Medium-and-long-term rainstorm flood early warning method, device and equipment based on regional scale

Abstract

The embodiment of the invention discloses a medium and long term rainstorm flood early warning method, device and equipment based on regional scale. A specific embodiment of the method comprises the steps of obtaining a historical meteorological data set and a historical flood data set in a preset time period in a target area from a database; generating a complemented meteorological data set; establishing a flood relevance model, and generating rainfall flood relevance features; performing data extraction on the historical meteorological data set to obtain an extreme rainfall data set, and generating an extreme rainfall recurrence period sequence and a corresponding rainfall extremum sequence; performing model testing on the flood relevance model to generate a flood prediction check value sequence; performing result verification on the flood prediction verification value sequence to generate a verification result; and performing flood prediction on the target area to generate medium-and-long-term flood early warning information in the target area, and executing early warning operation according to the medium-and-long-term flood early warning information. According to the embodiment, the flood early warning operation can be started in time.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of flood warning, and particularly to a medium- and long-term rainstorm flood warning method, device, and equipment based on a regional scale. Background Art

[0002] In recent years, with the rapid development of big data and artificial intelligence technologies, the meteorological prediction ability has been significantly improved. Currently, when carrying out flood warning, the commonly adopted methods are as follows: (1)

[0003] For regional flood risk assessment, "Munich Re" and "Swiss Re" risk maps are mostly used. This method is mainly based on local meteorological, hydrological, and geological conditions combined with the historical flood occurrence frequency, and is a comprehensive flood risk zoning map.

[0004] (2) For medium- and long-term rainstorm forecasts, it mainly relies on the model simulation methods of national meteorological departments (such as the U.S. National Oceanic and Atmospheric Administration, the Central Meteorological Bureau, etc.). This method is achieved based on the coordinated assimilation of multi-source data of the ocean, sea ice, and atmosphere.

[0005] (3) For dynamic flood risk assessment with a certain forecasting nature (such as the "National Small River Flood Meteorological Risk Warning" issued by the Central Meteorological Observatory), it mainly uses short-term forecasting models based on real-time monitored meteorological data from ground radars, stations, etc., combined with local hydrological data. The forecasting period is about 24 hours.

[0006] However, it is found in practice that when using the above methods for flood warning, the following technical problems often exist:

[0007] First, for the flood risk area results of industry-common risk maps such as "Munich Re" and "Swiss Re", the meteorological, hydrological, and geological data used are mostly collected once, and the update frequency is mostly once every few years. Generally, it has a relatively high confidence to judge the rainstorm frequency and rainstorm events in a certain area through this method, but it is difficult to reflect the occurrence of extreme weather through this method. For the natural fluctuation of precipitation (such as: the precipitation shows a certain upward or downward trend within a period of time, and the evaluation period happens to be in the rising stage of precipitation); and the local precipitation characteristics affected by greenhouse gas emissions and land use changes brought about by human activities, resulting in frequent extreme precipitation events, it is difficult to effectively evaluate, thus making it difficult to initiate flood warning operations in a timely manner;

[0008] Second, to achieve medium- and long-term heavy rain (precipitation) prediction and forecasting based on the pattern simulation method, it is necessary to coordinately assimilate multi-source observation data such as the ocean, sea ice, and atmosphere, which greatly occupies storage resources and computing resources. In addition, the spatial resolution of the results of this method is low, and the spatial scales are mostly global and national scales, making it difficult to ensure accuracy and reliability in a smaller area. As a result, it is difficult to initiate flood warning operations in a timely manner;

[0009] Third, the flood risk assessment and warning generated based on the short-term and near-term forecasting model mainly rely on ground observation meteorological data. In underdeveloped areas, as well as vast deserts and jungles, the distribution density of radars and stations is sparse or even missing, seriously affecting the assessment accuracy of this method. As a result, it is difficult to initiate flood warning operations in a timely manner.

[0010] The above information disclosed in this background art section is only used to enhance the understanding of the background of the inventive concept. Therefore, it may include information that does not form the prior art known to ordinary skilled artisans in the country. Summary of the Invention

[0011] This disclosure of the content is in part for introducing the concepts in a concise form, which will be described in detail in the following detailed implementation section. This disclosure of the content is not intended to identify the key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0012] Some embodiments of this disclosure propose a medium- and long-term heavy rain and flood warning method, device, and equipment based on the regional scale to solve one or more of the technical problems mentioned in the above background art section.

[0013] In a first aspect, some embodiments of the present disclosure provide a method for medium- and long-term rainstorm flood warning based on regional scale, the method comprising: obtaining a historical meteorological data set and a historical flood data set within a preset time period in a target area from a database; in response to determining that the historical meteorological data set does not meet a preset reference condition, performing data back-calculation on the historical meteorological data set to generate a complemented meteorological data set; establishing a flood correlation model based on the complemented meteorological data set and the historical flood data set, and generating rainfall-flood correlation features through the flood correlation model, wherein the rainfall-flood correlation features characterize the correlation relationship between the rainfall degree and the flood degree in the target area; extracting data from the historical meteorological data set to obtain an extreme precipitation data set, and extracting precipitation recurrence characteristics from each extreme precipitation data in the extreme precipitation data set to generate an extreme precipitation recurrence period sequence and a corresponding precipitation extreme value sequence; based on the rainfall-flood correlation features, the extreme precipitation recurrence period sequence and the corresponding precipitation extreme value sequence, performing model testing on the flood correlation model to generate a flood prediction verification value sequence; performing result verification on the flood prediction verification value sequence to generate a verification result; in response to determining that the verification result meets a preset model verification condition, performing flood prediction on the target area through the flood correlation model to generate medium- and long-term flood warning information within the target area, and performing a warning operation according to the medium- and long-term flood warning information.

