Cold vortex path ensemble prediction method and device

Abstract

The application discloses a cold vortex path set prediction method and device, relates to the technical field of meteorological data processing, and comprises the following steps: determining the real-time position of a cold vortex based on the latest zero field data of a global model; selecting N member paths with the minimum path error in each member cold vortex path of set prediction to perform arithmetic averaging, so as to obtain a corrected path, wherein the path error is the distance between the current time cold vortex center position of set prediction and the real-time position; obtaining the prediction data of the center position and path of the cold vortex of all prediction members of set prediction, and performing path clustering through a DSBCAN algorithm. Cold vortex path prediction products are determined based on path clustering and the corrected path, and objective and accurate prediction results can be obtained based on the products combined with the results after the 500-hPa situation field of an initial date is clustered. Further, the defects in the prior art are solved.

Description

Technical Field

[0001] This invention relates to the field of meteorological data processing technology, specifically to a method and apparatus for forecasting cold vortex path ensembles. Background Technology

[0002] Cold vortices, such as the Northeast Cold Vortex, refer to cold low-pressure systems that persist in the upper atmosphere (e.g., at 500 hPa) in central and northeastern my country, often causing strong convection, cooling, and persistent precipitation.

[0003] In related technologies, operational identification of cold vortices includes objective identification and subjective identification. Objective identification is based on factors such as isobaric geopotential height, temperature, and wind field to automatically identify cold vortices. One method uses an 8-point method to identify the low-value center of a cold vortex based on geopotential height, but this method ignores the coldness and circulation characteristics of the cold vortex. Another method utilizes geopotential height, wind field, and temperature field factors, but the selected cold vortex activity range is relatively small, and when tracking cold vortex processes, only the longitude of the center is specified to be continuous, without requiring changes in latitude. A third method uses constraints such as warm front parameters representing temperature gradient changes to identify cold vortices. This method considers the coldness characteristics of the cold vortex and the characteristics of a closed low-pressure circulation, but when determining a closed circulation, it only requires that the zonal winds at two adjacent points north of the candidate point be easterly or calm, which is insufficient. This study updates the identification algorithm based on existing cold vortex identification methods, comprehensively considering the low-value center of geopotential height and temperature field, the cyclonic circulation characteristics of the wind field, and the continuity characteristics of the low-vortex center. This research focuses on cold vortex identification and climatological statistical characteristic analysis. Patent CN118823384A developed a method and system for objective identification of cold eddies based on high spatiotemporal resolution data using pattern recognition or machine learning. It seeks the local minimum of the potential height and screens candidate points, but does not consider the cold characteristics of cold eddies.

[0004] In summary, the cold vortex forecasting technology has various defects, resulting in inaccurate and unobjective forecasts. Summary of the Invention

[0005] The main objective of this invention is to provide a method and apparatus for predicting cold vortex path ensembles, in order to address the shortcomings of related technologies.

[0006] To achieve the above objectives, according to a first aspect of the present invention, a method for ensemble forecasting of cold vortex paths is provided, comprising: determining the real-time location of a cold vortex based on the latest zero-field data from a global model; selecting N member paths with the smallest path errors among the cold vortex paths in the ensemble forecast and performing an arithmetic average to obtain a corrected path, wherein the path error is the distance between the current location of the cold vortex center in the ensemble forecast and the real-time location; acquiring forecast data of the center locations and paths of the cold vortices of all forecast members in the ensemble forecast and performing path clustering using the DSBCAN algorithm, wherein the superposition of the path clustering results and the cold vortex center locations of the corrected path is used as a cold vortex path forecasting product.

[0007] Optionally, the method further includes: if the cold vortex belongs to a long-lived cold vortex, then determine the category of its 500 hPa situational field, and superimpose the path corresponding to the category onto the cold vortex path forecast product before outputting it; if the cold vortex does not belong to a long-lived cold vortex, then output the cold vortex path forecast product.

[0008] Optionally, before determining the category of its 500 hPa morphological field, the method further includes: obtaining long-lived cold vortex events from a cold vortex history database; and clustering the long-lived cold vortex events to obtain the 500 hPa morphological field of the initial date of different categories of long-lived cold vortex events.

[0009] Optionally, if the cold vortex is a long-lived cold vortex, determining its 500 hPa situation field category includes: comparing the 500 hPa situation field on the first day of the long-lived cold vortex's inception with the anomaly correlation coefficients of the situation fields of different categories of cold vortices obtained through clustering to determine its category.

[0010] Optionally, the path error is the distance between the current location of the cold vortex center and the real-time location predicted by the ensemble forecast.

