, used for receiving Beidou satellite positioning data of a target area based on a Beidou satellite receiver, and determining a precise position of the target area by analyzing the Beidou satellite positioning data;

[0020] A data acquisition and processing module is used to acquire the current meteorological data source and the historical meteorological data source according to the precise location of the target area, and obtain the initial meteorological data and the historical meteorological data respectively after standardized processing;

[0021] Model building and training module, which is used to build extreme weather event prediction models, train models based on historical meteorological data using convolutional neural network and recurrent neural network algorithms, and evaluate and optimize models using cross-validation methods;

[0022] The feature extraction and warning issuance module is used to process the initial meteorological data through a time series analysis method to obtain key meteorological features and input the key features into the trained extreme weather event prediction model to obtain extreme weather event prediction results, and issue extreme weather event warning information to the terminal according to the extreme weather event prediction results.

[0023] Preferably, the extreme weather event warning device based on the Beidou navigation satellite system includes:

[0024] A memory, a processor, and an extreme weather event warning program based on the Beidou navigation satellite system stored in the memory and executable on the processor, wherein the extreme weather event warning program based on the Beidou navigation satellite system, when executed by the processor, implements the extreme weather event warning method based on the Beidou navigation satellite system as described in any one of claims 1 to 7.

[0025] Preferably, the computer program product includes an extreme weather event warning program based on the Beidou navigation satellite system, and when the extreme weather event warning program based on the Beidou navigation satellite system is executed by a processor, it implements the extreme weather event warning method based on the Beidou navigation satellite system as described in any one of claims 1 to 7.

[0026] The beneficial effects of the present invention are as follows: compared with the early warning system in the prior art that relies on traditional observation equipment, especially under rapidly changing weather conditions, the technical problem of being unable to achieve high-precision and real-time early warning of extreme weather events is solved. Since the present invention combines the Beidou navigation satellite system with a machine learning algorithm, high-precision and real-time early warning of extreme weather events is achieved, thereby avoiding the problem of early warning delays and improving the accuracy and efficiency of early warnings. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 This is a flow chart of a first embodiment of an extreme weather event early warning method based on the Beidou navigation satellite system of the present invention.

[0029] Figure 2 This is a diagram of the extreme weather event warning equipment based on the Beidou navigation satellite system of the present invention. DETAILED DESCRIPTION

[0030] 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.

[0031] Embodiment 1: Figure 1 , which is a flow chart of a first embodiment of an extreme weather event early warning method based on the BeiDou navigation satellite system according to the present invention.

[0032] Step S10: receiving Beidou satellite positioning data of the target area based on the Beidou satellite receiver, and determining the precise position of the target area by analyzing the Beidou satellite positioning data;

[0033] It should be noted that the Beidou satellite receiver refers to a device used to receive signals transmitted by the Beidou system and calculate the position of the receiver, including an antenna module, a signal processing module and an output interface; Beidou satellite positioning data refers to a data set received from the Beidou satellite system containing information such as timestamp, satellite number, signal strength, etc., including original pseudorange data and navigation messages; the precise position of the target area refers to the specific latitude and longitude coordinates of the target area on the earth calculated through high-precision positioning technology, such as differential positioning or carrier phase positioning technology, including longitude, latitude and elevation.

[0034] Step S20: acquiring a current meteorological data source and a historical meteorological data source according to the precise location of the target area, and obtaining initial meteorological data and historical meteorological data respectively through standardization processing;

[0035] It should be noted that the current meteorological data source refers to the system that collects meteorological conditions information at the current moment, including satellite meteorological data and ground meteorological station data; the historical meteorological data source refers to the database that stores meteorological information within a certain period of time in the past, including historical temperature records, precipitation, wind speed and other data; the initial meteorological data refers to the latest meteorological data collected from the current meteorological data source and cleaned and formatted, including real-time temperature, humidity, wind direction; historical meteorological data refers to meteorological data in the past time period extracted from the historical meteorological data source, including average temperature, total precipitation, maximum wind speed, etc.

[0036] Step S30: construct an extreme weather event prediction model, train the model based on historical meteorological data using convolutional neural network and recurrent neural network algorithms, and evaluate and optimize the model using a cross-validation method;

[0037] It should be understood that in order to more accurately predict extreme weather events, improvements have been made to the existing convolutional neural network (CNN) and recurrent neural network (RNN, especially LSTM) algorithms. The specific implementation steps are as follows:

[0038] 1. Improved Convolutional Neural Network (CNN)

[0039] In extreme weather forecasting, meteorological data usually have complex multidimensional features, and the spatial features at different time points are highly correlated. To this end, an improved multi-scale convolutional neural network (MS-CNN) is introduced to better capture the multi-scale spatial features in meteorological data.