[0014] Second aspect, some embodiments of the present disclosure provide a medium- and long-term rainstorm flood warning device based on regional scale. The device includes: an acquisition unit configured to acquire a historical meteorological data set and a historical flood data set within a preset time period in a target area from a database; a data back-calculation unit configured to perform data back-calculation on the historical meteorological data set to generate a complemented meteorological data set in response to determining that the historical meteorological data set does not meet a preset reference condition; a model establishment and feature association unit configured to establish a flood correlation model based on the complemented meteorological data set and the historical flood data set, and generate rainfall-flood association features through the flood correlation model, where the rainfall-flood association features characterize the association relationship between the rainfall degree and the flood degree in the target area; a feature extraction unit configured to perform data extraction on the historical meteorological data set to obtain an extreme precipitation data set, and perform precipitation recurrence feature extraction on each extreme precipitation data in the extreme precipitation data set to generate an extreme precipitation recurrence period sequence and a corresponding precipitation extreme value sequence; a model testing unit configured to perform model testing on the flood correlation model based on the rainfall-flood association features, the extreme precipitation recurrence period sequence and the corresponding precipitation extreme value sequence to generate a flood prediction verification value sequence; a result verification unit configured to perform result verification on the flood prediction verification value sequence to generate a verification result; a flood prediction unit configured to perform flood prediction on the target area through the flood correlation model to generate medium- and long-term flood warning information in the target area and perform a warning operation according to the medium- and long-term flood warning information in response to determining that the verification result meets a preset model verification condition.

[0015] Third aspect, some embodiments of the present disclosure provide an electronic device, including: one or more processors; a storage device storing one or more programs thereon, when the one or more programs are executed by the one or more processors, enabling the one or more processors to implement the method described in any implementation manner of the first aspect.

[0016] Fourth aspect, some embodiments of the present disclosure provide a computer-readable medium storing a computer program thereon, where the program, when executed by a processor, implements the method described in any implementation manner of the first aspect.

[0017] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: Through the medium- and long-term rainstorm flood warning method based on the regional scale in some embodiments of the present disclosure, flood warning operations can be initiated in a timely manner. Specifically, the reason for the difficulty in initiating flood warning operations in a timely manner is as follows: The flood risk area results of the industry's commonly used risk maps use meteorological, hydrological, and geological data that are mostly collected once, and the update frequency is mostly once every few years. Usually, it has a relatively high confidence level to determine the rainstorm frequency and rainstorm events in a certain area through this method, but it is very difficult to reflect the occurrence of extreme weather through this method. For the natural fluctuation changes of precipitation (such as: precipitation shows a certain upward or downward trend within a period of time, and the evaluation period happens to be in the upward stage of precipitation); and the local precipitation characteristics affected by greenhouse gas emissions and changes in land use patterns brought about by human activities lead to frequent extreme precipitation events, which are difficult to effectively evaluate. As a result, it is difficult to initiate flood warning operations in a timely manner. Based on this, the medium- and long-term rainstorm flood warning method based on the regional scale in some embodiments of the present disclosure, first, obtains the historical meteorological data set and historical flood data set within a preset time period in the target area from the database. Then, in response to determining that the above historical meteorological data set does not meet the preset reference conditions, data back-calculation is performed on the above historical meteorological data set to generate a complemented meteorological data set. Here, data back-calculation can be used to supplement missing data. After that, based on the above complemented meteorological data set and the above historical flood data set, a flood correlation model is established, and rainfall-flood correlation characteristics are generated through the above flood correlation model. Among them, the above rainfall-flood correlation characteristics represent the correlation relationship between the rainfall degree and the flood degree in the above target area. Here, considering that the relationship between precipitation and flood disasters is non-linear, if it is necessary to correlate flood disaster forecasts based on precipitation forecasts, a flood correlation model needs to be established. Thus, it can be used to determine the correlation relationship between the rainfall degree and the flood degree in the target area. Then, data extraction is performed on the above historical meteorological data set to obtain an extreme precipitation data set, and precipitation recurrence characteristics are extracted from each extreme precipitation data in the above extreme precipitation data set to generate an extreme precipitation recurrence period sequence and the corresponding precipitation extreme value sequence. Here, through data extraction, it can be used to collect extreme precipitation data. At the same time, the extreme precipitation recurrence period can also be determined based on the collected extreme precipitation data. Thus, it is convenient to determine the precipitation level and flood disaster level. Next, based on the above rainfall-flood correlation characteristics, the above extreme precipitation recurrence period sequence and the corresponding precipitation extreme value sequence, the above flood correlation model is tested to generate a flood prediction verification value sequence. Here, through model testing, it can be used to detect whether the established model is reliable. In addition, the results of the above flood prediction verification value sequence are verified to generate a verification result. Here, through result verification, it can be used to determine whether the model can be used for flood prediction.Finally, in response to determining that the above verification result meets the preset model verification condition, flood prediction is performed on the above target area through the above flood correlation model to generate medium- and long-term flood warning information within the target area, and warning operations are executed according to the above medium- and long-term flood warning information. Thus, flood warning operations can be initiated in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent. Throughout the accompanying drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the elements and elements are not necessarily drawn to scale.

[0019] Figure 1 is a flowchart of some embodiments of a medium- and long-term rainstorm flood warning method based on a regional scale according to the present disclosure;

[0020] Figure 2a 、 Figure 2b 、 Figure 2c is a schematic diagram of a 60-day medium-term flood risk forecast according to some embodiments of a medium- and long-term rainstorm flood warning method based on a regional scale according to the present disclosure;

[0021] Figure 3 is a schematic diagram of a half-year flood risk forecast according to some embodiments of a medium- and long-term rainstorm flood warning device based on a regional scale according to the present disclosure;

[0022] Figure 4 is a schematic structural diagram of some embodiments of a medium- and long-term rainstorm flood warning device based on a regional scale according to the present disclosure;

[0023] Figure 5 is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the accompanying drawings and embodiments of the present disclosure are only for illustrative purposes and are not used to limit the protection scope of the present disclosure.