[0011] According to a second aspect of the present invention, a cold vortex path ensemble forecasting device is provided, comprising: a location determination unit for determining the real-time location of a cold vortex based on the latest zero-field data from a global model; a corrected path determination unit for selecting N member paths with the smallest path errors among the cold vortex paths of each member of the ensemble forecast and performing an arithmetic average to obtain a corrected path; and a cold vortex path forecasting product generation unit for acquiring forecast data of the center positions and paths of the cold vortices of all forecast members of the ensemble forecast and performing path clustering using the DSBCAN algorithm, wherein the superposition of the path clustering results and the cold vortex center positions of the corrected paths is used as the cold vortex path forecasting product.

[0012] Optionally, the device further includes: a first output unit, configured to determine the category of the 500 hPa geopotential field if the cold vortex is a long-lived cold vortex, and then superimpose the path corresponding to the category onto the cold vortex path forecast product and output it; and a second output unit, configured to output the cold vortex path forecast product if the cold vortex is not a long-lived cold vortex.

[0013] Optionally, the apparatus further includes: an event acquisition unit for acquiring long-lived cold vortex events from a cold vortex history database; and a clustering unit for clustering the long-lived cold vortex events to obtain the 500 hPa situational field of the initial date of different categories of long-lived cold vortex events.

[0014] According to a third aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing the computer to perform the method described in any one of the first aspects.

[0015] According to a fourth aspect of the present invention, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to cause the at least one processor to perform the method described in any implementation of the first aspect.

[0016] The cold vortex path ensemble forecasting method of the present invention includes: determining the real-time position of the cold vortex based on the latest zero-field data from a global model; selecting N member paths with the smallest path errors from the ensemble forecast member cold vortex paths and performing an arithmetic average to obtain a corrected path, wherein the path error is the distance between the current position of the cold vortex center in the ensemble forecast and the real-time position; acquiring the forecast data of the center positions and paths of the cold vortices of all forecast members in the ensemble forecast, and performing path clustering using the DSBCAN algorithm, wherein the superposition of the path clustering results and the cold vortex center positions from the corrected path is used as the cold vortex path forecast product. Determining the cold vortex path forecast product based on path clustering and the corrected path lays the foundation for objectively and accurately forecasting the final cold vortex path. This overcomes the shortcomings of related technologies. Attached Figure Description

[0017] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1This is a flowchart of the cold vortex path set prediction method according to an embodiment of the present invention;

[0019] Figure 2 This is a schematic diagram of the first application of the cold vortex path set prediction method according to an embodiment of the present invention;

[0020] Figure 3 This is a schematic diagram of the fifth application of the cold vortex path set prediction method according to an embodiment of the present invention;

[0021] Figure 4 This is a schematic diagram of the overall process of the cold vortex path set prediction method according to an embodiment of the present invention;

[0022] Figure 5 This is a schematic diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0023] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of the invention described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0026] According to embodiments of the present invention, a method for predicting cold vortex path ensembles is provided, such as... Figure 1 As shown, steps 101 to 103 are included below:

[0027] Step 101: Determine the real-time location of the cold vortex based on the latest zero-field data from the global model.

[0028] In this step, global model zero-field data, such as numerical weather prediction models like ECMWF and GFS, are used to simulate atmospheric motion through mathematical equations. Zero-field data refers to the actual observational data (such as temperature, pressure, and wind field) used when the model was initialized at the latest time (e.g., UTC 00), serving as the initial conditions for the forecast. When determining the real-time location, the latest global model zero-field data (such as 500 hPa geopotential height, temperature, and wind fields) is used to identify the coordinates of the cold vortex center.

[0029] Step 102: Select the N member paths with the smallest path error among the cold vortex paths in the ensemble forecast and perform an arithmetic average to obtain the corrected path, where the path error is the distance between the current position of the cold vortex center in the ensemble forecast and the real-time position.

[0030] As an optional implementation of this embodiment, the path error is the distance between the current location of the cold vortex center and the real-time location predicted by the set forecast.

[0031] In this step, the N member paths with the smallest path errors from the latest ensemble forecasts are selected and their arithmetic averages are calculated. mean =AVE[Min|Dis(PE-P0)|1 N The corrected path is obtained. The path error refers to the distance between the ensemble forecast of the current location of the cold vortex center and the zero field determination of the cold vortex center location.

[0032] As an optional implementation of this embodiment, forecast data of the center position and path of cold vortices of all forecast members of the ensemble forecast are obtained, and path clustering is performed by the DSBCAN algorithm. The superposition of the path clustering result and the cold vortex center position of the corrected path is used as the cold vortex path forecast product.

