Flood inundation event prediction method and device

Abstract

The present application discloses a method and device for predicting flood inundation events. An emergence constraint model is constructed based on the change trend of the key physical factors of the spatial average of the watershed in the historical period under the global climate model and the change trend of the scale inundation magnitude of the watershed in the future period, and based on the emergence constraint model, the change trend of the scale inundation magnitude of the watershed in the future period after correction is determined by the key physical factors of the spatial average of the watershed corresponding to the ERA5-Land dataset, so as to characterize the evolution of flood inundation through the scale inundation magnitude of the watershed in the future period, thereby improving the prediction accuracy of the evolution.

Description

Technical Field

[0001] The present application relates to the technical field of climate data analysis, and in particular to a method and device for predicting flood inundation events. Background Art

[0002] Precipitation is a key factor in the hydrological cycle. Over the past few decades, the intensity and frequency of extreme precipitation in most parts of the world have increased significantly, and the flood disasters caused by them have caused economic losses of more than 30 billion US dollars each year. The water vapor content in the atmospheric boundary layer is the material basis for the formation of precipitation. According to the Clausius-Clapeyron thermodynamic equation, the saturated water vapor pressure increases nonlinearly with the increase in temperature, which is about 6.8% / oC, generally referred to as the CC scale. Foreign scholars further considered the physical connection between water vapor content and precipitation intensity, evaluated the intensity of global precipitation response to climate warming, and found that extreme precipitation in most regions presents a sub-CC scale or negative response coefficient. At the same time, ground observations and satellite inversion data in most parts of the world confirm that extreme precipitation generally presents a Hook climate response structure, that is, a "parabolic" trajectory that first rises and then falls with rising temperatures.

[0003] At present, the research on future climate change mainly relies on global climate models. Global climate models allow the simulation of the physical processes and interactions of the changes in the various components of the Earth's climate system (including the atmosphere, ocean, land surface processes, cryosphere and biosphere). Due to the complexity of the global climate system, each climate model makes different degrees of assumptions or approximations when simulating the changes in these components.

[0004] In related technologies, domestic and foreign scholars have combined the global climate model ensemble under the Sixth International Coupled Model Intercomparison Project with the basin hydrological model and machine learning model to study the evolution of future hydrological disasters. It is not difficult to find that these related technologies are difficult to accurately predict the evolution trend of drought-flood abrupt transition events. Summary of the invention

[0005] In view of this, the flood inundation event prediction method and device of the present application can accurately predict the evolution trend of flood inundation events.

[0006] In a first aspect, the present application provides a flood inundation event prediction method, comprising:

[0007] Determine the flooding magnitude at the basin scale within the forecast basin based on the flood warning water depth and the flood season river inundation depth under the global climate model;

[0008] Based on machine learning, the meteorological and hydrological data output by the global climate model are used to analyze the key physical factors of the basin spatial average in the historical period under the global climate model. The key physical factors are important factors that affect the maximum flooding depth.

[0009] According to the change trend of the key physical factors of the basin spatial average in the historical period under the global climate model and the change trend of the flooding magnitude of the basin in the future period, an emergence constraint model is constructed;

[0010] Based on the emergence constraint model, the trend of the flooding magnitude at the basin scale in the future period after correction is determined according to the key physical factors of the basin spatial average in the historical period corresponding to the ERA5-Land dataset;

[0011] The evolution of flood inundation events is predicted by taking a weighted average of the changing trends of the corrected basin-scale inundation magnitudes in the future period corresponding to each global climate model, and predicting the evolution of flood inundation events.

[0012] Optionally, basin-scale flooding magnitude within the predicted basin is determined based on the flood warning water depth and the flood season river channel flooding depth under the global climate model, and is performed by the following formula:

[0013] ;

[0014] In the above formula, Rish H is the basin-scale inundation magnitude of the flood-inundation forecast basin in a certain year; is the flooding depth of the g-th grid point on the d-th day of this year, is the flood warning water depth of the g-th grid point.

[0015] Optionally, the determination of the flood depth of the river channel during the flood season under the global climate model includes:

[0016] The simulated runoff depth series for each grid point in the predicted basin under different global climate models were obtained respectively;

[0017] Obtain the flood season ENSO index under different global climate models;

[0018] Based on the global hydrodynamic model CamaFlood, the flood depth of the river channel during the flood season under the global climate model is determined according to the simulated runoff depth series and the flood season ENSO index.

[0019] Optionally, obtaining a simulated runoff depth series for each grid point in the predicted watershed includes:

[0020] Based on a predefined artificial intelligence model for simulating runoff depth, a simulated runoff depth is obtained;

[0021] Based on the quantile mapping model, the corrected runoff depth is obtained;

[0022] According to the simulated runoff depth and the corrected runoff depth, a simulated runoff depth series for each grid point in the predicted watershed is determined.