[0025] It should also be noted that, for the sake of convenience of description, only the parts related to the relevant invention are shown in the accompanying drawings. Without conflict, the embodiments and the features in the embodiments of the present disclosure can be combined with each other.

[0026] It should be noted that concepts such as "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependent relationships.

[0027] It should be noted that the modifiers "one" and "multiple" mentioned in this disclosure are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly specified in the context, it should be understood as "one or more".

[0028] The names of the messages or information exchanged between multiple devices in the embodiments of this disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0029] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0030] Figure 1 Flow 100 of some embodiments of a medium- and long-term rainstorm and flood warning method based on regional scale according to the present disclosure is shown. The medium- and long-term rainstorm and flood warning method based on regional scale includes the following steps:

[0031] Step 101, obtain a historical meteorological data set and a historical flood data set within a preset time period in a target area from a database.

[0032] In some embodiments, the execution subject of the medium- and long-term rainstorm and flood warning method based on regional scale can obtain the historical meteorological data set and the historical flood data set within a preset time period in the target area from the database in a wired or wireless manner.

[0033] It should be noted that the above wireless connection methods can include but are not limited to 3G / 4G connections, WiFi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (ultra wideband) connections, and other currently known or future-developed wireless connection methods.

[0034] In some optional implementation manners of some embodiments, the above execution subject obtaining the historical meteorological data set and the historical flood data set within a preset time period in the target area from the database may include the following steps:

[0035] The first step, obtain the historical meteorological data set within the above target area from the above database according to a preset time period. Wherein, the preset time period may be a period of time set in advance up to the current time point. For example, within 10 years, 30 years, etc.

[0036] Step 2: Determine the initial historical flood data within the above-mentioned target area in the above-mentioned database. The initial historical flood data characterizes the flood situation that occurred within the above-mentioned target area during the above-mentioned preset time period.

[0037] Step 3: Screen out the data within the above-mentioned preset time period from the above-mentioned initial historical flood data to obtain a historical flood data set. Each historical flood data in the above-mentioned historical flood data set may include, but is not limited to, at least one of the following: flood area identifier, flood start time point, flood end time point, flood range data, and flood cause information. Here, the flood area identifier characterizes the area through which the flood passed. The flood range data may include the boundary coordinates reached by the flood. The flood cause information may be an identifier characterizing the cause of the flood. For example, identifier 1: characterizes the factor of levee breach, identifier 2: characterizes the factor of river channel blockage, identifier 3: characterizes the factor of landslide, etc.

[0038] Step 102: In response to determining that the historical meteorological data set does not meet the preset reference conditions, perform data back-calculation on the historical meteorological data set to generate a complemented meteorological data set.

[0039] In some embodiments, the above-mentioned execution entity may, in response to determining that the historical meteorological data set does not meet the preset reference conditions, perform data back-calculation on the historical meteorological data set to generate a complemented meteorological data set.

[0040] In some optional implementation manners of some embodiments, the above-mentioned execution entity, in response to determining that the historical meteorological data set does not meet the preset reference conditions, performing data back-calculation on the historical meteorological data set to generate a complemented meteorological data set, may include the following steps:

[0041] Step 1: In response to determining that the historical meteorological data set does not meet the preset reference conditions, perform data back-calculation on the historical meteorological data set to generate a back-calculated data set. The above-mentioned reference condition may be that the value of a data field in the historical meteorological data is empty. For example, the value of the data field "precipitation" is empty. Then, based on the CMA-CPSv3 (China Meteorological Administration's third-generation global climate model) system, perform data back-calculation on the historical meteorological data set to generate a back-calculated data set.

[0042] Step 2: Perform data fusion on the above-mentioned back-calculated data set and the above-mentioned historical meteorological data set to obtain a complemented meteorological data set. Among them, the back-calculated data may be replaced with the corresponding historical meteorological data in the historical meteorological data set to obtain a complemented meteorological data set.

[0043] In the process of adopting technical solutions to solve the problems mentioned in the background art, there is often another technical problem as follows: Since it is difficult to issue flood warnings in a timely manner, it is difficult to detect in advance whether flood control equipment is in good condition. As a result, it is difficult to repair faulty flood control equipment in a timely manner. Consequently, the flood control equipment is difficult to start in a timely manner, and electrical resources are wasted. In response to the above technical problems, the inventor decided to adopt the following solutions.

[0044] Step 103: Based on the complemented meteorological data set and the historical flood data set, establish a flood correlation model, and generate rainfall-flood correlation features through the flood correlation model.

[0045] In some embodiments, the above-mentioned execution entity may establish a flood correlation model based on the complemented meteorological data set and the historical flood data set, and generate rainfall-flood correlation features through the flood correlation model. Among them, the above-mentioned rainfall-flood correlation features represent the correlation relationship between the rainfall degree and the flood degree in the target area.

[0046] In some optional implementation manners of some embodiments, the above-mentioned execution entity establishing a flood correlation model based on the complemented meteorological data set and the historical flood data set, and generating rainfall-flood correlation features through the flood correlation model may include the following steps:

[0047] First step: Extract target data from the complemented meteorological data set and the historical flood data set to generate a daily precipitation record set. Among them, each daily precipitation record in the daily precipitation record set may correspond to a flood event at each flood location in the target area, and the flood event may include precipitation data from one week before the start of the flood to the end of the flood corresponding to the flood location. Among them, the target data can be extracted from the complemented meteorological data set and the historical flood data set through the index code established by the precipitation field to obtain the precipitation record set.

[0048] Second step: Determine the day with the largest precipitation in each daily precipitation record in the daily precipitation record set to obtain a set of largest precipitation day identifiers. Among them, the date of each day with the largest precipitation can be determined as the largest precipitation day identifier. Third step: Based on the set of largest precipitation day identifiers, establish a probability density function of the largest daily precipitation. Among them, the probability density function of the largest daily precipitation can be: P(precipitation├|flood = 1┤).

