Meteorological risk early warning method, device and system and storage medium

Abstract

The invention relates to a meteorological risk early warning method, device and system and a storage medium, and the method comprises the steps: obtaining the hour-by-hour matched historical rainfall data of a historical disaster sample of a target region, and the geological environment parameters of the target region; determining a rainfall mapping coefficient according to the historical rainfall data; the rainfall mapping coefficient represents a mapping relation between the rainfall in the future 24 hours and the rainfall in the future target time period; the target time period is less than 24 hours; according to the rainfall mapping coefficient and the predicted rainfall of the target area in the next 24 hours, the predicted rainfall of the target area in the future target time period is determined in combination with a rainfall mapping function corresponding to the target area; and determining a meteorological risk early warning index of the target area in the future target time period according to the predicted rainfall of the target area in the future target time period, the effective rainfall of the target area in a preset number of days before and the geological environment parameters. The meteorological early warning timeliness can be improved, and the early warning accuracy is improved.

Description

Technical Field

[0001] The present application relates to the field of meteorological warning, and in particular to meteorological risk warning methods, devices, systems and storage media. Background Art

[0002] Rainfall is a major factor in triggering geological disasters such as urban waterlogging, collapses, landslides, and mudslides. Therefore, intelligent and precise early warning systems can predict and detect rainfall risks in advance and issue alerts, buying time for evacuation and infrastructure protection, thereby avoiding or minimizing disaster losses.

[0003] Currently, meteorological risk warnings are often based on 24-hour critical rainfall thresholds or machine learning algorithms, with daily granularity. This approach fails to reflect the instantaneous dynamic characteristics of rainfall, resulting in insufficient timeliness for short-term warnings. It also fails to account for the impact of geological complexity on rainfall, leading to low warning accuracy.

[0004] There is currently no effective solution to the problems of insufficient timeliness and low accuracy of meteorological warnings in relevant technologies. Summary of the Invention

[0005] In this embodiment, a meteorological risk warning method, device, system and storage medium are provided to solve the problems of insufficient timeliness and low warning accuracy of meteorological warnings in related technologies.

[0006] First, in this embodiment, a meteorological risk early warning method is provided, including:

[0007] Obtaining historical rainfall data that matches historical disaster samples in the target area hour by hour, as well as geological environment parameters of the target area;

[0008] Determining a rainfall mapping coefficient based on the historical rainfall data; the rainfall mapping coefficient represents a mapping relationship between the rainfall in the next 24 hours and the rainfall in a future target period; the target period is less than 24 hours;

[0009] Determining the predicted rainfall of the target area in the future target period according to the rainfall mapping coefficient, the predicted rainfall of the target area in the next 24 hours, and the rainfall mapping function corresponding to the target area;

[0010] The meteorological risk warning index of the target area in the future target period is determined based on the predicted rainfall of the target area in the future target period, the effective rainfall of the target area in the previous preset days, and the geological environment parameters.

[0011] In some embodiments, determining the rainfall mapping coefficient based on the historical rainfall data includes:

[0012] Determining target disaster samples corresponding to maximum daily rainfall based on the historical rainfall data;

[0013] The rainfall mapping coefficient is determined according to the maximum daily rainfall of the target disaster sample and the maximum rainfall within the target period of the day of the target disaster sample.

[0014] In some embodiments, determining the rainfall mapping coefficient according to the maximum daily rainfall of the target disaster sample and the maximum rainfall within the target period of the target disaster sample on the same day includes:

[0015] The rainfall mapping coefficient is determined based on the ratio of the maximum daily rainfall of each target disaster sample to the maximum rainfall in the target period of the same day of the same target disaster sample, combined with the number of each target disaster sample.

[0016] In some embodiments, determining the predicted rainfall of the target area in the future target period according to the rainfall mapping coefficient, the predicted rainfall of the target area in the next 24 hours, and the rainfall mapping function corresponding to the target area includes:

[0017] Determining the predicted rainfall for the target area in the next 24 hours according to a preset 24-hour rainfall prediction model;

[0018] The rainfall mapping coefficient and the predicted rainfall of the target area in the next 24 hours are substituted into a pre-constructed rainfall mapping function of the target area to obtain the predicted rainfall of the target area in the future target period.

[0019] In some embodiments, determining a meteorological risk warning index for the target area during the future target period based on the predicted rainfall for the target area during the future target period, the effective rainfall for the target area in the previous preset days, and the geological environment parameters includes:

[0020] The predicted rainfall of the target area in the future target period, the effective rainfall of the target area in the preset days before, and the geological environment parameters are input as input data into the pre-built short-term warning model of the target area to obtain the meteorological risk warning index of the target area in the future target period.

