Meteorological disaster early warning method for point-line-plane carrier

Abstract

The invention relates to a meteorological disaster early warning method and system for a point-line-plane carrier, and relates to the technical field of meteorological disaster early warning, and the method comprises the steps: carrying out the positioning error compensation of each point coordinate in the carrier, and obtaining a carrier point coordinate set; according to the bearing body point coordinate set and the preset moving speed of the user, the point arrival time when the user reaches each point coordinate is obtained, and a bearing body meteorological data set is obtained; obtaining a meteorological sparse coefficient of each piece of bearing meteorological data in the bearing body meteorological data set, and obtaining a meteorological sparse coefficient set; and obtaining a moving speed error coefficient of the user, carrying out meteorological disaster analysis, obtaining a meteorological disaster rate, and carrying out meteorological disaster early warning. According to the method, the problem that traditional meteorological disaster early warning cannot accurately early warn point-line-plane carriers is solved, personalized meteorological disaster early warning for different carriers is realized through the steps of positioning error compensation, meteorological data spatio-temporal indexing, sparsity evaluation and the like, and the early warning accuracy and pertinence are improved.

Description

Technical Field

[0001] The present application relates to the field of meteorological disaster early warning, and in particular to a meteorological disaster early warning method and system for point, line, and surface carriers. Background Art

[0002] With the development of intelligent meteorological warning technology, accurate early warning for specific points, lines, and surfaces has become key to improving disaster prevention efficiency. Currently, traditional meteorological disaster warning systems often use a unified regional warning model, which suffers from insufficient personalization and poor adaptability. This makes it difficult to meet the precise early warning needs of specific points, routes, or regions in sectors such as shipping and agriculture.

[0003] The existing early warning method only relies on conventional regional data for early warning, resulting in insufficient warning accuracy for specific areas of user concern. It can neither meet the differentiated needs of different scenarios nor adapt to the requirements of accuracy and real-time performance in the intelligent transformation of meteorological early warning. Summary of the Invention

[0004] In order to solve the above technical problems, this application provides a meteorological disaster warning method and system for point, line and surface carriers, which solves the problems of insufficient personalization, poor adaptability and low warning accuracy for specific carriers of traditional meteorological disaster warnings, realizes precise warning based on point, line and surface customization, and improves the pertinence and effectiveness of meteorological disaster warnings.

[0005] The embodiments of this application disclose the following technical solutions: In a first aspect, an embodiment of the present application provides a meteorological disaster early warning method for point, line, and surface carriers, the method comprising: Obtaining a carrier selected by a user, performing positioning error compensation on the coordinates of each point within the carrier to obtain a carrier point coordinate set, wherein the carrier is one of a point, a line, or a surface, and the carrier includes the point coordinates of at least one point; According to the carrier point coordinate set, based on the user's preset moving speed, the user's arrival time at each point coordinate is obtained, and the meteorological data corresponding to each point coordinate and arrival time is obtained by indexing in the meteorological data sequence to obtain the carrier meteorological data set; Obtaining a meteorological sparse coefficient of each bearer meteorological data in the bearer meteorological data set to obtain a meteorological sparse coefficient set; The user's moving speed error coefficient is obtained, and the meteorological sparse coefficient set and the carrier meteorological data set are combined to perform meteorological disaster analysis, obtain the meteorological disaster rate, and issue a meteorological disaster warning.

[0006] In a second aspect, an embodiment of the present application provides a meteorological disaster warning system for point, line, and surface carriers, the system comprising: A carrier coordinate compensation module is used to obtain a carrier selected by a user, perform positioning error compensation on the coordinates of each point within the carrier, and obtain a carrier point coordinate set, wherein the carrier is one of a point, a line, or a surface, and the carrier includes the point coordinates of at least one point; A meteorological data spatiotemporal indexing module is configured to obtain, based on the carrier point coordinate set and the user's preset moving speed, the point arrival time of the user at each point coordinate, index the meteorological data corresponding to each point coordinate and arrival time within the meteorological data sequence, and obtain a carrier meteorological data set; A data sparsity evaluation module is used to obtain a meteorological sparse coefficient of each carrier meteorological data in the carrier meteorological data set to obtain a meteorological sparse coefficient set; The disaster rate comprehensive warning module is used to obtain the user's mobile speed error coefficient, combine the meteorological sparse coefficient set and the carrier meteorological data set to perform meteorological disaster analysis, obtain the meteorological disaster rate, and issue a meteorological disaster warning.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: This application proposes a meteorological disaster early warning method and system, which collects multi-source meteorological data, moving speed error coefficient and meteorological sparse coefficient, comprehensively analyzes the basic meteorological disaster rate, speed compensation parameters and regional environmental characteristics, and dynamically compensates and optimizes the multi-dimensional monitoring data. At the same time, based on multiple types of information such as real-time meteorological elements, equipment movement errors, regional monitoring density, etc., the basic disaster risk assessment results are dynamically corrected in combination with the speed compensation coefficient and the meteorological sparse coefficient, which effectively improves the accuracy and reliability of meteorological disaster early warnings, and realizes accurate risk prediction in scenarios such as complex meteorological conditions and dynamic movement of monitoring equipment, avoiding the problem of inaccurate early warnings caused by data deviation or environmental factors. Through the steps of multi-source data fusion, dynamic coefficient compensation and regional risk correction, multi-channel monitoring information is integrated and multiple influencing factors are quantified, effectively avoiding the problem of early warning deviation caused by a single data source and static analysis.

[0008] The technical solution of this application realizes accurate assessment and early warning of meteorological disaster risks by integrating dynamic parameters such as real-time meteorological data, movement speed error coefficient and meteorological sparse coefficient, solves the problems of misjudgment and missed judgment caused by equipment movement error and uneven distribution of monitoring sites in traditional early warning, improves the timeliness and effectiveness of disaster warning, and avoids delayed emergency response and mismatch of disaster prevention resources caused by inaccurate warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic flow chart of a meteorological disaster early warning method for point, line, and surface carriers provided in an embodiment of the present application; Figure 2A schematic structural diagram of a meteorological disaster warning system for point, line, and surface carriers provided in an embodiment of the present application; In the accompanying drawings, the components represented by the reference numerals are described as follows: Carrier coordinate compensation module 01, meteorological data spatiotemporal index module 02, data sparsity assessment module 03, disaster rate comprehensive warning module 04. DETAILED DESCRIPTION

[0010] The present application provides a meteorological disaster warning method and system for point, line and surface carriers, which is used to solve the technical problems existing in the prior art of traditional meteorological warnings, such as insufficient personalization, poor adaptability and low warning accuracy for specific carriers.