[0049] Fourth step: Based on the daily precipitation record set, establish a regional daily precipitation probability density function. Here, the regional daily precipitation probability density function can be represented by P(precipitation).

[0050] Step 5: Determine the historical flood occurrence probability value sequences corresponding to each daily precipitation record in the above daily precipitation record set. Among them, the historical flood occurrence probability P(flood = 1) can be estimated from the historical flood occurrence locations and days.

[0051] Step 6: Based on the above historical flood occurrence probability value sequences, the above maximum daily precipitation probability density function, and the above regional daily precipitation probability density function, establish a flood correlation model. Among them, the established flood correlation model can be shown by the following formula: P(flood = 1│precipitation) = P(precipitation│flood = 1)P(flood = 1) / P(precipitation).

[0052] Step 7: Input the daily precipitation record set into the above flood correlation model to generate rainfall-flood correlation features. Among them, each daily precipitation record can be separately input into the above flood correlation model to solve the model parameters. Finally, the solved model parameters can be substituted into the flood correlation model as rainfall-flood correlation features.

[0053] Step 104: Extract data from the historical meteorological data set to obtain an extreme precipitation data set, and extract precipitation recurrence characteristics for each extreme precipitation data in the extreme precipitation data set to generate an extreme precipitation recurrence period sequence and the corresponding precipitation extreme value sequence.

[0054] In some embodiments, the above execution subject can extract data from the above historical meteorological data set to obtain an extreme precipitation data set, and extract precipitation recurrence characteristics for each extreme precipitation data in the extreme precipitation data set to generate an extreme precipitation recurrence period sequence and the corresponding precipitation extreme value sequence.

[0055] In some optional implementation manners of some embodiments, the above execution subject extracts data from the above historical meteorological data set to obtain an extreme precipitation data set, and extracts precipitation recurrence characteristics for each extreme precipitation data in the extreme precipitation data set to generate an extreme precipitation recurrence period sequence and the corresponding precipitation extreme value sequence, which may include the following steps:

[0056] First step: Divide the above target area into grid areas, and obtain the divided grid areas. Among them, the above target area can be divided into equidistant rectangular areas using a preset division ratio (for example, 10 kilometers) for grid division to obtain the divided grid areas.

[0057] Second step: Extract historical meteorological data that meets the preset numerical conditions from the above historical meteorological data set as extreme precipitation data to obtain an extreme precipitation data sequence. Among them, each extreme precipitation data in the above extreme precipitation data sequence can include the historical precipitation extreme value, and each extreme precipitation data can correspond to a region in the above divided grid area.

[0058] In the third step, determine the number of precipitation events in each extreme precipitation data in the above extreme precipitation dataset that are within a preset time period and meet the preset rainfall conditions, to obtain a precipitation event number set. Among them, the preset rainfall condition can be that the rainfall amount is greater than a preset threshold. Thus, the number of times of rainfall amounts greater than the preset threshold in each region within the preset time period can be counted.

[0059] In the fourth step, use the above precipitation event number set to generate an extreme precipitation recurrence period sequence. Among them, the storm frequency of each precipitation event in all precipitation events can be determined. The reciprocal of this storm frequency is determined as the average interval time for a rainfall with a storm intensity to occur once. The extreme precipitation recurrence period is obtained.

[0060] As an example, the extreme precipitation recurrence period can include time periods such as twenty years, fifty years, one hundred years, one thousand years, etc. This is used to represent storm levels such as once in twenty years, once in fifty years, once in one hundred years, once in one thousand years, etc.

[0061] In the fifth step, according to the above historical meteorological dataset, fit a historical precipitation Pearson distribution curve model corresponding to the raster regions after the above division. Among them, the historical precipitation data corresponding to the historical meteorological dataset can be used to fit a preset Pearson type 3 distribution curve as the historical precipitation Pearson distribution curve model.

[0062] In the sixth step, determine the distribution parameters of the probability density of the above historical precipitation Pearson distribution curve, where the above distribution parameters include a precipitation shape parameter, a precipitation scale parameter, and a precipitation location parameter. Here, the precipitation shape parameter (α), the precipitation scale parameter (β), and the precipitation location parameter (ξ).

[0063] In the seventh step, use the above historical precipitation Pearson distribution curve and the above distribution parameters to predict the precipitation extreme values corresponding to each extreme precipitation recurrence period in the above extreme precipitation recurrence period sequence for the raster regions after the above division, to obtain a precipitation extreme value sequence. Among them, the distribution data can be substituted into the historical precipitation Pearson distribution curve to obtain a fitted precipitation Pearson distribution curve. Then, through the precipitation Pearson distribution curve, the precipitation extreme values corresponding to each extreme precipitation recurrence period in the extreme precipitation recurrence period sequence can be calculated to obtain a precipitation extreme value sequence.

[0064] Step 105, based on the rainfall-flood correlation characteristics, the extreme precipitation recurrence period sequence, and the corresponding precipitation extreme value sequence, perform model testing on the flood correlation model to generate a flood prediction verification value sequence.

[0065] In some embodiments, the above-mentioned execution entity may perform model testing on the above-mentioned flood correlation model based on the above-mentioned rainfall-flood correlation characteristics, the above-mentioned extreme precipitation recurrence period sequence, and the corresponding precipitation extreme value sequence to generate a flood prediction verification value sequence.

[0066] In some alternative implementation manners of some embodiments, the above-mentioned execution entity performing model testing on the above-mentioned flood correlation model based on the above-mentioned rainfall-flood correlation characteristics, the above-mentioned extreme precipitation recurrence period sequence, and the corresponding precipitation extreme value sequence to generate a flood prediction verification value sequence may include the following steps:

[0067] According to the above-mentioned rainfall-flood correlation characteristics, determine the flood prediction verification value sequence of each precipitation extreme value in the above-mentioned precipitation extreme value sequence within each extreme precipitation recurrence period in the above-mentioned extreme precipitation recurrence period sequence. Among them, each precipitation extreme value in the above-mentioned precipitation extreme value sequence may be substituted into the function of the above-mentioned rainfall-flood correlation characteristics to generate the flood prediction verification value sequence within each extreme precipitation recurrence period in the above-mentioned extreme precipitation recurrence period sequence.