[0033] In this optional implementation, the forecast data of the center position and path of the cold vortex of all forecast members of the latest acquired ensemble forecast system are used. Figure 2 Intensity binomial mapping (DBSCAN), a method determines a region as high-density if there are a sufficient number of points within its neighborhood radius. This region can be expanded into a cluster. A cluster is expanded by connecting points with high density; points that cannot be assigned to any cluster are considered noise points.

[0034] The cold vortex track forecast product is an overlay of DBSCAN clustering of the ensemble forecast track and the real-time corrected location of the cold vortex center.

[0035] As an optional implementation of this embodiment, the method further includes: if the cold vortex belongs to a long-lived cold vortex, then determine the category of its 500 hPa situational field, and superimpose the path corresponding to the category onto the cold vortex path forecast product and output it; if the cold vortex does not belong to a long-lived cold vortex, then output the cold vortex path forecast product.

[0036] In this optional implementation, the lifespan of the cold eddy in the latest model forecast is used to determine whether it belongs to a long lifespan (e.g., more than 8 days). If it does, the category is determined by comparing the anomaly correlation coefficient between the 500 hPa morphological field on the first day of the cold eddy's initiation and the morphological fields of different categories of cold eddies obtained by K-means clustering. The path background obtained by clustering is then superimposed on the path forecast of the cold eddy path forecast product. If it does not belong to a long lifespan cold eddy, the cold eddy path forecast product is output.

[0037] As an optional implementation of this embodiment, before determining the category of its 500 hPa situational field, the method further includes: obtaining long-lived cold vortex events from a cold vortex history database; and clustering the long-lived cold vortex events to obtain the 500 hPa situational field of the initial date of different categories of long-lived cold vortex events.

[0038] In this optional implementation, a cold vortex history database from 1961 to 2024 is established using 500 hPa geopotential height field, temperature field, and wind field data from NCEP / NCAR reanalysis data from 1961 to 2024 through an objective identification method.

[0039] The identification of cold vortices is based on the meteorological definition of cold vortices, and wind field identification is added to ensure that the cold vortex system meets the characteristics of cyclonic circulation. The specific identification process is as follows:

[0040] (1) In the 500 hPa pressure level of the study area, if the second partial derivative of the zonal temperature of one of the nine grid points, including any low point of potential height, is positive, then the low point of potential height is the potential cold vortex center grid point.

[0041] (2) To determine whether there is a cyclonic circulation at the potential cold vortex center, among the 8 grid points around the low value center, if the zonal wind speed is less than zero at the north grid point, the zonal wind speed is greater than zero at the south grid point, the meridional wind speed is greater than zero at the east grid point, and the meridional wind speed is less than zero at the west grid point, then it is considered that there is a cyclonic circulation at that point.

[0042] (3) At any given time, all potential cold vortex center grid points within the 5°×5° grid box are considered to be within the same cold vortex. Among them, the grid point with the lower potential height value is considered to be the main center grid point of the cold vortex.

[0043] (4) In any two consecutive time intervals (6 hours apart), if the distances of the two central grid points that meet the above conditions from the latitude and longitude directions are both less than 10 degrees, then they are considered to be the same cold vortex. Otherwise, they belong to two independent cold vortices.

[0044] Taking a cold vortex that lasted for 10 days from November 23 to December 1, 2024 as an example, a schematic diagram of its intensity change is given, as follows: Figure 3 .

[0045] Based on the established cold vortex historical database from 1961 to 2024, cases of cold vortices with a lifespan exceeding 8 days were selected. There were 36 cases in spring, with an average lifespan of 9 days and a longest lifespan of 12 days; 69 cases in summer, with an average lifespan of 10 days and a longest lifespan of 15 days; 31 cases in autumn, with an average lifespan of 9 days and a longest lifespan of 15 days; and 62 cases in winter, with an average lifespan of 9 days and a longest lifespan of 19 days.

[0046] Furthermore, long-lived cases were selected from the cold vortex history database, and K-means clustering was performed on these long-lived cold vortex events. Using an unsupervised clustering algorithm with distance as the similarity metric, the data was iteratively divided into K clusters, ensuring that data within the same cluster was as similar as possible, while differences between different clusters were significant. Subsequently, the 500 hPa morphological field of the initial date of different categories of long-lived cold vortex events was presented.