[0011] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0012] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the described features. In the description of this application, "plurality" means two or more, unless otherwise specifically specified.

[0013] In the description of this application, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art will recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in this application.

[0014] Example 1, as shown in the attached Figure 1 As shown, the present application provides a meteorological disaster early warning method for point, line and surface carriers. The method comprises the following steps: S100: Acquire a carrier selected by a user, perform positioning error compensation on each point coordinate within the carrier, and obtain a carrier point coordinate set, wherein the carrier is one of a point, a line, or a surface, and the carrier includes the point coordinates of at least one point; In an embodiment of the present application, during the meteorological disaster warning process, it is necessary to obtain the carrier selected by the user in the meteorological map through the interactive interface (the point carrier contains 1 point coordinate, and the line / surface carrier contains multiple point coordinates), and obtain the positioning error parameters (such as parameter values that characterize the error range).

[0015] Furthermore, the positioning error parameters are used to compensate each original point coordinate to generate multiple compensation point coordinates within the error range nearby, and the original point coordinates are integrated with all the compensation point coordinates to form a carrier point coordinate set.

[0016] This process covers the coordinate range that may be affected by positioning errors by matching the error compensation logic of the carrier type (point / line / surface), providing a coordinate reference that includes the possibility of error for subsequent data processing.

[0017] Step S100 of the method provided in the embodiment of the present application includes: Obtaining a carrier selected by the user in the weather map, wherein a carrier is one of a point, a line, or a surface. A point carrier includes the coordinates of a single point, while a line carrier and a surface carrier include the coordinates of multiple points. Get positioning error parameters; The positioning error parameters are used to perform error compensation on each point coordinate in the carrier to obtain multiple compensation point coordinates, and then all point coordinates and all compensation point coordinates are obtained to obtain a carrier point coordinate set.

[0018] In the embodiment of the present application, during the meteorological disaster warning process, in order to accurately locate the area of interest to the user, it is necessary to first obtain the carrier selected by the user through the meteorological map interactive interface.

[0019] Specifically, by calling the point selection, line drawing or circle selection functions of the map API, the coordinate data of the point / line / surface form can be obtained and stored as structured data in a preset format (such as the latitude and longitude tuple of the point coordinates, the coordinate sequence of the line / surface).

[0020] For example, if a user circles Xuanwu District, Nanjing City, Jiangsu Province (surface carrier) on a weather map, the coordinates of its boundary vertices will be recorded as ("Type": "surface", "Coordinate ring": [[118.812, 32.065], [118.837, 32.088], [118.861, 32.072], [118.812, 32.065]], "Number": "Region 001"), and a closed area data structure is formed through the same coordinates at the beginning and end.

[0021] At the same time, positioning error parameters (such as the standard error range of satellite positioning, terrain influence coefficient, etc.) are retrieved from the parameter library. The parameters can be dynamically matched according to different carrier types (such as mountain points and sea routes).

[0022] For example, when the positioning error parameter corresponds to the distance between two point coordinates, the point coordinates within the distance between two point coordinates near each original point coordinate are used together with the original coordinates as the carrier point coordinates, thereby covering the deviation range that may occur in actual positioning, providing a more reliable position reference for the spatiotemporal index of subsequent meteorological data, and avoiding the offset of warning data caused by coordinate errors.

[0023] For example, if a user draws a sea route (line carrier) from Lianyungang Port to Yancheng Port on a weather map, the coordinates of the starting point and passing points of the route are obtained through the map API and recorded as ("Type": "Line", "Coordinate Sequence": [[119.16, 34.60], [120.03, 33.78], [120.03, 33.78], [120.23, 33.50]], "Number": "Line Segment 002").

[0024] Furthermore, positioning error parameters applicable to sea routes are retrieved from the parameter library, such as the standard error range of satellite positioning is ±80 meters and the offset range caused by the ocean current influence coefficient is ±50 meters. The two errors are combined and quantified into the range of the coordinate distance between two points.

[0025] Based on these parameters, the coordinates of all points within the range of 2 points near each original point coordinate of the route are integrated with the original coordinates to form the final carrier point coordinate set, ensuring that when the meteorological data of the route is subsequently retrieved, the range caused by ship navigation deviation and positioning error can be effectively covered, thereby ensuring the accuracy of meteorological disaster warnings.

[0026] S200: Based on the carrier point coordinate set and the user's preset moving speed, obtaining the user's arrival time at each point coordinate, indexing the meteorological data corresponding to each point coordinate and arrival time in the meteorological data sequence, and obtaining a carrier meteorological data set; In the embodiment of the present application, during the meteorological disaster warning process, it is necessary to further obtain corresponding meteorological data based on the carrier point coordinate set.

[0027] Specifically, the preset movement speed input by the user is first obtained. When the carrier is a point, the default preset movement speed is 0. When the carrier is a line or a surface, the preset movement speed can be set according to the actual scenario (such as the standard driving speed, the sailing speed of a ship, etc.).

[0028] Furthermore, the user's current location is obtained, and the estimated time for the user to reach each point coordinate is calculated using a distance-speed formula in combination with the preset moving speed and the carrier point coordinate set.

[0029] Among them, if the carrier is a point, the point arrival time is the current time; if it is a line or a surface, the estimated arrival time of each point is calculated in sequence according to the moving path to form a point arrival time set.

[0030] Finally, from the meteorological data sequence, based on the correspondence between the point arrival time set and the point coordinates, the meteorological data (such as wind speed, rainfall, temperature, etc.) of each coordinate point at the corresponding time are accurately indexed, and these data are integrated into the carrier meteorological data set to provide data support for subsequent meteorological disaster risk assessment and early warning.

[0031] Step S200 in the method provided in the embodiment of the present application includes: Get the user's preset moving speed, where when the carrier is a point, the preset moving speed is 0; Obtain the user's current location, and combine the preset moving speed and the carrier point coordinate set to obtain the user's arrival time at each point coordinate to obtain an arrival time set; Acquire a meteorological data sequence, and obtain meteorological data corresponding to each point coordinate and arrival time according to the arrival time set, and obtain a carrier meteorological data set.