[0021] In some embodiments, the method further comprises:

[0022] The meteorological risk level of the target area in the future target period is determined according to a preset warning classification threshold and a meteorological risk warning index of the target area in the future target period.

[0023] In some embodiments, the method further comprises:

[0024] Visually output the meteorological risk level of the target area during the future target period.

[0025] In a second aspect, a meteorological risk warning device is provided in this embodiment, comprising: an acquisition module, a coefficient determination module, a rainfall prediction module, and a meteorological risk warning module; wherein:

[0026] The acquisition module is used to obtain historical rainfall data that matches historical disaster samples of the target area hour by hour, as well as geological environment parameters of the target area;

[0027] The coefficient determination module is used to determine a rainfall mapping coefficient based on the historical rainfall data; the rainfall mapping coefficient represents: a mapping relationship between the rainfall in the next 24 hours and the rainfall in a future target period; the target period is less than 24 hours;

[0028] The rainfall prediction module is used to determine the predicted rainfall of the target area in the future target period based on the rainfall mapping coefficient, the predicted rainfall of the target area in the next 24 hours, and the rainfall mapping function corresponding to the target area;

[0029] The meteorological risk warning module is used to determine the meteorological risk warning index of the target area in the future target period based on the predicted rainfall of the target area in the future target period, the effective rainfall of the target area in the preset days before, and the geological environment parameters.

[0030] In a third aspect, a weather risk warning system is provided in this embodiment, including: a server device and a display device;

[0031] The server device is used to execute the meteorological risk warning method described in the first aspect above;

[0032] The display device is used to visually display the output result of the server device.

[0033] In a fourth aspect, a storage medium is provided in this embodiment, on which a computer program is stored. When the program is executed by a processor, the meteorological risk warning method described in the first aspect is implemented.

[0034] Compared with related technologies, this embodiment provides a meteorological risk warning method, device, system, and storage medium. The meteorological risk warning method first obtains historical rainfall data that matches historical disaster samples in the target area hour by hour, as well as the geological environment parameters of the target area; then, based on the historical rainfall data, determines the rainfall mapping coefficient; the rainfall mapping coefficient represents: the mapping relationship between the rainfall in the next 24 hours and the rainfall in the future target period; the target period is less than 24 hours; based on the rainfall mapping coefficient, the predicted rainfall in the target area in the next 24 hours, and the rainfall mapping function corresponding to the target area, the predicted rainfall in the target area in the future target period is determined; finally, based on the predicted rainfall in the target area in the future target period, the effective rainfall in the target area for a preset number of days before, and the geological environment parameters, the meteorological risk warning index of the target area in the future target period is determined. It can achieve meteorological risk warnings with higher time precision and take into account the impact of the geological environment on rainfall, thereby improving the timeliness and accuracy of meteorological warnings.

[0035] The details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0037] Figure 1 This is a hardware structure block diagram of a terminal of the meteorological risk warning method according to an embodiment of the present application;

[0038] Figure 2 This is a flow chart of the meteorological risk warning method according to an embodiment of the present application;

[0039] Figure 3 is a flow chart of a meteorological risk warning method according to some embodiments of the present application;

[0040] Figure 4 This is a technical diagram of a meteorological risk warning method according to an embodiment of the present application;

[0041] Figure 5 This is a structural block diagram of a meteorological risk warning device according to an embodiment of the present application;

[0042] Figure 6 Schematic diagram of the structure of the meteorological risk warning system of this embodiment. DETAILED DESCRIPTION