[0068] Step 106: Perform result verification on the flood prediction verification value sequence to generate a verification result.

[0069] In some embodiments, the above-mentioned execution entity may perform result verification on the above-mentioned flood prediction verification value sequence to generate a verification result.

[0070] In practice, the comprehensive score of the spatial anomaly correlation coefficient ACC of the monthly precipitation forecast in the study area is used for performance evaluation. Taking 0.2 (domestic meteorological forecast level) as the threshold, if the ACC score is higher than 0.2, it indicates that the prediction model has a certain forecasting ability and can be used, that is, a verification result indicating that the verification has passed is generated. Otherwise, a verification result indicating that the verification has not passed is generated.

[0071] Step 107: In response to determining that the verification result meets the preset model verification condition, perform flood prediction on the target area through the flood correlation model to generate medium- and long-term flood warning information in the target area, and perform a warning operation according to the medium- and long-term flood warning information.

[0072] In some embodiments, the above-mentioned execution entity may, in response to determining that the above-mentioned verification result meets the preset model verification condition, perform flood prediction on the above-mentioned target area through the above-mentioned flood correlation model to generate medium- and long-term flood warning information in the target area, and perform a warning operation according to the above-mentioned medium- and long-term flood warning information. Among them, the model verification condition may be that the model verification result indicates that the verification has passed.

[0073] In some alternative implementations of some embodiments, in response to determining that the above verification result meets the preset model verification condition, the above execution entity performs flood prediction on the above target area through the above flood correlation model to generate medium- and long-term flood warning information within the target area, which may include the following steps:

[0074] First step, obtain the current precipitation prediction value sequence within the future time period corresponding to the current time point. Among them, the precipitation prediction value sequence within the future time period (for example, within 30 days) corresponding to the current time point can be obtained from the meteorological server.

[0075] Second step, input each current precipitation prediction value in the above current precipitation prediction value sequence into the above flood correlation model to perform flood prediction on the above target area to generate medium- and long-term flood warning information within the target area. Among them, the current precipitation prediction value can be input into the above flood correlation model to obtain medium- and long-term flood warning information within the target area. Here, the medium- and long-term flood warning information may include the flood risk probability values at various positions within the target area for a period of time.

[0076] In some alternative implementations of some embodiments, the above execution entity performs a warning operation according to the above medium- and long-term flood warning information, which may include the following steps:

[0077] First step, in response to determining that the above medium- and long-term flood warning information includes flood prediction values exceeding the warning threshold, determine the prediction time point corresponding to the above flood prediction values. Among them, the medium- and long-term flood warning information may include a prediction time point or time period. Therefore, the prediction time point or time period corresponding to the flood prediction values exceeding the warning threshold can be obtained.

[0078] Second step, according to the above prediction time point, at the time point before the preset time period interval, control the flood control equipment within the above target area to perform a flood control simulation operation to detect whether the flood control equipment is abnormal. The flood control simulation operation may be to issue a control instruction to control the start of each flood control equipment within the target area, and at the same time receive an indication of whether the start is completed. For example, the flood control equipment may include flood control gates. When receiving the information that the flood control gates are started normally and the closing of the gates is completed, it is determined that there is no abnormality.

[0079] Third step, in response to detecting normality and the time reaching the above prediction time point, control the above flood control equipment to open the flood control equipment.

[0080] Optionally, the above execution entity may further include the following steps:

[0081] In response to determining that the above verification result does not meet the above model verification conditions, a flood correlation model is established again for flood prediction processing. Among them, steps 103 - 106 can be executed again to establish a flood correlation model for flood prediction processing.

[0082] In practice, establishing the flood correlation model again can be used for model adjustment to make the ACC score higher than 0.2.

[0083] As an example, refer to Figure 2a 、 Figure 2b 、 Figure 2c for the medium - term flood risk forecast of a certain overseas linear project in the next 60 days. It shows the flood risk prediction results with September 8, 2024 as the starting date and a 10 - day period as each prediction period. As can be seen from the results, throughout the forecast cycle, the overall flood risk in the project area is relatively low (shown as yellow or blue in the figure), and no obvious flood risk signals are seen in the areas passed by the project.

[0084] As another example, refer to Figure 3 for the flood risk forecast of a certain overseas linear project in the past six months. Using the CMA - CPSv3 system, the rainfall trend for a six - month period from September 2024 to March 2025 is forecast. Since the time span is relatively long, single - day forecasts no longer have practical significance, so monthly forecast results are output. At the same time, in the medium - and long - term climate assessment, the prediction of relative trends has a more clear physical meaning than the prediction of the absolute value of rainfall. Therefore, the output result is the percentage deviation of the predicted monthly rainfall from the average value of the same period in previous years. When the result is a positive deviation, it means that the rainfall in that area is higher in that month and the flood risk increases; when the result is a negative deviation, it means that the rainfall in that area is lower in that month and the flood risk decreases. Figure 3 In [reference], a relatively red color indicates less rainfall compared to previous years, and a relatively blue color indicates more rainfall compared to previous years. The areas passed by the linear project are marked with red - bordered rectangles in the figure.