[0032] In an embodiment of the present application, during the meteorological disaster warning process, in order to achieve accurate matching of meteorological data with the user's area of interest, it is necessary to further obtain corresponding meteorological data based on the carrier point coordinate set.

[0033] First, in order to achieve accurate indexing of meteorological data in combination with the time dimension, it is necessary to obtain the user's preset movement speed.

[0034] Among them, if the carrier is a point (such as a fixed monitoring station), the default preset moving speed is 0, and the time when the user arrives at this point is the current time; if the carrier is a line (such as a route) or a surface (such as an urban area), the moving speed input by the user is obtained through the interactive interface. For example, the driving scene uses the road speed limit, and the shipping scene matches the speed according to the ship type.

[0035] Furthermore, the user's current location coordinates are obtained through the positioning function of the mobile terminal or the map API, and are used as the starting reference for time calculation.

[0036] Among them, for a point carrier with a preset moving speed of 0, the current system time is directly marked as the arrival time; for a line or surface carrier, the estimated arrival time of the starting point is calculated based on the spatial distance between the user's current position and the starting point of the carrier, combined with the preset moving speed, using the formula "time = distance / speed".

[0037] Furthermore, coordinate points are extracted along the path or boundary of the carrier according to a preset distance interval (such as 500 meters). Based on the calculated arrival time of the previous point, the estimated arrival time of each coordinate point is calculated in turn, and finally an arrival time set covering the coordinates of all carrier points is formed, providing an accurate time dimension reference for subsequent meteorological data retrieval.

[0038] In the method provided in the embodiment of the present application, the steps of “obtaining a meteorological data sequence, and obtaining meteorological data corresponding to each point coordinate and arrival time by indexing according to the arrival time set, and obtaining a carrier meteorological data set” include: Acquire a meteorological data sequence according to a meteorological data monitoring system, wherein the meteorological data sequence includes meteorological data for multiple moments in the future, and each meteorological data sequence includes meteorological data for all coordinates in a meteorological map; According to the carrier point coordinate set and arrival time set, the meteorological data under each point coordinate and arrival time in the meteorological data sequence is indexed to obtain a carrier meteorological data set.

[0039] In an embodiment of the present application, during the meteorological disaster warning process, in order to achieve accurate coupling of meteorological data with the spatial position and time dimension of the user's area of interest, it is necessary to implement spatiotemporal joint retrieval and acquisition of corresponding meteorological data based on the carrier point coordinate set that has completed positioning error compensation.

[0040] Specifically, we first obtain a multi-source meteorological data sequence by connecting to the meteorological data monitoring system. This sequence contains meteorological data for multiple moments in the future, and each moment covers the meteorological elements (such as wind speed, precipitation, temperature, etc.) of all coordinates in the meteorological map.

[0041] Furthermore, based on the obtained arrival time set, a spatiotemporal joint indexing operation is performed in the meteorological data sequence to obtain a carrier meteorological data set that can reflect the dynamic meteorological characteristics of the user's area of interest throughout the entire period.

[0042] Specifically, the spatial scope is first defined. This means using the coordinate set of the carrier point as the spatial retrieval benchmark. If the carrier is a linear structure (such as a marathon track, road, or waterway), a linear spatial scope is formed based on its coordinate point sequence. If it is a surface structure (such as a factory area, urban area, or river basin), a closed spatial boundary is constructed using the coordinates of polygon vertices to clearly define the spatial matching scope of the meteorological data.

[0043] Furthermore, corresponding time anchors are generated. This means that the arrival time set is aligned with the timestamps of the meteorological data series. The arrival time set contains the estimated arrival time (accurate to the minute) for each carrier point coordinate. For example, the arrival time of 10:30 calculated for a highway coordinate point serves as the search anchor in the time dimension.

[0044] Furthermore, a spatiotemporal joint search is performed. This involves performing a composite query based on "coordinate point + timestamp" in the meteorological database. Specifically, a search area is formed with the coordinates of a single carrier point as the center, combined with a preset spatial error compensation radius (e.g., ±100 meters), and the meteorological observation data within this area closest to the target arrival time is matched.

[0045] Among them, if there is a time sampling interval (such as data is updated every 15 minutes), the observation value with the closest timestamp is selected as the matching result.

[0046] Finally, data structured integration is implemented, that is, the coordinates of each carrier point are combined with the meteorological data at the corresponding time to generate standardized data records containing latitude and longitude coordinates, timestamps, and meteorological parameters (wind speed, precipitation intensity, temperature, etc.), forming a carrier meteorological data set, which intuitively presents the dynamic meteorological conditions of the user's area of interest in a temporal and spatial manner.

[0047] For example, when the user selects the highway from Nanjing Xinjiekou to Lukou Airport as the area of interest (line carrier), the coordinate point set of the route is first corrected based on the positioning error compensation mechanism.

[0048] Furthermore, it connects to the meteorological data monitoring system to obtain a series of meteorological data at intervals of 15 minutes within the next 6 hours, which covers meteorological elements such as wind speed, precipitation, visibility, etc. at the coordinate points along the entire route.

[0049] Furthermore, based on the preset driving speed of 80km / h, combined with the user's current location and route coordinates, the estimated arrival time at each key node (such as toll booths and interchanges) is calculated to form an arrival time set.

[0050] Finally, with the corrected route coordinate point set as the spatial range and the arrival time set as the time anchor point, a spatiotemporal joint indexing operation is performed in the meteorological data sequence to retrieve the meteorological data at the corresponding time of each node. After integration, a carrier meteorological data set is generated to provide users with dynamic meteorological warning information throughout the entire process.

[0051] S300: Obtaining a meteorological sparse coefficient of each bearer meteorological data in the bearer meteorological data set to obtain a meteorological sparse coefficient set; In the embodiment of the present application, in order to evaluate the reliability of the carried meteorological data, it is necessary to further calculate the meteorological sparsity coefficient of each data.

[0052] Specifically, the coordinates of the meteorological stations within the meteorological map are first obtained. Using a spatial distance algorithm, the spatial distance between each point in the carrier's meteorological dataset and the coordinates of the nearest meteorological station is calculated, forming a meteorological station distance set. This distance intuitively reflects the proximity of each point's coordinates to the source of the actual observation data.