[0040] Multi-scale convolution layer: The improved convolution operation can use convolution kernels of different scales and combine their results. The formula is as follows:

[0041] in,

[0042] f i,j,k : This value represents the convolution result of position (i, j) in the kth feature map;

[0043] S: the number of convolution kernel groups;

[0044] M s , N s : These two parameters determine the size of the convolution kernel. The convolution kernel is a two-dimensional matrix that slides over the image to extract local features in image processing.

[0045] x i+m,j+n : is the value of the input raw data (such as image data), which represents the input data at position (i+m,j+n). The convolution operation processes the input data by sliding each convolution window step by step.

[0046] w m,n,k,s : is the weight of the convolution kernel, which represents the weight of the kth convolution kernel in the sth group of convolution kernels at position (m,n). Each convolution kernel performs a dot multiplication operation with the input data to calculate the features.

[0047] b k,s : is the bias term of the kth convolution kernel in the sth group of convolution kernels. This bias term will be added to the convolution result and is usually used to improve the fitting ability of the model.

[0048] By combining convolution kernels of different scales, this method can simultaneously capture large-scale (such as atmospheric circulation) and small-scale (such as localized cloud clusters) features in weather images, helping to more accurately identify extreme weather patterns.

[0049] 2. Improved Long Short-Term Memory Network (LSTM)

[0050] When processing meteorological time series data, traditional LSTM may not be able to fully utilize the nonlinear trends and periodic features in meteorological data. To this end, a periodicity-enhanced LSTM (PE-LSTM) is proposed to capture the periodic features in weather data by introducing periodic memory units. The improved LSTM formula adds a periodic memory unit at each time step. To capture the periodic pattern in the data: Represents an estimated value or model prediction value at time t, where T represents the cycle length of the meteorological data (such as daily cycle, annual cycle). and Used to adjust the weights of periodic memory units at different time steps, where t represents the current time step or time point. As time goes by, t increases continuously, which is used to represent the corresponding feature or signal value at different time points. Update memory unit: The improved memory unit update formula is:

[0051] Among them, C t is the unit state at the current moment, f t is the forget gate, which controls how much of the previous cell state is retained. t-1 is the unit state at the previous moment, i t is the input gate, which controls how much new information is allowed into the cell state, It is the candidate unit state adjusted based on periodicity at the current moment. PE-LSTM can more accurately capture the periodic changes in weather data when memorizing and predicting extreme weather events, thereby improving the accuracy of predictions. In extreme weather predictions, it can enhance the model's ability to recognize periodic weather patterns (such as seasonal rainfall or periodic temperature changes), thereby improving the prediction accuracy of extreme weather events.

[0052] Step S40: Processing the initial meteorological data by a time series analysis method to obtain key meteorological features and inputting the features into a trained extreme weather event prediction model to obtain extreme weather event prediction results, and issuing extreme weather event warning information to the terminal according to the extreme weather event prediction results.

[0053] It should be noted that when processing initial meteorological data, the time series analysis method can extract the most critical meteorological features for the prediction of extreme weather events by decomposing the trend, seasonality, periodicity and randomness of the data. These features may include the temperature change rate, pressure gradient change, etc. After extraction, these features will be input into the trained prediction model to further enhance the prediction accuracy of the model.

[0054] It is understandable that the prediction model of extreme weather events relies on the accurate extraction and analysis of multiple key meteorological features. Since extreme weather events have complex nonlinear characteristics, time series analysis can not only identify short-term changes in meteorological data, but also capture long-term trends and periodic characteristics, thus providing strong support for the issuance of warning information.

[0055] It should be understood that the prediction results of extreme weather events have a certain probability. Therefore, when issuing warning information, the warning system will grade warnings according to the credibility of the prediction results to ensure the reliability and timeliness of the information. For example, when the results of the prediction model show high credibility, the warning information will be issued with a higher priority so that end users can take timely response measures.

[0056] In the second embodiment, in step S40, the step of issuing extreme weather event warning information to the terminal according to the extreme weather event prediction result includes:

[0057] Generate dynamic visual warning information according to the type and risk level of the extreme weather event;

[0058] Different terminal devices are automatically adapted according to the dynamic visual warning information, and the best communication channel is selected to send the dynamic visual warning information to the target terminal.

[0059] It should be noted that the types of extreme weather events can include different types of natural disasters such as heavy rain, typhoons, thunderstorms, and blizzards. Each extreme weather event will be divided into different risk levels according to the scope, intensity, and duration of its impact, such as "low risk", "medium risk", "high risk", etc. The system will generate dynamic visual warning information based on these factors, which will visually display the real-time dynamics of weather events, including rainfall, wind speed, wind direction changes and other key information. These data will be displayed in the form of icons, heat maps, charts, animations, etc. to enhance the comprehensibility and operability of the warning.