[0043] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0044] Unless otherwise defined, technical or scientific terms used in this application shall have the ordinary meanings as understood by persons of ordinary skill in the art to which this application belongs. The terms "a," "an," "the," "these," and similar expressions in this application do not denote limitations on quantity and may be singular or plural. The terms "comprise," "include," "have," and any variations thereof, as used in this application, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units) but may include unlisted steps or modules (units) or other steps or modules (units) inherent to the process, method, product, or device. The terms "connected," "connected," "coupled," and similar expressions used in this application are not limited to physical or mechanical connections but may include electrical connections, whether direct or indirect. As used in this application, "plurality" means two or more. "And / or" describes an association between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone; A and B exist simultaneously; or B exists alone. Generally, the character " / " indicates that the objects in the preceding and following relationship are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0045] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 This is a hardware structure diagram of the terminal of the meteorological risk warning method of this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 The processor 102 (only one is shown) and a memory 104 for storing data, wherein the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The terminal may also include a transmission device 106 for communication functions and an input / output device 108. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0046] Memory 104 can be used to store computer programs, such as software programs and modules of application software, such as the computer program corresponding to the meteorological risk warning method in this embodiment. Processor 102 executes the computer program stored in memory 104 to execute various functional applications and data processing, thereby implementing the above-mentioned method. Memory 104 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 104 may further include memory remotely located relative to processor 102, and these remote memories may be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0047] Transmission device 106 is used to receive or transmit data via a network. This network may include a wireless network provided by the terminal's communications provider. In one embodiment, transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0048] In this embodiment, a meteorological risk early warning method is provided. Figure 2 Flowchart of the meteorological risk warning method of this embodiment is as follows: Figure 2 As shown, the process includes the following steps:

[0049] Step S210: Acquire historical rainfall data that matches historical disaster samples in the target area hour by hour, and geological environment parameters of the target area.

[0050] Specifically, historical disaster samples collected previously can be cleaned to identify historical disaster samples with clear occurrence times in a target area, and hourly rainfall data can be matched to these historical disaster samples. The target area can be an administrative district divided according to the administrative division hierarchy, for example, Province A, City B, District C. Furthermore, the target area can also be a geographical area divided according to other division criteria, which is not specifically limited in this embodiment. Historical disaster samples can specifically be case information corresponding to previously recorded disaster events (such as debris flows, flash floods, and landslides). For example, each historical disaster sample can include the time, location, type, intensity, and environmental information that triggered the disaster. The rainfall data matched to the historical disaster samples can be rainfall data associated with the historical disaster samples in terms of time and location. The geological environmental parameters can be gridded geological quantitative parameters covering several geological indicators, such as slope, rock formations, and vegetation. In some embodiments, the geological environmental parameters can specifically include slope, aspect, vegetation, engineering geological rock formations, stratigraphic lithology, land use type, forest type, and average annual rainfall. Among them, historical disaster samples and historical rainfall data can be extracted from a pre-built database or an associated cloud, and the historical disaster samples and historical rainfall data can be matched hour by hour. In addition, the geological environment parameters of the target area can be extracted from the pre-built database or an associated cloud.

[0051] Step S220, determining a rainfall mapping coefficient based on historical rainfall data; the rainfall mapping coefficient represents a mapping relationship between the rainfall in the next 24 hours and the rainfall in a future target period; the target period is less than 24 hours.

[0052] Specifically, various rainfall parameters can be extracted from historical rainfall data, such as the 24-hour cumulative rainfall corresponding to each historical disaster sample, the rolling rainfall for a target period (e.g., three hours), and the maximum rainfall within the target period for the day (e.g., the maximum three-hour rainfall for the day). Statistics are then collected from these extracted rainfall parameters to determine the mapping relationship between the 24-hour rainfall and the rainfall for the target period, thereby deriving the aforementioned rainfall mapping coefficients. It is understood that different target areas will have different corresponding rainfall mapping coefficients, which can be adjusted based on the historical rainfall data for that target area.

[0053] Step S230 , determining the predicted rainfall of the target area in the future target period based on the rainfall mapping coefficient, the predicted rainfall of the target area in the next 24 hours, and the rainfall mapping function corresponding to the target area.

[0054] The rainfall mapping function can be a function pre-established based on multiple rainfall data sets, representing a mathematical relationship between the predicted rainfall for the next 24 hours and the predicted rainfall for a future target period (e.g., the next three hours). The rainfall mapping function can include a rainfall mapping coefficient and a predetermined correction coefficient. Based on the rainfall mapping coefficient and the correction coefficient, the predicted rainfall for the target area for the next 24 hours is used as input, and the predicted rainfall for the target area for the next target period is used as output. In this way, based on the rainfall forecast for the next 24 hours and the mapping relationship between the 24-hour rainfall and the rainfall for the target period, a rainfall forecast for the future target period can be achieved, thereby achieving a more refined rainfall forecast with a finer granularity.

[0055] Step S240 , determining a meteorological risk warning index for the target area in the future target period based on the predicted rainfall for the target area in the future target period, the effective rainfall for the target area in the previous preset days, and geological environment parameters.