[0053] Furthermore, a preset standard meteorological station distance is set as a reference threshold. This threshold can be flexibly configured based on the meteorological data monitoring accuracy requirements or application scenarios (such as urban areas and mountainous areas). Each distance value in the meteorological station distance set is compared with the preset standard meteorological station distance. The resulting ratio is the meteorological sparse coefficient of the corresponding point coordinate.

[0054] Among them, the farther the distance, the larger the ratio, indicating that the accuracy of meteorological data is reduced due to the lack of support from neighboring observations, and the corresponding meteorological sparse coefficient is larger; conversely, the closer the distance, the smaller the coefficient.

[0055] Finally, through the above calculation process, each carrier meteorological data in the carrier meteorological data set is assigned a corresponding meteorological sparse coefficient, and the meteorological sparse coefficient set is integrated to provide a quantitative basis for subsequent meteorological disaster risk assessment and warning information classification based on data reliability.

[0056] Step S300 in the method provided in the embodiment of the present application includes: Obtain the coordinates of the meteorological stations in the meteorological map, calculate the distance between the coordinates of each point carrying meteorological data and the coordinates of the nearest meteorological station, and obtain the meteorological station distance set; According to the meteorological station distance set, the meteorological sparse coefficient set is calculated.

[0057] In the embodiment of the present application, during the meteorological disaster warning process, in order to evaluate the reliability of the data in the carrier meteorological data set, it is necessary to further obtain the meteorological sparse coefficient corresponding to each data.

[0058] Specifically, in order to accurately calculate the meteorological sparse coefficient, it is first necessary to obtain the coordinates of the meteorological stations in the meteorological map.

[0059] Among them, if the meteorological map uses a standard geographic coordinate system (such as WGS84), the latitude and longitude coordinates of the meteorological station in this coordinate system are directly obtained; if the meteorological map uses a custom projection coordinate system (such as a local independent coordinate system), the coordinates of the meteorological station need to be converted into coordinates in the same coordinate system as the coordinates of the meteorological data points through coordinate conversion.

[0060] Furthermore, for each point coordinate in the carrier meteorological data set, a spatial distance measurement algorithm (such as the Euclidean distance formula or the Haversine formula) is used to calculate its spatial distance with all meteorological station coordinates one by one, and the minimum distance value is selected as the distance between the point coordinate and the nearest meteorological station.

[0061] For two-dimensional coordinates, the Euclidean distance formula is used; for longitude and latitude coordinates, the Haversine formula is used. The values obtained by these two calculation formulas are combined to form a meteorological station distance set.

[0062] Furthermore, based on the existing meteorological station distance set, a meteorological sparse coefficient set is calculated.

[0063] In the method provided in the embodiment of the present application, the step of “calculating a meteorological sparse coefficient set based on a meteorological station distance set” includes: Get the distance to the preset standard weather station; The ratio of the distance of each meteorological station in the meteorological station distance set to the preset standard meteorological station distance is calculated to obtain a meteorological sparse coefficient set.

[0064] Specifically, the preset standard weather station distance is first obtained. This distance serves as a benchmark threshold for measuring the reliability of weather data and can be flexibly set according to the actual application scenario.

[0065] If applied to urban areas with dense meteorological monitoring stations, considering the high-precision requirements of data monitoring, the preset standard meteorological station distance can be set to a smaller value (such as 500 meters); if applied to mountainous or remote areas with sparse meteorological monitoring stations, in order to adapt to their monitoring conditions, the preset standard meteorological station distance can be appropriately increased (such as 5 kilometers).

[0066] Furthermore, based on the acquired meteorological station distance set, a ratio operation is performed on each meteorological station distance data in the set and a preset standard meteorological station distance to obtain a meteorological sparse coefficient set.

[0067] Specifically, the meteorological sparseness coefficient = meteorological station distance / preset standard meteorological station distance. Through this operation, the distance between each point coordinate and the nearest meteorological station can be normalized, so that the distance information is converted into a value between 0 and positive infinity.

[0068] Among them, when the distance to the meteorological station is ≤ the preset standard meteorological station distance, that is, the meteorological sparse coefficient is ≤1, it indicates that the reliability of the meteorological data at this point is relatively high; when the distance to the meteorological station is greater than the preset standard meteorological station distance, that is, the meteorological sparse coefficient is greater than 1, it indicates that the reliability of the meteorological data at this point is relatively low, and the farther the distance, the larger the coefficient and the lower the data accuracy.

[0069] Furthermore, all meteorological sparse coefficients obtained through ratio calculation are orderly integrated to form a meteorological sparse coefficient set that corresponds one-to-one to the data in the carrier meteorological data set.

[0070] This collection provides a quantitative basis for subsequent operations such as meteorological data quality assessment, warning information weight allocation, and risk level classification, ensuring the scientificity and reliability of data application in the meteorological disaster warning process.

[0071] S400: Obtain the user's moving speed error coefficient, combine the meteorological sparse coefficient set and the carrier meteorological data set to perform meteorological disaster analysis, obtain the meteorological disaster rate, and issue a meteorological disaster warning.

[0072] In the embodiment of the present application, in order to improve the accuracy of meteorological disaster warnings, it is necessary to comprehensively consider the impact of user movement speed errors and the sparsity of the spatial distribution of meteorological data on disaster prediction.

[0073] Specifically, the user's speed error coefficient is first obtained. This coefficient is related to the type of the carrier. When the carrier is a point, the default speed error coefficient is 0; when the carrier is a line or surface, the coefficient is calculated based on historical speed fluctuation data.

[0074] Furthermore, the carrier meteorological data set is input into the meteorological disaster predictor, and multiple basic meteorological disaster rates are output and the average is calculated as the initial disaster risk assessment value.

[0075] Furthermore, a compensation correction is performed by combining the mobile speed error coefficient and the meteorological sparse coefficient set. Specifically, the speed compensation coefficient is calculated by summing 1 and the mobile speed error coefficient. This coefficient and the meteorological sparse coefficient set are then multiplied by the basic meteorological disaster rate, and the average is taken to obtain the final meteorological disaster rate. The larger the mobile speed error and the sparser the meteorological data, the higher the meteorological disaster rate correction value.