[0060] It is understandable that the types of terminal devices and communication environments may vary, and the system needs to automatically adjust the presentation of warning information based on these differences. For example, on a smartphone, the system will generate a simplified version of the warning information, such as focusing on core data such as wind speed and rainfall, and using weather icons to convey basic information; on devices such as desktop computers or tablets, the system can display more detailed information, such as typhoon path forecasts, wind speed trend charts, and the degree of impact in different areas. At this point, dynamic visual warnings may include animated radar maps that show the progress of real-time weather changes. In the in-vehicle navigation system, the system can directly mark the warning area on the map and indicate whether it is recommended to re-plan the driving route.

[0061] It should be understood that the process of selecting the best communication channel is to ensure that the warning information can reach the user terminal quickly and accurately, and can maintain efficient transmission in different network environments. For example, if the target terminal is in a good Wi-Fi environment, the system will give priority to sending detailed dynamic warning information through mobile applications or emails; if the user is in a mobile network environment, the system may choose to send warning information through push notifications or text messages to avoid consuming a lot of data traffic and time. In the case of unstable network, such as when the user is in a remote area or the mobile signal is weak, the system will automatically reduce the complexity of the information, simplify the image or video content, and give priority to sending emergency text notifications to ensure that the warning information can arrive in time. For example, assuming that a typhoon is about to occur in a certain area, the system predicts that the typhoon will affect the area in the next 24 hours by analyzing real-time weather data. First, the system generates a visual warning map based on the type of typhoon (e.g., typhoon) and risk level (e.g., high risk), including dynamic information such as the typhoon's movement path, expected wind speed, and rainfall. The system then generates adaptive warning information for different terminal devices, such as sending alerts with icons and simple maps on smartphones, while displaying animations of typhoon paths and detailed trend forecasts on desktop computers. The system also selects the most appropriate communication channel based on the user's network connection, such as sending full warning content via Wi-Fi environment and sending simplified emergency warnings via SMS.

[0062] In addition, the present invention also provides an extreme weather event warning device based on the Beidou navigation satellite system, please refer to Figure 2 , the extreme weather event warning device based on the Beidou navigation satellite system includes:

[0063] A positioning module, used for receiving Beidou satellite positioning data of a target area based on a Beidou satellite receiver, and determining a precise position of the target area by analyzing the Beidou satellite positioning data;

[0064] A data acquisition and processing module is used to acquire the current meteorological data source and the historical meteorological data source according to the precise location of the target area, and obtain the initial meteorological data and the historical meteorological data through standardized processing;

[0065] A model building and training module is used to build an extreme weather event prediction model based on the initial meteorological data and historical meteorological data, use convolutional neural network and recurrent neural network algorithms to train the model, and evaluate and optimize the model through a cross-validation method;

[0066] The feature extraction and warning issuance module is used to process the initial meteorological data through a time series analysis method to obtain key meteorological features and input them into the trained extreme weather event prediction model, and issue extreme weather event warning information to the terminal according to the extreme weather event prediction results.

[0067] The extreme weather event warning device based on the Beidou navigation satellite system provided by the present invention adopts an extreme weather event warning method based on the Beidou navigation satellite system in the above embodiment, which can solve the technical problem of extreme weather event warning based on the Beidou navigation satellite system. Compared with the prior art, the beneficial effects of the extreme weather event warning device based on the Beidou navigation satellite system provided by the present invention are the same as the beneficial effects of the extreme weather event warning method based on the Beidou navigation satellite system provided by the above embodiment, and the other technical features of the extreme weather event warning device based on the Beidou navigation satellite system are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0068] The present invention provides an extreme weather event warning device based on the Beidou navigation satellite system, and the extreme weather event warning device based on the Beidou navigation satellite system includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by at least one processor, and the instructions are executed by at least one processor, so that at least one processor can execute an extreme weather event warning method based on the Beidou navigation satellite system in the above-mentioned embodiment 1. An extreme weather event warning device based on the Beidou navigation satellite system in the embodiment of the present invention may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. An extreme weather event warning device based on the Beidou navigation satellite system is only an example, and should not bring any limitation to the functions and scope of use of the embodiments of the present invention. An extreme weather event warning device based on the Beidou navigation satellite system may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of an extreme weather event warning device based on the Beidou navigation satellite system are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 may allow an extreme weather event warning device based on the Beidou navigation satellite system to communicate wirelessly or wired with other devices to exchange data. Although the figure shows an extreme weather event warning device based on the Beidou navigation satellite system with various systems, it should be understood that it is not required to implement or have all the systems shown.Greater or fewer systems may alternatively be implemented or provided.