[0056] A general model formula can be constructed in advance for the predicted rainfall and meteorological risk warning index. Specifically, a general model formula for warning the geological hazard risk can be constructed by referring to the geological hazard meteorological risk warning standard. Then, based on this general model formula, a short-term warning model for the future target period can be constructed. The predicted rainfall of the target area in the future target period obtained in step S230, the effective rainfall in the target area for the preset number of days before, and the geological environment parameters are input into the short-term warning model, and the meteorological risk warning index of the target area in the future target period is output. Based on this, the meteorological risk prediction of the target area in the future target period can be completed.

[0057] Related technologies often use 24-hour critical rainfall thresholds or machine learning algorithms to provide meteorological risk warnings at a daily granularity. This approach fails to reflect the instantaneous dynamic characteristics of rainfall, resulting in insufficient timeliness for short-term warnings. Furthermore, the impact of geological complexity on rainfall can also lead to low warning accuracy. This approach also fails to meet the required temporal precision for short-term warnings.

[0058] For example, related technologies often construct rainfall prediction models based on disaster samples with daily time accuracy. However, the insufficient temporal precision of these samples makes it impossible to construct short-term models. Furthermore, these daily rainfall forecasts cannot cope with sudden changes in rainfall within a short period of time (e.g., within three hours). For example, a disaster in Area C occurred at 8:00 a.m. on a certain day in a certain month of a certain year. The total rainfall for that day was 80 millimeters (mm), but the rainfall in the three hours before the disaster was 45 mm, exceeding the safety threshold for three-hour rainfall. Using existing daily rainfall forecasts would miss the critical warning window, making it impossible to provide timely warnings of three-hour meteorological risks. Furthermore, the machine learning used in these technologies relies on large amounts of data and has poor interpretability.

[0059] To improve the temporal accuracy of meteorological risk warnings, this embodiment analyzes various rainfall data and considers the mapping patterns between rainfall parameters for a 24-hour period and a target period (e.g., 3 hours). This mapping pattern, combined with the 24-hour rainfall forecast, enables a more refined rainfall forecast for the target period, thereby providing more timely meteorological risk warnings. Furthermore, this embodiment considers the impact of the geological environment when implementing meteorological risk warnings, combining relevant geological parameters with predicted rainfall to determine a meteorological risk warning index. This approach accounts for the impact of geological environmental complexity on rainfall, improving warning accuracy.

[0060] Therefore, through the above steps S210 to S240, the historical rainfall data of the historical disaster samples of the target area are matched hour by hour, as well as the geological environment parameters of the target area; based on the historical rainfall data, the rainfall mapping coefficient is determined; the rainfall mapping coefficient represents: the mapping relationship between the rainfall in the next 24 hours and the rainfall in the future target period; the target period is less than 24 hours; based on the rainfall mapping coefficient, the predicted rainfall of the target area in the next 24 hours, and the rainfall mapping function corresponding to the target area, the predicted rainfall of the target area in the future target period is determined; based on the predicted rainfall of the target area in the future target period, the effective rainfall of the target area in the preset days before, and the geological environment parameters, the meteorological risk warning index of the target area in the future target period is determined. It can achieve meteorological risk warnings with higher time accuracy and take into account the impact of the geological environment on rainfall, thereby improving the timeliness of meteorological warnings and improving the accuracy of warnings.

[0061] In one embodiment, based on the above step S220, determining the rainfall mapping coefficient according to historical rainfall data may specifically include:

[0062] Based on historical rainfall data, the target disaster sample corresponding to the maximum daily rainfall is determined; based on the maximum daily rainfall of the target disaster sample and the maximum rainfall in the target period of the day, the rainfall mapping coefficient is determined.

[0063] By statistically analyzing historical rainfall data and following preset extraction rules, the maximum daily rainfall within a preset number of days and the maximum rainfall within a target period on the date associated with the maximum daily rainfall can be determined. The maximum rainfall within a target period can be obtained by rolling statistics of hourly rainfall data using the target period as a time window, obtaining rainfall for each target period within the day (for example, rainfall every three hours). The maximum rainfall within the target period can then be determined based on the rainfall for each target period. Furthermore, the rainfall mapping coefficient can be determined based on the maximum daily rainfall for multiple target disaster samples and the maximum rainfall within the target period on the day.

[0064] This embodiment can solve the mapping relationship between 24-hour rainfall and target period rainfall based on rainfall parameters corresponding to two time spans of 24 hours and target period in historical data, thereby providing a data basis for subsequent refined rainfall forecasting.