[0076] Finally, the meteorological disaster rate is compared with a preset threshold. If it exceeds the threshold, the corresponding warning is triggered; otherwise, it is not triggered. Through this mechanism, disaster risk assessment can be dynamically adjusted according to user mobility scenarios to improve the accuracy of warnings.

[0077] Step S400 in the method provided in the embodiment of the present application includes: Obtain the user's movement speed error coefficient, where the movement speed error coefficient is the amplitude of the movement speed error. When the carrier is a point, the movement speed error coefficient is 0; Perform meteorological disaster prediction based on each carrier meteorological data in the carrier meteorological data set, and process to obtain a basic meteorological disaster rate; According to the moving speed error coefficient, a speed compensation coefficient is calculated, and combined with the meteorological sparse coefficient set, the basic meteorological disaster rate is compensated to obtain the meteorological disaster rate, and meteorological disaster warning judgment is performed.

[0078] In the embodiment of the present application, in order to accurately assess the risk of meteorological disasters, it is necessary to obtain the user's mobile speed error coefficient, which is used to characterize the amplitude of the mobile speed error, and its value is closely related to the carrier type.

[0079] Among them, when the carrier is a point (such as a fixed monitoring station or a stationary target area), the default moving speed error coefficient is 0 because there is no movement; when the carrier is a line (such as a road route or an air route) or a surface (such as an urban area or an activity range), the moving speed error coefficient can be calculated based on the standard moving speed set by the user, the actual moving speed measured in real time, and arithmetic operations.

[0080] Specifically, when calculating the moving speed error coefficient, first obtain the standard moving speed set by the user (such as 60km / h), then measure the user's actual moving speed in real time (such as 50km / h), subtract the actual moving speed from the standard moving speed to obtain the speed difference (60-50=10km / h), and divide the absolute value of the speed difference by the standard moving speed. The final result is the moving speed error coefficient (moving speed error coefficient = |10| / 60≈0.17).

[0081] In the method provided in the embodiment of the present application, the step of “performing meteorological disaster prediction based on each bearer meteorological data in the bearer meteorological data set and processing to obtain a basic meteorological disaster rate” includes: Input each carrier meteorological data in the carrier meteorological data set into a meteorological disaster predictor, and predict and output a plurality of predicted basic meteorological disaster rates, wherein the meteorological disaster predictor is trained using a sample carrier meteorological data set and a sample meteorological disaster rate set, and the sample meteorological disaster rate is the proportion of meteorological disasters caused by different sample carrier meteorological data; Calculate the average of the multiple predicted basic meteorological disaster rates to obtain the basic meteorological disaster rate.

[0082] In the embodiment of the present application, in order to accurately assess the meteorological disaster risk and obtain a reliable basic meteorological disaster rate, it is necessary to first construct a meteorological disaster predictor.

[0083] During the training process of the meteorological disaster predictor, by looking back at historical meteorological monitoring archives, meteorological data under different years, seasons, and geographical conditions are screened from the database of the meteorological data center to form a sample carrier meteorological data set. The meteorological data carried includes multi-dimensional meteorological elements such as temperature, humidity, wind speed, air pressure, and precipitation, as well as geographic environmental parameters such as altitude, terrain slope, and vegetation coverage. Data collection adopts a uniform time resolution of one hour and is acquired simultaneously from multiple sources such as ground weather stations, meteorological satellites, and radar monitoring to ensure the integrity and accuracy of the sample data.

[0084] For example, we screened out monitoring data from a region's summer meteorological data for typical meteorological disasters, including heavy rain (precipitation ≥ 50 mm / 24 hours), high winds (wind speed ≥ 17.2 m / s), and high temperatures (temperature ≥ 35°C). This data exhibits specific patterns in the feature space. For example, heavy rain is often accompanied by relative humidity ≥ 90% and a sudden drop in air pressure.

[0085] Furthermore, an analysis team composed of meteorological experts used professional data analysis tools to manually label the occurrence of meteorological disasters corresponding to the meteorological data carried by each sample.

[0086] During the labeling process, unified disaster determination standards are followed. For example, precipitation exceeding 50 mm for three consecutive hours is determined to be a rainstorm disaster, and daily maximum temperatures ≥ 35°C for three consecutive days is determined to be a high temperature disaster. The disaster type and occurrence probability corresponding to each data sample are recorded to form a sample meteorological disaster rate set.

[0087] Furthermore, after completing the construction of the sample carrier meteorological data set and the sample meteorological disaster rate set, the random forest algorithm is used as the basic architecture to construct a meteorological disaster predictor.

[0088] The random forest algorithm takes a sample meteorological data set as input and, through the parallel computation of multiple decision trees, directly outputs a corresponding set of sample meteorological disaster rates, mapping meteorological data to disaster probabilities. By constructing multiple decision trees, the random forest algorithm automatically extracts complex feature relationships in the data, adapting to the multi-factor influencing nature of meteorological disaster prediction.

[0089] Specifically, the algorithm's input layer receives standardized meteorological data (consisting of 10 meteorological elements and 5 geographic parameters). Each decision tree uses bootstrap sampling to extract approximately 65% of the original data as a training set, and then randomly selects certain features for node splitting. The Gini coefficient is used as an evaluation metric during the node splitting process. After 10 splits, five decision tree branches are cascaded to capture multi-dimensional features such as meteorological element trends and the impact of the geographic environment.

[0090] In particular, at the end of the algorithm, the final probability of meteorological disaster occurrence is output through a voting mechanism or average prediction value, which forms a corresponding relationship with the sample meteorological disaster rate set.

[0091] During the model training phase, the sample-bearing meteorological data set was divided into a training set and a validation set in an 8:2 ratio. During training, mean squared error was used as the optimization objective, and iterative optimization was performed by adjusting parameters such as the number of decision trees and maximum depth. The initial number of trees was set to 50, and performance evaluation was performed every 10 additional trees.

[0092] For example, in the first round of training, a batch (e.g., 100 groups) of sample data was input, and the average error between the model's outputted meteorological disaster probability predictions and the labeled values was 0.15. After 30 rounds of training, the average error on the validation set dropped to 0.05, and the error curve stabilized, indicating that the model had converged.

[0093] During the training process, overfitting is avoided by using the early stopping strategy, that is, when the error value on the validation set does not decrease for 5 consecutive rounds, the training is automatically stopped.