[0069] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for early warning of extreme weather events based on the Beidou navigation satellite system. The computer program product provided by the present invention can solve the technical problem of early warning of extreme weather events based on the Beidou navigation satellite system. Compared with the prior art, the beneficial effects of the computer program product provided by the present invention are the same as the beneficial effects of the method for early warning of extreme weather events based on the Beidou navigation satellite system provided by the above-mentioned embodiment, which will not be repeated here.

[0070] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through a communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present invention are executed.

[0071] It should be understood that the various parts disclosed in the present invention can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0072] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for early warning of extreme weather events based on the Beidou navigation satellite system, characterized in that: The method comprises: Step S10: receiving Beidou satellite positioning data of the target area based on the Beidou satellite receiver, and determining the precise position of the target area by analyzing the Beidou satellite positioning data; Step S20: acquiring a current meteorological data source and a historical meteorological data source according to the precise location of the target area, and obtaining initial meteorological data and historical meteorological data respectively through standardization processing; Step S30: construct an extreme weather event prediction model, train the model based on historical meteorological data using convolutional neural network and recurrent neural network algorithms, and evaluate and optimize the model using a cross-validation method; Step S40: Processing the initial meteorological data by a time series analysis method to obtain key meteorological features and inputting the features into a trained extreme weather event prediction model to obtain extreme weather event prediction results, and issuing extreme weather event warning information to the terminal according to the extreme weather event prediction results.

2. The extreme weather event early warning method according to claim 1, characterized in that: In step S40, the step of issuing extreme weather event warning information to the terminal according to the extreme weather event prediction result includes: Generate dynamic visual warning information according to the type and risk level of the extreme weather event; Different terminal devices are automatically adapted according to the dynamic visual warning information, and the best communication channel is selected to send the dynamic visual warning information to the target terminal.

3. The extreme weather event early warning method according to claim 1, characterized in that: In the step S40, after the step of issuing extreme weather event warning information to the terminal according to the extreme weather event prediction result, it also includes: updating the meteorological database according to the actual weather conditions, and optimizing the prediction model according to the updated database.

4. The extreme weather event early warning method according to claim 1, characterized in that: The process of constructing the extreme weather event prediction model also includes correcting the impact of terrain, altitude and vegetation coverage environmental factors on extreme weather events.

5. The extreme weather event early warning method according to claim 1, characterized in that: The model training phase shares databases between extreme weather event prediction models in different regions.

6. The extreme weather event early warning method according to claim 1, characterized in that: In the time series analysis method, spectrum analysis and wavelet transform methods are used to capture periodic changes and sudden anomalies in initial meteorological data.

7. The extreme weather event early warning method according to claim 1, characterized in that: The warning information is pushed to the user's terminal device through the API interface, showing the area and risk level expected to be affected by the extreme weather event.

8. An extreme weather event warning device based on the Beidou navigation satellite system, characterized in that: The extreme weather event early warning device based on the Beidou navigation satellite system includes: A positioning module, used for receiving Beidou satellite positioning data of a target area based on a Beidou satellite receiver, and determining a precise position of the target area by analyzing the Beidou satellite positioning data; A data acquisition and processing module is used to acquire the current meteorological data source and the historical meteorological data source according to the precise location of the target area, and obtain the initial meteorological data and the historical meteorological data respectively after standardized processing; Model building and training module, which is used to build extreme weather event prediction models, train models based on historical meteorological data using convolutional neural network and recurrent neural network algorithms, and evaluate and optimize models using cross-validation methods; The feature extraction and warning issuance module is used to process the initial meteorological data through a time series analysis method to obtain key meteorological features and input the key features into the trained extreme weather event prediction model to obtain extreme weather event prediction results, and issue extreme weather event warning information to the terminal according to the extreme weather event prediction results.

9. An extreme weather event warning device based on the Beidou navigation satellite system, characterized in that: The extreme weather event warning equipment based on the Beidou navigation satellite system includes: A memory, a processor, and an extreme weather event warning program based on the Beidou navigation satellite system stored in the memory and executable on the processor, wherein the extreme weather event warning program based on the Beidou navigation satellite system, when executed by the processor, implements the extreme weather event warning method based on the Beidou navigation satellite system as described in any one of claims 1 to 7.

10. A computer program product, characterized in that The computer program product includes an extreme weather event warning program based on the Beidou navigation satellite system. When the extreme weather event warning program based on the Beidou navigation satellite system is executed by a processor, it implements the extreme weather event warning method based on the Beidou navigation satellite system as described in any one of claims 1 to 7.

Citation Information

Cited By

  • Photovoltaic station tropical cyclone early warning method, device, equipment and medium

    CN119832711A