[0065] In one embodiment, the rainfall mapping coefficient is determined based on the maximum daily rainfall of the target disaster sample and the maximum rainfall within the target period of the target disaster sample on the same day, which may specifically include:

[0066] The rainfall mapping coefficient is determined based on the ratio of the maximum daily rainfall of each target disaster sample to the maximum rainfall during the target period of the same day for the same target disaster sample, combined with the number of target disaster samples.

[0067] Specifically, we can calculate the ratio of the maximum daily rainfall of each target disaster sample to the maximum rainfall in the corresponding target period of the day. Determine the number of samples for each ratio, and take the weighted average of each ratio according to the corresponding number of samples to obtain the rainfall mapping coefficient. The specific solution process can be referred to the following formula:

[0068] ;

[0069] Among them, n i It is a ratio of the maximum daily rainfall of the same target disaster sample to the maximum rainfall in the target period of the same day; N i Indicates the ratio is n i where N is the number of samples for the target disaster; m is the rainfall mapping coefficient. For example, if m is 2.1, the rainfall mapping coefficient between the 24-hour rainfall in the target area and the rainfall during the target period is 2.1.

[0070] This embodiment can achieve accurate mapping of 24-hour rainfall and target period rainfall based on different historical disaster samples, thereby achieving more refined rainfall forecasts with higher time accuracy.

[0071] Additionally, in one embodiment, based on the above step S230, the predicted rainfall of the target area in the next 24 hours is determined according to the rainfall mapping coefficient, the predicted rainfall of the target area in the next target period, and the rainfall mapping function corresponding to the target area. Specifically, the following steps may be performed:

[0072] According to the preset 24-hour rainfall prediction model, the predicted rainfall of the target area in the next 24 hours is determined; the rainfall mapping coefficient and the predicted rainfall of the target area in the next 24 hours are substituted into the pre-built rainfall mapping function of the target area to obtain the predicted rainfall of the target area in the future target period.

[0073] Based on a pre-built 24-hour rainfall prediction model, the predicted rainfall for the target area over the next 24 hours can be first predicted. This 24-hour rainfall prediction can be achieved through machine learning, or by utilizing a pre-built 24-hour rainfall prediction model formula based on real-time rainfall data and geological environment parameters. This embodiment does not specifically limit the 24-hour rainfall prediction process.

[0074] Then, based on the rainfall mapping function, the predicted rainfall of the target area in the future target period can be determined. Specifically, the rainfall prediction for the future target period can be completed by referring to the following formula:

[0075] R ah =m×R 24h +C;

[0076] Among them, R ah is the predicted rainfall in the future target period. If the target period is 3 hours, then R ah R 3h ; m is the rainfall mapping coefficient; R 24h is the predicted rainfall in the next 24 hours; C is the correction parameter, which can be fitted according to the rainfall data corresponding to the historical disaster samples in the target area.

[0077] Therefore, this embodiment can combine the rainfall forecast for the next 24 hours and the mapping of the 24-hour rainfall and the rainfall for the target period to achieve a more timely rainfall forecast for the target period.

[0078] Furthermore, in one embodiment, based on the above step S240, the meteorological risk warning index of the target area in the future target period is determined according to the predicted rainfall of the target area in the future target period, the effective rainfall of the target area in the previous preset days, and the geological environment parameters. Specifically, the meteorological risk warning index of the target area in the future target period may include:

[0079] The predicted rainfall in the target area during the future target period, the effective rainfall in the target area during the preset days before, and the geological environment parameters are used as input data and input into the pre-built short-term warning model of the target area to obtain the meteorological risk warning index of the target area during the future target period.

[0080] The short-term warning model can be determined based on a pre-set short-term warning model formula. The short-term warning model can have the following form:

[0081] T 3h =f(G,R 3h ,R p );

[0082] Among them, T 3his the early warning index, G is the geological environment parameter, which can be a quantitative geological environment parameter based on a grid (for example, a 500-meter grid) covering multiple indicators such as slope, rock group, and vegetation; R 3h The predicted rainfall of the target area in the future target period; R p The effective rainfall is the amount of rainfall in the previous preset days. The effective rainfall can be the amount of rainfall that has an impact on the occurrence of the disaster before the disaster occurs. In some embodiments, the effective rainfall can be determined by referring to the following formula:

[0083] ;

[0084] Among them, R j is the daily rainfall in the previous j days (in mm); n is the number of effective rainfall days (the number of rainfall days with rainfall reaching the preset threshold); k is the effective rainfall coefficient (specifically, it can be the proportion of rainfall that actually participates in soil infiltration, runoff or groundwater recharge, and can be a dimensionless value between 0 and 1).