[0094] At the same time, in order to enhance the adaptability of the model to different meteorological environments, a data enhancement strategy is used to expand the meteorological data set of the sample carrier.

[0095] Specifically, by performing characteristic perturbation operations on the original data, such as adding ±2°C random noise to the temperature data, scaling the wind speed data by ±10%, and simulating the changing patterns of meteorological elements under different terrain conditions, diversified derivative data samples are generated.

[0096] This method enables the model to be exposed to more diverse meteorological data features during the training phase, effectively improving its adaptability to data differences caused by monitoring equipment errors and environmental changes in actual applications, ensuring accurate prediction of meteorological disasters under different climatic conditions.

[0097] Ultimately, after multiple rounds of iterative training and parameter optimization, the resulting meteorological disaster predictor achieved 90% accuracy and 85% recall on the test set. This predictor can accurately predict the probability of meteorological disasters such as heavy rain, high winds, and high temperatures, providing reliable technical support for subsequent meteorological disaster warnings.

[0098] Furthermore, multiple real-time meteorological data sets are sequentially fed into a trained meteorological disaster predictor. Using the feature analysis capabilities of the random forest algorithm, the predictor automatically analyzes the combined characteristics of meteorological elements in the data and, using pre-set disaster determination rules, accurately predicts the probability of a meteorological disaster.

[0099] Furthermore, after obtaining multiple predicted basic meteorological disaster rates, in order to form a unified and global risk assessment indicator, it is necessary to calculate the average of multiple predicted basic meteorological disaster rates to obtain the basic meteorological disaster rate.

[0100] Specifically, the validity of the multiple predicted basic meteorological disaster rates output by the predictor is first verified, and outliers caused by abnormal data transmission or monitoring equipment failure are eliminated. For example, when the predicted probability of a certain area exceeds 100% or is less than 0%, corrections are made through interpolation of data from neighboring stations to ensure the rationality of the data.

[0101] Furthermore, the arithmetic mean method is used to calculate the basic meteorological disaster rate, that is, all valid prediction probabilities are added together and divided by the number of stations.

[0102] For example, the predicted probabilities of rainstorm disasters output by 10 monitoring stations in a certain river basin are 82%, 78%, 85%, 90%, 75%, 88%, 80%, 92%, 76% and 83% respectively. Adding these values together and dividing by 10, that is, (82+78+85+90+75+88+80+92+76+83) / 10=83.9%, and the basic meteorological disaster rate of the river basin is 83.9%, which provides effective data reference for local emergency management departments to initiate risk avoidance plans.

[0103] In the method provided in the embodiment of the present application, the step of "calculating a speed compensation coefficient based on the moving speed error coefficient, compensating the basic meteorological disaster rate in combination with the meteorological sparse coefficient set to obtain a meteorological disaster rate, and performing meteorological disaster warning judgment" includes: Calculate the sum of 1 and the moving speed error coefficient to obtain the speed compensation coefficient; The speed compensation coefficient and each meteorological sparse coefficient in the meteorological sparse coefficient set are used to perform compensation calculation processing on the basic meteorological disaster rate respectively to obtain multiple compensated meteorological disaster rates, calculate the average to obtain the meteorological disaster rate, determine whether it is greater than or equal to the meteorological disaster rate threshold, and perform meteorological disaster warning judgment.

[0104] In the embodiment of the present application, in order to further improve the prediction accuracy and optimize the warning results in combination with actual environmental factors, compensation processing is required based on the moving speed error coefficient and the meteorological sparse coefficient set to achieve accurate calculation and warning judgment of the meteorological disaster rate.

[0105] Specifically, the speed compensation coefficient is obtained through linear calculation logic, that is, the speed compensation coefficient can be directly obtained through 1+moving speed error coefficient.

[0106] This coefficient is used to quantify the impact of speed deviation on data accuracy for mobile observation equipment (such as weather drones and vehicle-mounted radars). For example, if the actual speed of the equipment exceeds the preset value, resulting in a 5% error in the monitoring data, the corresponding speed compensation coefficient is 1.05 (1 + 5% = 1.05).

[0107] Furthermore, the basic meteorological disaster rate is compensated and calculated based on the speed compensation coefficient and the meteorological sparse coefficient set to obtain a plurality of compensated meteorological disaster rates.

[0108] Specifically, the speed compensation coefficient is multiplied by each element in the meteorological sparse coefficient set, and then multiplied by the basic meteorological disaster rate. That is, the formula compensated meteorological disaster rate = (speed compensation coefficient × corresponding element in the meteorological sparse coefficient set) / basic meteorological disaster rate is used to calculate multiple compensated meteorological disaster rates.

[0109] Among them, the compensation process takes into account the impact of differences in the distribution density of meteorological monitoring stations in different regions (such as sparse stations in mountainous areas resulting in insufficient data representativeness) on the prediction results.

[0110] For example, in a sparse meteorological station area, the meteorological sparse coefficient is 0.8. Combined with the speed compensation coefficient of 1.05 and the basic meteorological disaster rate of 80%, the compensated meteorological disaster rate of the area is calculated to be 67.2% (1.05×0.8×80%=67.2%).

[0111] Furthermore, after completing the multi-region compensation calculation, the meteorological disaster rate is obtained by calculating the arithmetic mean.

[0112] Specifically, all compensated meteorological disaster rates are added together and divided by the total number of regions, that is, the final meteorological disaster rate is calculated through the formula meteorological disaster rate = sum of all meteorological disaster rates / total number of regions, so as to further achieve accurate meteorological disaster identification.

[0113] Furthermore, the calculated meteorological disaster rate is compared with the preset meteorological disaster rate threshold (such as 70%). If the meteorological disaster rate is ≥ the threshold, the early warning mechanism is immediately triggered, the red warning information is pushed to the emergency management department, and the high-risk area is marked; if the meteorological disaster rate is < the threshold, the data is continuously monitored and the current warning level is maintained.

[0114] For example, a region encompasses five monitoring zones, with compensated meteorological disaster rates of 67.2%, 75.0%, 82.1%, 69.8%, and 78.5%, respectively, and a threshold of 70%. Substituting this into the formula yields the following: Meteorological Disaster Rate = (67.2 + 75.0 + 82.1 + 69.8 + 78.5) / 5 = 74.52%. If 74.52% is ≥ the threshold of 70%, an orange rainstorm warning will be automatically issued, along with a simultaneous generation of the disaster impact area. This provides intuitive and accurate data support for emergency response decisions, such as allocating relief supplies and organizing public evacuation.