[0047] The specific steps of K-means clustering are as follows: The k-means algorithm uses k as a parameter to divide n objects into k clusters, ensuring high similarity within clusters and low similarity between clusters. First, k objects are randomly selected, each initially representing the mean or center of a cluster. Then, for each remaining object, it is assigned to the nearest cluster based on its distance from the cluster centers; the mean of each cluster is then recalculated. This process is repeated until the criterion function converges.

[0048] In the specific calculation, the initial values ​​for clustering are improved from the standard k-means initial value selection. The algorithm steps are as follows:

[0049] (1) Randomly select a center among the data points.

[0050] (2) For each data point x that has not yet been selected, calculate d(x,u i ), which is the distance between x and the nearest center that has been selected.

[0051] (3) A new data point is randomly selected as the new center using a weighted probability distribution, where the probability of the selected point is proportional to the probability of the selected data point. d(x,u i It is directly proportional to.

[0052] (4) Repeat steps 2 and 3 until k centers are selected (i.e., j = k).

[0053] (5) Now that the initial centers have been selected, continue to use standard k-means clustering.

[0054] K-means clustering is performed on long-lived events. Using an unsupervised clustering algorithm, distance is used as a similarity metric. The data is iteratively divided into K clusters, so that the data within the same cluster are as similar as possible, and the differences between different clusters are significant.

[0055] As an optional implementation of this embodiment, if the cold vortex belongs to a long-lived cold vortex, the category of its 500 hPa situation field is determined by comparing the anomaly correlation coefficient of the 500 hPa situation field on the first day of the start of the long-lived cold vortex with the situation fields of different categories of cold vortices obtained by clustering.

[0056] In this optional implementation, if it has a long lifespan (e.g., more than 8 days), the category is determined by comparing the anomaly correlation coefficient between the 500 hPa situation field on the first day of the cold vortex's initiation and the situation fields of different categories of cold vortices obtained by K-means clustering.

[0057] refer to Figure 4 The overall flowchart of cold vortex ensemble forecasting is illustrated. The objective cold vortex identification method used in this embodiment comprehensively considers the dynamic and thermodynamic properties of the cold vortex system and establishes a real-time monitoring and ensemble forecasting process for cold vortices. A comparison of the forecast and actual data for a cold vortex event lasting 9 days in late November 2024 shows that the actual data product clearly displays the center location and movement path of the cold vortex event, while the ensemble forecast product can provide forecasts of the cold vortex path and intensity for the next two weeks, filling a gap in cold vortex forecasting products in forecasting operations.

[0058] Based on a comprehensive consideration of the dynamic and thermodynamic properties of cold vortices, we will develop an objective identification algorithm suitable for frontline weather forecasting operations, establish a historical case database of cold vortices, and develop an objective forecasting system for the location, path, and intensity of cold vortex centers based on global numerical weather prediction models.

[0059] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0060] According to an embodiment of the present invention, a cold vortex path ensemble forecasting device is also provided, comprising: a location determination unit for determining the real-time location of the cold vortex based on the latest zero-field data from the global model; a corrected path determination unit for selecting the N member paths with the smallest path errors among the cold vortex paths of each member of the ensemble forecast and performing an arithmetic average to obtain a corrected path; and a cold vortex path forecasting product generation unit for acquiring the forecast data of the center positions and paths of the cold vortices of all forecast members of the ensemble forecast and performing path clustering using the DSBCAN algorithm, wherein the superposition of the path clustering results and the cold vortex center positions of the corrected paths is used as the cold vortex path forecasting product.

[0061] As an optional implementation of this embodiment, the device further includes: a first output unit, configured to determine the category of the 500 hPa situational field if the cold vortex belongs to a long-lived cold vortex, and then superimpose the path corresponding to the category onto the cold vortex path forecast product and output it; and a second output unit, configured to output the cold vortex path forecast product if the cold vortex does not belong to a long-lived cold vortex.

[0062] As an optional implementation of this embodiment, the device further includes: an event acquisition unit, used to acquire long-lived cold vortex events from a cold vortex history database; and a clustering unit, used to cluster the long-lived cold vortex events to obtain the 500 hPa situational field of the initial date of different categories of long-lived cold vortex events.

[0063] According to embodiments of the present invention, the present invention also provides an electronic device, the electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to implement the methods described in any of the above embodiments.

[0064] According to embodiments of the present invention, the present invention also provides a readable storage medium storing computer instructions that enable a computer to perform the methods described in any of the above embodiments when executed.

[0065] According to embodiments of the present invention, the present invention also provides a computer program product that, when executed by a processor, can implement the methods described in any of the above embodiments.

[0066] Figure 5 A schematic block diagram of an example electronic device 300 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices.