[0085] Exemplarily, the short-term warning model may further have the following form:

[0086] T 3h =G×(m×R 3h +R p );

[0087] Therefore, by combining geological environmental parameters, predicted rainfall for a future target period, and effective rainfall in the target area a preset number of days prior, this embodiment can achieve more timely, precise, and accurate meteorological risk warnings. This can improve the success rate of short-term warnings and reduce the warning area.

[0088] It is understandable that coordinated warnings can be implemented for different geographical regions based on the meteorological risk warning index corresponding to different target areas. For example, coordinated warnings can be implemented at the province-city-county level, with warning outputs down to the village level. Furthermore, the aforementioned rainfall mapping coefficients can be dynamically adjusted based on different target areas to adapt to different geological environments.

[0089] Compared with some related technologies, the warning level classification relies on the probability calculated by machine learning and cannot explain the specific geological and rainfall coupling mechanism. This embodiment constructs a general model formula for meteorological risk warning based on geological environment parameters, effective rainfall, and predicted rainfall, thereby improving the interpretability of meteorological risk warning.

[0090] Additionally, in one embodiment, the above-mentioned meteorological risk warning method may further include:

[0091] The meteorological risk level of the target area in the future target period is determined based on the pre-set warning classification threshold and the meteorological risk warning index of the target area in the future target period.

[0092] Different warning level thresholds can be set to implement graded warnings. For example, corresponding warning level thresholds can be set according to the red warning, orange warning, yellow warning and blue warning corresponding to the meteorological risk warning:

[0093] When T 3h When the intensity is ≥6.6 (corresponding to the cumulative proportion of historical disasters ≥75%), a red alert is confirmed during the target period;

[0094] When 4.1≤T 3h <6.6, confirm that the target period has an orange warning;

[0095] When 1.3≤T 3h When the temperature is less than 4.1, a yellow warning is confirmed during the target period;

[0096] When 0.4≤T 3h When the temperature is less than 1.3, a blue warning is confirmed during the target period.

[0097] The setting of the threshold can be determined based on industry standards and historical disaster samples.

[0098] It should also be noted that the hit rate and granularity of the meteorological risk warning method of this embodiment can be verified based on past historical disaster samples, such as typhoon cases in a certain year, by simulating the rainfall process of the historical disaster samples.

[0099] In particular, in one embodiment, the above-mentioned meteorological risk warning method may further include:

[0100] Visualize the meteorological risk level of the target area during the target future period. Dynamic visualization of the meteorological risk level during the target future period can be achieved through graphics, text, and charts on the associated display interface, using both spatial and temporal distribution dimensions. For example, spatial distribution maps of meteorological risk warnings can be displayed based on geographic information systems (such as ArcGIS and QGIS), Python libraries, and mapping platforms.

[0101] Figure 3 Flowcharts of meteorological risk warning methods in some embodiments are shown in FIG. Figure 3 As shown, the meteorological risk early warning method includes the following steps:

[0102] Step S301: Acquire historical rainfall data that matches historical disaster samples in the target area hour by hour, and geological environment parameters of the target area.

[0103] Step S302: Determine the target disaster sample corresponding to the maximum daily rainfall based on historical rainfall data.

[0104] Step S303 , determining a rainfall mapping coefficient based on the ratio of the maximum daily rainfall of each target disaster sample to the maximum rainfall in the target period of the same day of the same target disaster sample, combined with the number of target disaster samples.

[0105] Step S304: Determine the predicted rainfall in the target area in the next 24 hours based on a preset 24-hour rainfall prediction model.

[0106] Step S305 , substituting the rainfall mapping coefficient and the predicted rainfall of the target area in the next 24 hours into the pre-built rainfall mapping function of the target area to obtain the predicted rainfall of the target area in the future target period.

[0107] In step S306, the predicted rainfall of the target area in the future target period, the effective rainfall of the target area in the preset number of days before, and the geological environment parameters are input as input data into a pre-built short-term warning model for the target area to obtain the meteorological risk warning index of the target area in the future target period.

[0108] Step S307 , determining the meteorological risk level of the target area in the future target period according to a preset warning classification threshold and the meteorological risk warning index of the target area in the future target period.

[0109] Step S308: Visually output the meteorological risk level of the target area in the future target period.