[0115] The embodiments of the present application achieve the following technical effects through the above specific implementation methods: The embodiment of the present application provides a meteorological disaster warning method for point, line and surface carriers. First, the carrier selected by the user in the meteorological map is obtained, and the carrier point coordinates are compensated using the positioning error parameter to construct a carrier point coordinate set containing the error range, thereby solving the warning data offset problem caused by positioning deviation. Secondly, the estimated time of arrival at each point is calculated based on the user's preset moving speed and current position, and the meteorological data sequence is retrieved through spatiotemporal joint retrieval to obtain the carrier meteorological data set, thereby achieving accurate matching of meteorological data with the user's area of interest. Then, the distance between the carrier meteorological data point and the nearest meteorological station is calculated and compared with the preset standard distance to obtain a meteorological sparse coefficient set to quantitatively evaluate the reliability of the data. Finally, the moving speed error coefficient is obtained, the carrier meteorological data is input into the predictor, the basic meteorological disaster rate is calculated, and the speed compensation coefficient and the meteorological sparse coefficient are used for compensation and correction to obtain the final meteorological disaster rate, which is compared with the preset threshold and triggers the corresponding warning.

[0116] The method provided in the embodiments of this application solves the problem of false alarms and missed detections in traditional meteorological disaster warnings caused by positioning deviations of carriers, movement speed errors, and sparse monitoring data. Through a multi-dimensional processing mechanism that includes positioning error compensation, dynamic movement speed correction, and meteorological data sparsity assessment, it breaks through the limitations of the traditional unified regional warning model, achieves personalized and accurate warnings for point, line, and surface carriers, improves warning adaptability, and promotes the development of intelligent and precise meteorological disaster prevention.

[0117] Example 2, as shown in the attached Figure 2 As shown, based on the inventive concept of the meteorological disaster early warning method for point, line and surface carriers provided in Example 1, this application also provides a meteorological disaster early warning system for point, line and surface carriers, specifically including: The carrier coordinate compensation module 01 is used to obtain a carrier selected by the user, perform positioning error compensation on the coordinates of each point in the carrier, and obtain a carrier point coordinate set, wherein the carrier is one of a point, a line, or a surface, and the carrier includes the point coordinates of at least one point; The meteorological data spatiotemporal indexing module 02 is configured to obtain the user's arrival time at each point coordinate based on the carrier point coordinate set and the user's preset moving speed, and to obtain the meteorological data corresponding to each point coordinate and arrival time by indexing within the meteorological data sequence to obtain the carrier meteorological data set; The data sparsity evaluation module 03 is used to obtain the meteorological sparse coefficient of each meteorological data in the meteorological data set of the carrier, and obtain a meteorological sparse coefficient set; The disaster rate comprehensive warning module 04 is used to obtain the user's mobile speed error coefficient, combine the meteorological sparse coefficient set and the carrier meteorological data set, perform meteorological disaster analysis, obtain the meteorological disaster rate, and issue a meteorological disaster warning.

[0118] In one embodiment, the carrier coordinate compensation module 01 is further configured to: Obtaining a carrier selected by the user in the weather map, wherein a carrier is one of a point, a line, or a surface. A point carrier includes the coordinates of a single point, while a line carrier and a surface carrier include the coordinates of multiple points. Get positioning error parameters; The positioning error parameters are used to perform error compensation on each point coordinate in the carrier to obtain multiple compensation point coordinates, and then all point coordinates and all compensation point coordinates are obtained to obtain a carrier point coordinate set.

[0119] In one embodiment, the meteorological data spatiotemporal indexing module 02 is further configured to: Get the user's preset moving speed, where when the carrier is a point, the preset moving speed is 0; Obtain the user's current location, and combine the preset moving speed and the carrier point coordinate set to obtain the user's arrival time at each point coordinate to obtain an arrival time set; Acquire a meteorological data sequence, and obtain meteorological data corresponding to each point coordinate and arrival time according to the arrival time set, and obtain a carrier meteorological data set.

[0120] In one embodiment, the data sparsity assessment module 03 is further configured to: Obtain the coordinates of the meteorological stations in the meteorological map, calculate the distance between the coordinates of each point carrying meteorological data and the coordinates of the nearest meteorological station, and obtain the meteorological station distance set; According to the meteorological station distance set, the meteorological sparse coefficient set is calculated In one embodiment, the disaster rate comprehensive early warning module 04 is further configured to: Obtain the user's movement speed error coefficient, where the movement speed error coefficient is the amplitude of the movement speed error. When the carrier is a point, the movement speed error coefficient is 0; Perform meteorological disaster prediction based on each carrier meteorological data in the carrier meteorological data set, and process to obtain a basic meteorological disaster rate; According to the moving speed error coefficient, a speed compensation coefficient is calculated, and combined with the meteorological sparse coefficient set, the basic meteorological disaster rate is compensated to obtain the meteorological disaster rate, and meteorological disaster warning judgment is performed.

[0121] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0122] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0123] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A meteorological disaster early warning method for point, line, and surface carriers, characterized in that: include: Obtaining a carrier selected by a user, performing positioning error compensation on the coordinates of each point within the carrier to obtain a carrier point coordinate set, wherein the carrier is one of a point, a line, or a surface, and the carrier includes the point coordinates of at least one point; According to the carrier point coordinate set, based on the user's preset moving speed, the user's arrival time at each point coordinate is obtained, and the meteorological data corresponding to each point coordinate and arrival time is obtained by indexing in the meteorological data sequence to obtain the carrier meteorological data set; Obtaining a meteorological sparse coefficient of each bearer meteorological data in the bearer meteorological data set to obtain a meteorological sparse coefficient set; The user's moving speed error coefficient is obtained, and the meteorological sparse coefficient set and the carrier meteorological data set are combined to perform meteorological disaster analysis, obtain the meteorological disaster rate, and issue a meteorological disaster warning.