[0085] Here, based on the above data, the monthly flood risk trends of the north, middle, and south sections of the project line relative to the same period are sorted into the following table:

[0086] 2024.10 2024.11 2024.12 2025.01 2025.02 2025.03 North section On the high side On the high side On the high side On a par On a par On the high side Middle section On the high side On the high side On a par On the high side On a par On the low side South section On the high side On the low side On the low side On a par On the low side On a par

[0087] The above steps 103 - 107 and their related content are an inventive point of the embodiments of the present disclosure, which solve the fourth technical problem mentioned in the background art: "Since it is difficult to issue flood warnings in a timely manner, it is difficult to detect in advance whether flood control equipment is in good condition. As a result, it is difficult to repair faulty flood control equipment in a timely manner. Consequently, the flood control equipment is difficult to start in a timely manner and electrical resources are wasted." In order to achieve the effect of "timely detecting whether flood control equipment is faulty so as to start flood control equipment in a timely manner and reduce power resource consumption", first, a rainstorm flood risk assessment is realized based on precipitation forecasts. In the modeling of the correlation between precipitation and floods and the return period analysis, the sorted precipitation and disaster historical data of the assessment area are strictly used, making the precipitation return period and its correlation with floods unique, fitting the spatial distribution of flood risks in the assessment area to the greatest extent, and ensuring the accuracy of the assessment. Then, both meteorological data and flood disaster data are continuously updated and iterated, so that the temporal changes of flood risks in the assessment area can be fitted to the greatest extent. Against the background of global warming and frequent extreme precipitation events, the rainstorm flood risks are revealed in a timely manner.

[0088] In practice, because the relationship between precipitation and floods is non - linear, the level of precipitation is converted into the risk and probability of floods. It is equivalent to obtaining the flood risk probability based on the correlation of the precipitation level. However, the level of floods is mostly expressed as a once - in - XX - year occurrence. Therefore, it is necessary to obtain the "once - in - XX - year" level of the precipitation level at this moment among all historical precipitations in this area according to step 104. This relationship is also non - linear and follows the Pearson type III distribution. Thus, the level of precipitation can be converted into the risk and probability of floods through the rainfall - flood correlation characteristics. Thus, based on the determined flood risk, the flood control equipment can be inspected and repaired to avoid the waste of electrical resources and flood risks caused by repeatedly driving faulty flood control equipment.

[0089] In addition, compared with the existing methods for simulating medium- and long-term climate models released by various institutions, this method only assimilates and organizes the data within the evaluation area, greatly saving computing resources and storage resources. At the same time, the precipitation forecast and flood risk assessment provided by this method are formed based on the fitting of regional precipitation and flood historical records, and can best express the spatio-temporal distribution characteristics of medium- and long-term precipitation and flood risks in the evaluation area. Compared with the commonly used risk maps such as "Swiss Re" and "Munich Re", the data used in this method to establish the correlation between precipitation and floods is updated in real time, and the latest meteorological data is used in flood risk assessment. Therefore, the realized risk assessment results change dynamically and are continuously iteratively improved over time. Thus, it has stronger accuracy and timeliness. Compared with the flood risk forecasts and early warnings released by the existing meteorological and disaster departments, this method is based on the medium- and long-term model simulation method and has less dependence on the meteorological data collected by ground facilities. Therefore, the accuracy and effect are not affected by ground meteorological monitoring facilities, and normal assessment and forecasting can also be achieved in areas lacking facility coverage or where the facilities fail to operate properly. Finally, it can provide medium- and long-term flood risk times from 10 days to 1 year. Compared with the 48-hour / 24-hour early warnings released by the existing meteorological and disaster departments, more time is gained for the implementation of disaster prevention measures. Therefore, disaster prevention measures that require a long time to implement, such as facility construction, water level regulation, and emergency plan drills, can be realized, ensuring the safety of people and property in the evaluation area.

[0090] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: Through the medium- and long-term rainstorm flood warning method based on the regional scale in some embodiments of the present disclosure, flood warning operations can be initiated in a timely manner. Specifically, the reason for the difficulty in initiating flood warning operations in a timely manner is as follows: The flood risk area results of the commonly used risk maps in the industry mostly use meteorological, hydrological, and geological data collected once, and the update frequency is mostly once every few years. Usually, it has a relatively high confidence level to judge the rainstorm frequency and rainstorm events in a certain area through this method, but it is very difficult to reflect the occurrence of extreme weather through this method. For the natural fluctuating changes in precipitation (such as: precipitation shows a certain upward or downward trend within a period of time, and it is exactly in the upward stage of precipitation during the evaluation period); and the local precipitation characteristics affected by greenhouse gas emissions and changes in land use patterns brought about by human activities lead to frequent extreme precipitation events, which are difficult to effectively evaluate. As a result, it is difficult to initiate flood warning operations in a timely manner. Based on this, the medium- and long-term rainstorm flood warning method based on the regional scale in some embodiments of the present disclosure, first, obtains the historical meteorological data set and historical flood data set within a preset time period in the target area from the database. Then, in response to determining that the above-mentioned historical meteorological data set does not meet the preset reference conditions, data back-calculation is performed on the above-mentioned historical meteorological data set to generate a complemented meteorological data set. Here, data back-calculation can be used to supplement missing data. After that, based on the above-mentioned complemented meteorological data set and the above-mentioned historical flood data set, a flood correlation model is established, and rainfall-flood correlation characteristics are generated through the above-mentioned flood correlation model. Among them, the above-mentioned rainfall-flood correlation characteristics represent the correlation relationship between the rainfall degree and the flood degree in the above-mentioned target area. Here, considering that the relationship between precipitation and flood disasters is non-linear, if it is necessary to correlate flood disaster forecasts based on precipitation forecasts, a flood correlation model needs to be established. Thus, it can be used to determine the correlation relationship between the rainfall degree and the flood degree in the target area. Then, data extraction is performed on the above-mentioned historical meteorological data set to obtain an extreme precipitation data set, and precipitation recurrence characteristics are extracted from each extreme precipitation data in the above-mentioned extreme precipitation data set to generate an extreme precipitation recurrence period sequence and the corresponding precipitation extreme value sequence. Here, through data extraction, it can be used to collect extreme precipitation data. At the same time, the extreme precipitation recurrence period can also be determined according to the collected extreme precipitation data. Thus, it is convenient to determine the precipitation level and flood disaster level. Next, based on the above-mentioned rainfall-flood correlation characteristics, the above-mentioned extreme precipitation recurrence period sequence and the corresponding precipitation extreme value sequence, the above-mentioned flood correlation model is tested to generate a flood prediction verification value sequence. Here, through model testing, it can be used to detect whether the established model is reliable. In addition, the results of the above-mentioned flood prediction verification value sequence are verified to generate a verification result. Here, through result verification, it can be used to determine whether the model can be used for flood prediction.Finally, in response to determining that the above verification result meets the preset model verification condition, flood prediction is performed on the above target area through the above flood correlation model to generate medium- and long-term flood warning information within the target area, and warning operations are executed according to the above medium- and long-term flood warning information. Thus, flood warning operations can be initiated in a timely manner.