[0067] like Figure 5As shown, the electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. The RAM 303 may also store various programs and data required for the operation of the electronic device 300. The computing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0068] Multiple components in electronic device 300 are connected to I / O interface 305, including: input unit 306, such as keyboard, mouse, etc.; output unit 307, such as various types of displays, speakers, etc.; storage unit 308, such as disk, optical disk, etc.; and communication unit 309, such as network card, modem, wireless transceiver, etc. Communication unit 309 allows electronic device 300 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0069] The computing unit 301 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 301 performs the various methods and processes described above, such as the object matching method. For example, in some embodiments, the object matching method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by the computing unit 301, one or more steps of the methods described above may be performed.

[0070] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0071] The program code used to implement the methods of the present invention can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0072] In the context of this invention, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

Claims

1. A method for predicting cold vortex path ensembles, characterized in that, include: The real-time location of the cold vortex was determined based on the latest zero-field data from the global model. The corrected path is obtained by arithmetically averaging the N member paths with the smallest path errors among the cold vortex paths in the ensemble forecast, where the path error is the distance between the current position of the cold vortex center in the ensemble forecast and the real-time position. The forecast data of the center position and path of the cold vortex of all forecast members of the ensemble forecast are obtained, and path clustering is performed. Then, the superposition of the path clustering results and the cold vortex center position of the corrected path is used as the cold vortex path forecast product. After obtaining the cold vortex path forecast product, the method further includes: If the cold vortex is a long-lived cold vortex, then determine the category of its 500 hPa situational field, and then output the path corresponding to the category after superimposing it onto the cold vortex path forecast product. If the cold vortex is not a long-lived cold vortex, then output the cold vortex path forecast product; Before determining the category of its 500 hPa morphological field, the method also includes: obtaining long-lived cold vortex events from a cold vortex history database; and clustering the long-lived cold vortex events to obtain the 500 hPa morphological field of the initial date of different categories of long-lived cold vortex events. If a cold vortex is a long-lived cold vortex, determining its 500 hPa situation field category involves comparing the 500 hPa situation field on the first day of the long-lived cold vortex's inception with the anomaly correlation coefficients of the situation fields of different categories of cold vortices obtained through clustering to determine its category.

2. The cold vortex path ensemble prediction method according to claim 1, characterized in that, The path error is the distance between the current location of the cold vortex center and the real-time location predicted by the ensemble forecast.

3. A cold vortex path ensemble prediction device, characterized in that, include: The location determination unit is used to determine the real-time location of the cold vortex based on the latest zero-field data from the global model. The corrected path determination unit selects the N member paths with the smallest path error among the ensemble forecast member cold vortex paths and performs an arithmetic average to obtain the corrected path. The cold vortex path forecast product generation unit is used to acquire forecast data of the center position and path of cold vortices of all forecast members in the ensemble forecast, and to perform path clustering using the DSBCAN algorithm. The superposition of the path clustering results and the cold vortex center position of the corrected path is used as the cold vortex path forecast product. The device also includes: a first output unit, used to determine the category of the 500 hPa situational field if the cold vortex is a long-lived cold vortex, and to output the path corresponding to the category after superimposing it onto the cold vortex path prediction product; The second output unit is used to output the cold vortex path prediction product if the cold vortex does not belong to a long-lived cold vortex. The device also includes: an event acquisition unit for acquiring long-lived cold vortex events from a cold vortex history database; and a clustering unit for clustering long-lived cold vortex events to obtain the 500 hPa situational field of the initial date of different categories of long-lived cold vortex events. Before determining the category of its 500 hPa morphological field, the device retrieves long-lived cold vortex events from the cold vortex history database; the long-lived cold vortex events are clustered to obtain the 500 hPa morphological field of the initial date of different categories of long-lived cold vortex events. If a cold vortex is a long-lived cold vortex, determining its 500 hPa situation field category involves comparing the 500 hPa situation field on the first day of the long-lived cold vortex's inception with the anomaly correlation coefficients of the situation fields of different categories of cold vortices obtained through clustering to determine its category.

4. The cold vortex path ensemble prediction device according to claim 3, characterized in that, The device also includes: an event acquisition unit for acquiring long-lifetime cold vortex events from a cold vortex history database; Clustering units are used to cluster long-lived cold vortex events to obtain the 500 hPa situational field of the initial date of different categories of long-lived cold vortex events.

5. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the cold vortex path set prediction method according to any one of claims 1-2.

6. An electronic device, characterized in that, include: At least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to cause the at least one processor to perform the cold vortex path set prediction method according to any one of claims 1-2.

Images