2. The meteorological disaster early warning method for point, line and surface carriers according to claim 1 is characterized in that: Get the carrier selected by the user, perform positioning error compensation on the coordinates of each point in the carrier, and obtain the carrier point coordinate set, including: Obtaining a carrier selected by the user in the weather map, wherein a carrier is one of a point, a line, or a surface. A point carrier includes the coordinates of a single point, while a line carrier and a surface carrier include the coordinates of multiple points. Get positioning error parameters; The positioning error parameters are used to perform error compensation on each point coordinate in the carrier to obtain multiple compensation point coordinates, and then all point coordinates and all compensation point coordinates are obtained to obtain a carrier point coordinate set.

3. The meteorological disaster early warning method for point, line and surface carriers according to claim 1 is characterized in that: According to the carrier point coordinate set and the user's preset moving speed, the user's arrival time at each point coordinate is obtained, and the meteorological data corresponding to each point coordinate and arrival time is obtained by indexing within the meteorological data sequence to obtain the carrier meteorological data set, including: Get the user's preset moving speed, where when the carrier is a point, the preset moving speed is 0; Obtain the user's current location, and combine the preset moving speed and the carrier point coordinate set to obtain the user's arrival time at each point coordinate to obtain an arrival time set; Acquire a meteorological data sequence, and obtain meteorological data corresponding to each point coordinate and arrival time according to the arrival time set, and obtain a carrier meteorological data set.

4. The meteorological disaster early warning method for point, line and surface carriers according to claim 3 is characterized in that: Obtain a meteorological data sequence, and obtain meteorological data corresponding to each point coordinate and arrival time according to the arrival time set, and obtain a carrier meteorological data set, including: Acquire a meteorological data sequence according to a meteorological data monitoring system, wherein the meteorological data sequence includes meteorological data for multiple moments in the future, and each meteorological data sequence includes meteorological data for all coordinates in a meteorological map; According to the carrier point coordinate set and arrival time set, the meteorological data under each point coordinate and arrival time in the meteorological data sequence is indexed to obtain a carrier meteorological data set.

5. The meteorological disaster early warning method for point, line and surface carriers according to claim 1 is characterized in that: Obtaining a meteorological sparse coefficient of each meteorological data element in the meteorological data set of the carrier to obtain a meteorological sparse coefficient set includes: Obtain the coordinates of the meteorological stations in the meteorological map, calculate the distance between the coordinates of each point carrying meteorological data and the coordinates of the nearest meteorological station, and obtain the meteorological station distance set; According to the meteorological station distance set, the meteorological sparse coefficient set is calculated.

6. The meteorological disaster early warning method for point, line and surface carriers according to claim 5, characterized in that: According to the meteorological station distance set, the meteorological sparse coefficient set is calculated, including: Get the distance to the preset standard weather station; The ratio of the distance of each meteorological station in the meteorological station distance set to the preset standard meteorological station distance is calculated to obtain a meteorological sparse coefficient set.

7. The meteorological disaster early warning method for point, line and surface carriers according to claim 1, characterized in that: Obtain the user's mobile speed error coefficient, combine the meteorological sparse coefficient set and the carrier meteorological data set, perform meteorological disaster analysis, obtain the meteorological disaster rate, and issue a meteorological disaster warning, including: Obtain the user's movement speed error coefficient, where the movement speed error coefficient is the amplitude of the movement speed error. When the carrier is a point, the movement speed error coefficient is 0; Perform meteorological disaster prediction based on each carrier meteorological data in the carrier meteorological data set, and process to obtain a basic meteorological disaster rate; According to the moving speed error coefficient, a speed compensation coefficient is calculated, and combined with the meteorological sparse coefficient set, the basic meteorological disaster rate is compensated to obtain the meteorological disaster rate, and meteorological disaster warning judgment is performed.

8. The meteorological disaster early warning method for point, line and surface carriers according to claim 7, characterized in that: Perform meteorological disaster prediction based on each carrier meteorological data in the carrier meteorological data set, and process to obtain a basic meteorological disaster rate, including: Input each carrier meteorological data in the carrier meteorological data set into a meteorological disaster predictor, and predict and output a plurality of predicted basic meteorological disaster rates, wherein the meteorological disaster predictor is trained using a sample carrier meteorological data set and a sample meteorological disaster rate set, and the sample meteorological disaster rate is the proportion of meteorological disasters caused by different sample carrier meteorological data; Calculate the average of the multiple predicted basic meteorological disaster rates to obtain the basic meteorological disaster rate.

9. The meteorological disaster early warning method for point, line and surface carriers according to claim 7, characterized in that: The method comprises the following steps: calculating a speed compensation coefficient based on the moving speed error coefficient, performing compensation processing on the basic meteorological disaster rate in combination with the meteorological sparse coefficient set, obtaining a meteorological disaster rate, and performing meteorological disaster early warning judgment, including: Calculate the sum of 1 and the moving speed error coefficient to obtain the speed compensation coefficient; The speed compensation coefficient and each meteorological sparse coefficient in the meteorological sparse coefficient set are used to perform compensation calculation processing on the basic meteorological disaster rate respectively to obtain multiple compensated meteorological disaster rates, calculate the average to obtain the meteorological disaster rate, determine whether it is greater than or equal to the meteorological disaster rate threshold, and perform meteorological disaster warning judgment.

10. A meteorological disaster early warning system for point, line and surface carriers, characterized in that: The system is used to execute the meteorological disaster early warning method for point, line and surface carriers according to any one of claims 1 to 9, and the system includes: A carrier coordinate compensation module is used to obtain a carrier selected by a user, perform positioning error compensation on the coordinates of each point within the carrier, and obtain a carrier point coordinate set, wherein the carrier is one of a point, a line, or a surface, and the carrier includes the point coordinates of at least one point; A meteorological data spatiotemporal indexing module is configured to obtain, based on the carrier point coordinate set and the user's preset moving speed, the point arrival time of the user at each point coordinate, index the meteorological data corresponding to each point coordinate and arrival time within the meteorological data sequence, and obtain a carrier meteorological data set; A data sparsity evaluation module is used to obtain a meteorological sparse coefficient of each carrier meteorological data in the carrier meteorological data set to obtain a meteorological sparse coefficient set; The disaster rate comprehensive warning module is used to obtain the user's mobile speed error coefficient, combine the meteorological sparse coefficient set and the carrier meteorological data set to perform meteorological disaster analysis, obtain the meteorological disaster rate, and issue a meteorological disaster warning.

Images