[0091] For further reference Figure 4 , as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a medium- and long-term rainstorm flood warning device based on regional scale, and these device embodiments correspond to Figure 1 the method embodiments shown, and the device can be specifically applied to various electronic devices.

[0092] As Figure 4 shown, a medium- and long-term rainstorm flood warning device 400 based on regional scale in some embodiments includes: an acquisition unit 401, a data back-calculation unit 402, a establishment and feature association unit 403, a feature extraction unit 404, a model testing unit 405, a result verification unit 406, and a flood prediction unit 407. Among them, the acquisition unit 401 is configured to acquire a historical meteorological data set and a historical flood data set within a preset time period in the target area from a database; the data back-calculation unit 402 is configured to perform data back-calculation on the above historical meteorological data set in response to determining that the historical meteorological data set does not meet the preset reference condition to generate a complemented meteorological data set; the establishment and feature association unit 403 is configured to establish a flood correlation model based on the above complemented meteorological data set and the above historical flood data set, and generate rainfall-flood association features through the above flood correlation model, where the above rainfall-flood association features characterize the association relationship between the rainfall degree and the flood degree within the target area; the feature extraction unit 404 is configured to perform data extraction on the above historical meteorological data set to obtain an extreme precipitation data set, and perform precipitation recurrence feature extraction on each extreme precipitation data in the above extreme precipitation data set to generate an extreme precipitation recurrence period sequence and a corresponding precipitation extreme value sequence; the model testing unit 405 is configured to perform model testing on the above flood correlation model based on the above rainfall-flood association features, the above extreme precipitation recurrence period sequence and the corresponding precipitation extreme value sequence to generate a flood prediction verification value sequence; the result verification unit 406 is configured to perform result verification on the above flood prediction verification value sequence to generate a verification result; the flood prediction unit 407 is configured to perform flood prediction on the above target area through the above flood correlation model in response to determining that the above verification result meets the preset model verification condition to generate medium- and long-term flood warning information within the target area, and execute warning operations according to the above medium- and long-term flood warning information.

[0093] It can be understood that the various units described in the apparatus 400 correspond to the respective steps in the method described with reference to Figure 1 Therefore, the operations, features, and beneficial effects described above for the method also apply to the apparatus 400 and the units included therein, and will not be elaborated herein.

[0094] Reference is now made to Figure 5 , which shows a schematic structural diagram of an electronic device (e.g., a computing device) 500 suitable for implementing some embodiments of the present disclosure. Figure 5 The electronic device shown is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present disclosure.

[0095] As Figure 5 shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which may perform various appropriate actions and processes according to a program stored in the read-only memory 502 or a program loaded from the storage device 508 into the random access memory 503. In the random access memory 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the read-only memory 502, and the random access memory 503 are connected to each other via a bus 504. The input / output interface 505 is also connected to the bus 504.

[0096] Generally, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or wirelesly to exchange data. Although Figure 5 shows an electronic device 500 having various devices, it should be understood that it is not required to implement or include all the shown devices. Instead, more or fewer devices may be implemented or included. Figure 5 Each block shown in

[0097] In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes program code for performing the methods shown in the flowcharts. In such some embodiments, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the read-only memory 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the methods of some embodiments of the present disclosure are performed.

[0098] It should be noted that the computer-readable medium described in some embodiments of the present disclosure can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable signal medium can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0099] In some embodiments, the client and the server can communicate using any currently known or future-developed network protocol such as HTTP (Hyper Text Transfer Protocol), and can be interconnected with digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include local area networks ("LANs"), wide area networks ("WANs"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0100] The above computer-readable medium can be included in the above electronic device; or can exist separately without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by the electronic device, the electronic device is caused to: obtain a historical meteorological data set and a historical flood data set within a preset time period in a target area from a database; in response to determining that the above historical meteorological data set does not meet a preset reference condition, perform data back-calculation on the above historical meteorological data set to generate a complemented meteorological data set; based on the above complemented meteorological data set and the above historical flood data set, establish a flood correlation model, and generate rainfall-flood correlation features through the above flood correlation model, where the above rainfall-flood correlation features characterize the correlation relationship between the rainfall degree and the flood degree in the above target area; perform data extraction on the above historical meteorological data set to obtain an extreme precipitation data set, and perform precipitation recurrence feature extraction on each extreme precipitation data in the above extreme precipitation data set to generate an extreme precipitation recurrence period sequence and a corresponding precipitation extreme value sequence; based on the above rainfall-flood correlation features, extreme precipitation recurrence period sequence and corresponding precipitation extreme value sequence, perform model testing on the flood correlation model to generate a flood prediction verification value sequence; perform result verification on the above flood prediction verification value sequence to generate a verification result; in response to determining that the above verification result meets a preset model verification condition, perform flood prediction on the target area through the above flood correlation model to generate medium- and long-term flood warning information within the target area, and perform a warning operation according to the medium- and long-term flood warning information.