[0110] The above steps S301 to S308, based on historical disaster samples, realize the determination of the correlation between the indicators of 24-hour rainfall and the rainfall in the target period, and then realize the dynamic conversion of 24-hour predicted rainfall to predicted rainfall in the target period based on the mapping function. Combined with the quantitative indicators of geological environmental hazards, a grid-based short-term meteorological warning level mechanism is constructed, which realizes meteorological risk warnings with higher timeliness, higher time precision and higher accuracy.

[0111] Figure 4 This is a technical diagram of a meteorological risk warning method according to the present embodiment. Figure 4As shown, implementing meteorological risk warnings involves the stages of model and data foundation analysis, the construction of a three-hour rainfall forecast model, and the development of a three-hour short-term warning model. During this phase, existing meteorological risk warning models for the target area can be compiled and organized to develop a general model formula and warning indicator system, combining warning business needs with industry standards for geological disaster warnings. Furthermore, geological survey results can be compiled to obtain geological hazard and geoenvironmental data. This geological hazard data can be used to generate the aforementioned historical disaster samples, while the geoenvironmental data can be used to obtain the aforementioned geoenvironmental parameters.

[0112] During the three-hour rainfall forecast model construction phase, early warning zoning for geometeorological risks can be implemented based on the geological environment, disaster-prone zoning, and risk zoning, identifying target areas. Historical disaster samples are collected for the target areas, cleaned, and data with specific time points is selected. Furthermore, the relationship between 24-hour rainfall indicators and geological disasters is analyzed. Based on the 24-hour stimulated rainfall and the previous effective rainfall, 24-hour rainfall forecast models are constructed for different target areas. Based on rainfall characteristics and patterns from several years (for example, statistics on the maximum daily rainfall and the maximum three-hour rainfall on that day), the relationship between the indicators of the next 24 hours and the next three hours is analyzed to determine the rainfall mapping coefficients. Furthermore, the three-hour rainfall forecast model is constructed for each region. During the three-hour short-term warning model construction phase, the basic conditions for building the short-term warning model are established, the method and process for building the short-term warning model are determined, and the operational data support for the short-term warning model is combined to achieve the construction of the three-hour short-term warning model.

[0113] In this embodiment, a weather risk warning device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments. Details already described are not repeated here. The terms "module," "unit," "subunit," etc. used below refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0114] Figure 5 : is a structural block diagram of the weather risk warning device 50 of this embodiment, as shown in FIG. Figure 5 As shown, the meteorological risk warning device 50 includes: an acquisition module 52, a coefficient determination module 54, a rainfall prediction module 56 and a meteorological risk warning module 58; wherein:

[0115] An acquisition module 52 is used to obtain hourly historical rainfall data that matches historical disaster samples in the target area, as well as geological environmental parameters of the target area; a coefficient determination module 54 is used to determine a rainfall mapping coefficient based on historical rainfall data; the rainfall mapping coefficient represents the mapping relationship between the rainfall in the next 24 hours and the rainfall in the future target period; the target period is less than 24 hours; a rainfall prediction module 56 is used to determine the predicted rainfall in the target area in the future target period based on the rainfall mapping coefficient, the predicted rainfall in the target area in the next 24 hours, and the rainfall mapping function corresponding to the target area; a meteorological risk warning module 58 is used to determine the meteorological risk warning index of the target area in the future target period based on the predicted rainfall in the target area in the future target period, the effective rainfall in the target area for a preset number of days before, and geological environmental parameters.

[0116] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0117] This embodiment also provides a meteorological risk warning system. Figure 6 This is a schematic diagram of the structure of the meteorological risk warning system 60 of this embodiment. Figure 6 As shown, the meteorological risk warning system 60 may include: a server device 62 and a display device 64; the server device 62 is used to execute the meteorological risk warning method provided by any of the above embodiments; and the display device 64 is used to visually display the output results of the server device 62.

[0118] It should be noted that, for specific examples in this embodiment, reference may be made to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0119] In addition, in conjunction with the meteorological risk warning method provided in the above embodiments, a storage medium may be provided in this embodiment to implement the method. The storage medium stores a computer program that, when executed by a processor, implements any of the meteorological risk warning methods in the above embodiments.

[0120] It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0121] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0122] Obviously, the accompanying drawings are merely examples or embodiments of the present application. A person skilled in the art can also apply the present application to other similar situations based on these drawings without inventive effort. Furthermore, it is understandable that, although the work involved in this development process may be complex and lengthy, certain design, manufacturing, or production changes based on the technical content disclosed in this application are merely routine technical means for a person skilled in the art and should not be considered to constitute a deficiency in the disclosure of the present application.

[0123] The term "embodiment" as used in this application refers to specific features, structures, or characteristics described in conjunction with the embodiment that can be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily mean that the embodiment is the same, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is understood, either explicitly or implicitly, by those skilled in the art that the embodiments described in this application can be combined with other embodiments when there is no conflict.

[0124] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of patent protection. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A meteorological risk early warning method, characterized in that: include: Obtaining historical rainfall data that matches historical disaster samples in the target area hour by hour, as well as geological environment parameters of the target area; determining a rainfall mapping coefficient based on the historical rainfall data; The rainfall mapping coefficient represents the mapping relationship between the rainfall in the next 24 hours and the rainfall in the future target period; The target period is less than 24 hours; Determining the predicted rainfall of the target area in the future target period according to the rainfall mapping coefficient, the predicted rainfall of the target area in the next 24 hours, and the rainfall mapping function corresponding to the target area; The meteorological risk warning index of the target area in the future target period is determined based on the predicted rainfall of the target area in the future target period, the effective rainfall of the target area in the previous preset days, and the geological environment parameters.

2. The meteorological risk early warning method according to claim 1, characterized in that: Determining a rainfall mapping coefficient based on the historical rainfall data includes: Determining target disaster samples corresponding to maximum daily rainfall based on the historical rainfall data; The rainfall mapping coefficient is determined according to the maximum daily rainfall of the target disaster sample and the maximum rainfall within the target period of the day of the target disaster sample.

3. The meteorological risk early warning method according to claim 2, characterized in that: The rainfall mapping coefficient is determined according to the maximum daily rainfall of the target disaster sample and the maximum rainfall within the target period of the target disaster sample on the same day, including: The rainfall mapping coefficient is determined based on the ratio of the maximum daily rainfall of each target disaster sample to the maximum rainfall in the target period of the same day of the same target disaster sample, combined with the number of each target disaster sample.

4. The meteorological risk early warning method according to claim 1, characterized in that: Determining the predicted rainfall of the target area in the future target period according to the rainfall mapping coefficient, the predicted rainfall of the target area in the next 24 hours, and a rainfall mapping function corresponding to the target area, including: Determining the predicted rainfall for the target area in the next 24 hours according to a preset 24-hour rainfall prediction model; The rainfall mapping coefficient and the predicted rainfall of the target area in the next 24 hours are substituted into a pre-constructed rainfall mapping function of the target area to obtain the predicted rainfall of the target area in the future target period.

5. The meteorological risk early warning method according to claim 1, characterized in that: Determining a meteorological risk warning index for the target area in the future target period based on the predicted rainfall for the target area in the future target period, the effective rainfall for the target area in the previous preset days, and the geological environment parameters, includes: The predicted rainfall of the target area in the future target period, the effective rainfall of the target area in the preset days before, and the geological environment parameters are input as input data into the pre-built short-term warning model of the target area to obtain the meteorological risk warning index of the target area in the future target period.

6. The meteorological risk early warning method according to any one of claims 1 to 5, characterized in that: The method further comprises: The meteorological risk level of the target area in the future target period is determined according to a preset warning classification threshold and a meteorological risk warning index of the target area in the future target period.

7. The meteorological risk early warning method according to claim 6, characterized in that: The method further comprises: Visually output the meteorological risk level of the target area during the future target period.

8. A meteorological risk warning device, characterized in that: include: Acquisition module, coefficient determination module, rainfall prediction module and meteorological risk warning module; among them: The acquisition module is used to obtain historical rainfall data that matches historical disaster samples of the target area hour by hour, as well as geological environment parameters of the target area; The coefficient determination module is used to determine a rainfall mapping coefficient based on the historical rainfall data; the rainfall mapping coefficient represents: a mapping relationship between the rainfall in the next 24 hours and the rainfall in a future target period; the target period is less than 24 hours; The rainfall prediction module is used to determine the predicted rainfall of the target area in the future target period based on the rainfall mapping coefficient, the predicted rainfall of the target area in the next 24 hours, and the rainfall mapping function corresponding to the target area; The meteorological risk warning module is used to determine the meteorological risk warning index of the target area in the future target period based on the predicted rainfall of the target area in the future target period, the effective rainfall of the target area in the preset days before, and the geological environment parameters.

9. A meteorological risk warning system, characterized in that: include: Server equipment and display equipment; The server device is used to execute the meteorological risk warning method according to any one of claims 1 to 7; The display device is used to visually display the output result of the server device.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the meteorological risk warning method according to any one of claims 1 to 7 are implemented.

Images