[0101] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0102] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0103] The units described in some embodiments of the present disclosure may be implemented in software or in hardware. The described units may also be provided in a processor. For example, a processor may be described as including an acquisition unit, a data back-calculation unit, an establishment and feature association unit, a feature extraction unit, a model testing unit, a result verification unit, and a flood prediction unit. Among them, the names of these units do not constitute a limitation on the unit itself in some cases. For example, the acquisition unit may also be described as "the unit for acquiring historical meteorological data sets and historical flood data sets within a preset time period in a target area from a database".

[0104] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include: Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), Systems on a Chip (SOCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0105] The above description is only some preferred embodiments of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, technical solutions formed by mutually replacing the above features with technical features having similar functions (but not limited to) disclosed in the embodiments of the present disclosure.

Claims

1. A medium- and long-term rainstorm and flood warning method based on regional scale, including: Acquire historical meteorological data sets and historical flood data sets for a preset time period in the target area from the database; In response to determining that the historical meteorological data set does not meet a preset reference condition, performing data back calculation on the historical meteorological data set to generate a completed meteorological data set; Based on the completed meteorological data set and the historical flood data set, a flood correlation model is established, and a rainfall-flood correlation feature is generated through the flood correlation model, wherein the rainfall-flood correlation feature characterizes the correlation between the rainfall degree and the flood degree in the target area; Extracting data from the historical meteorological data set to obtain an extreme precipitation data set, and extracting precipitation recurrence features from each extreme precipitation data in the extreme precipitation data set to generate an extreme precipitation recurrence period sequence and a corresponding precipitation extreme value sequence; Based on the rainfall-flood correlation characteristics, the extreme precipitation return period sequence and the corresponding precipitation extreme value sequence, the flood correlation model is tested to generate a flood prediction verification value sequence; Performing result verification on the flood prediction verification value sequence to generate a verification result; In response to determining that the verification result meets the preset model verification condition, flood prediction is performed on the target area through the flood correlation model to generate medium- and long-term flood warning information in the target area, and a warning operation is performed according to the medium- and long-term flood warning information.

2. The method according to claim 1, wherein: The performing of the warning operation according to the medium- and long-term flood warning information includes: In response to determining that the medium- and long-term flood warning information includes a flood prediction value that exceeds a warning threshold, determining a prediction time point corresponding to the flood prediction value; According to the predicted time point, at a time point before the preset time interval, controlling the flood control equipment in the target area to perform a flood control simulation operation to detect whether the flood control equipment is abnormal; In response to the detection being normal and the time reaching the predicted time point, each flood prevention device is controlled to be turned on.

3. The method according to claim 1, wherein: The method further comprises: In response to determining that the verification result does not satisfy the model verification condition, a flood correlation model is established again for use in flood prediction processing.

4. The method according to claim 1, wherein: The step of obtaining a historical meteorological data set and a historical flood data set within a preset time period in the target area from the database includes: Acquiring a historical meteorological data set within the target area from the database according to a preset time period; determining initial historical flood data within the target area in the database; Data within the preset time period is filtered out from the initial historical flood data to obtain a historical flood data set, wherein each historical flood data in the historical flood data set includes at least one of the following: flood area identification, flood revelation time point, flood end time point, flood range data and flood cause information.

5. The method according to claim 1, wherein: In response to determining that the historical meteorological data set does not meet a preset reference condition, back-calculating the historical meteorological data set to generate a completed meteorological data set includes: In response to determining that the historical meteorological data set does not meet a preset reference condition, performing data back-calculation on the historical meteorological data set to generate a back-calculated data set; The back-calculated data set is fused with the historical meteorological data set to obtain a completed meteorological data set.

6. The method according to claim 1, wherein: The performing result verification on the flood prediction verification value sequence to generate a verification result includes: Determining a precipitation correlation coefficient corresponding to the flood prediction verification value sequence; In response to determining that the precipitation correlation coefficient is greater than a preset coefficient threshold, generating a verification result indicating that the verification has passed; In response to determining that the precipitation correlation coefficient is less than or equal to a preset coefficient threshold, a verification result indicating that the verification has failed is generated.

7. The method according to claim 1, wherein: In response to determining that the verification result satisfies a preset model verification condition, flood prediction is performed on the target area through the flood correlation model to generate medium- and long-term flood warning information in the target area, including: Get the current precipitation forecast value sequence in the future time period corresponding to the current time point; Each current precipitation prediction value in the current precipitation prediction value sequence is input into the flood correlation model to perform flood prediction on the target area, so as to generate medium- and long-term flood warning information in the target area.

8. A medium- and long-term rainstorm and flood warning device based on regional scale, comprising: An acquisition unit is configured to acquire a historical meteorological data set and a historical flood data set in a preset time period in a target area from a database; a data back-calculation unit, configured to, in response to determining that the historical meteorological data set does not meet a preset reference condition, perform data back-calculation on the historical meteorological data set to generate a completed meteorological data set; An establishment and feature association unit is configured to establish a flood correlation model based on the completed meteorological data set and the historical flood data set, and generate a rainfall-flood correlation feature through the flood correlation model, wherein the rainfall-flood correlation feature represents the correlation between the rainfall degree and the flood degree in the target area; a feature extraction unit configured to perform data extraction on the historical meteorological data set to obtain an extreme precipitation data set, and perform precipitation recurrence feature extraction on each extreme precipitation data in the extreme precipitation data set to generate an extreme precipitation recurrence period sequence and a corresponding precipitation extreme value sequence; A model testing unit is configured to perform a model test on the flood correlation model based on the rainfall-flood correlation characteristics, the extreme precipitation return period sequence and the corresponding precipitation extreme value sequence to generate a flood prediction verification value sequence; A result verification unit is configured to perform result verification on the flood prediction verification value sequence to generate a verification result; The flood prediction unit is configured to, in response to determining that the verification result meets the preset model verification condition, perform flood prediction on the target area through the flood correlation model to generate medium- and long-term flood warning information in the target area, and perform warning operations based on the medium- and long-term flood warning information.

9. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images