[0023] Optionally, the corrected runoff depth is obtained based on the quantile mapping model, which is performed by the following formula,

[0024] ;

[0025] ;

[0026] in, T Represents air temperature, specific humidity, relative humidity, shortwave radiation and longwave radiation, P Represents precipitation, snowfall, and runoff depth, adj represents the corrected series, obs represents the observed data, ref and fut Represent the historical reference period and the future forecast period respectively, d Represents daily data, Q Represents each quantile.

[0027] Optionally, the relative humidity is determined by the following formula,

[0028] ;

[0029] In the above formula, T dew is the dew point temperature, T 2m The temperature at 2m, e sat (.) represents the Clausius-Clapeyron thermodynamic equation;

[0030] The specific humidity is determined by the following formula,

[0031] ;

[0032] In the above formula, p stands for ERA5 Earth pressure, T dew is the dew point temperature, e sat (.) represents the Clausius-Clapeyron thermodynamic equation.

[0033] Optionally, the emergence constraint model is represented by the following formula:

[0034] ;

[0035] In the above formula, Indicates the changing trend of the flooding magnitude at the basin scale in the future period, KKtrend express KK The changing trend of the factors, a and b represent the model parameters.

[0036] In a second aspect, the present application provides a flood inundation event prediction device, comprising:

[0037] The first determination module is used to determine the flood magnitude of the watershed scale in the predicted watershed according to the flood warning water depth and the flood depth of the river channel in the flood season under the global climate model;

[0038] An analysis module, for analyzing the meteorological and hydrological data output by the global climate model based on machine learning to obtain the key physical factors of the basin spatial average of the historical period under the global climate model, wherein the key physical factors are important factors affecting the maximum flooding depth;

[0039] A construction module is used to construct an emergence constraint model according to the change trend of the key physical factors of the basin spatial average in the historical period under the global climate model and the change trend of the flooding magnitude of the basin at the scale in the future period;

[0040] The second determination module is used to determine the change trend of the flooding magnitude at the basin scale in the future period after correction based on the emergence constraint model and the key physical factors of the basin spatial average of the historical period corresponding to the ERA5-Land data set;

[0041] The prediction module is used to predict the evolution of flood inundation events by weighted averaging the changing trends of the corrected basin-scale inundation magnitudes in the future period corresponding to each global climate model.

[0042] In a third aspect, the present application provides a computer-readable storage medium, comprising a program, which, when executed on a computer, enables the computer to execute the method as described above.

[0043] In a fourth aspect, the present application provides an execution device, comprising a processor and a memory, wherein the processor is coupled to the memory;

[0044] The memory is used to store programs;

[0045] The processor is used to execute the program in the memory, so that the execution device executes the above method.

[0046] In the method disclosed in the present application, an emergence constraint model is constructed according to the changing trends of the key physical factors of the spatial average of the watershed in the historical period under the global climate model and the changing trends of the scale inundation magnitude of the watershed in the future period, and based on the emergence constraint model, the changing trends of the scale inundation magnitude of the watershed in the future period after correction are determined by the key physical factors of the spatial average of the watershed corresponding to the ERA5-Land dataset, so as to characterize the evolution of flood inundation by the scale inundation magnitude of the watershed in the future period, thereby improving the prediction accuracy of the evolution status. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The technical solution and other beneficial effects of the present application will be made apparent by describing in detail the specific implementation methods of the present application in conjunction with the accompanying drawings.

[0048] Figure 1 An operational flow chart of a flood inundation event prediction method provided by an exemplary embodiment is shown.

[0049] Figure 2 A block diagram of a flood inundation event prediction device provided by an exemplary embodiment is shown;

[0050] Figure 3 A block diagram of the execution device provided by an exemplary embodiment is shown. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the specific embodiments disclosed below.

[0052] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. The naming or numbering of steps in this application does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The process steps that have been named or numbered can change the execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved. The division of units in this application is a logical division. There may be other division methods when it is implemented in actual applications. For example, multiple units can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between units can be electrical or other similar forms, which are not limited in this application. In addition, the units or sub-units described as separate components may or may not be physically separated, may or may not be physical units, or may be distributed in multiple circuit units, and some or all of the units may be selected according to actual needs to achieve the purpose of the present application.

[0053] Please refer to Figure 1 , Figure 1 A flow chart of a flood inundation event prediction method provided by an exemplary embodiment is shown. The method is implemented through steps 102-110.

[0054] In step 102, the flooding magnitude at the watershed scale within the predicted watershed is determined based on the flood warning water depth and the flooding depth of the river channel during the flood season under the global climate model.

[0055] The term “flood season” as used in this article is defined by first extracting the maximum daily flow of each month and then identifying the five consecutive months with the largest daily maximum flow, which are defined as the flood season for the flood inundation prediction basin.

[0056] As an example, the basin-scale flooding magnitude in the predicted basin is determined based on the flood warning water depth and the flood season river inundation depth under the global climate model, which is implemented by the following formula:

[0057] ;

[0058] In the above formula, Rish H is the basin-scale inundation magnitude of the flood-inundation forecast basin in a certain year; For the g The flooding depth of the grid point on day d of this year is, For the g The flood warning water depth at each grid point.

[0059] It is understandable that the moment when the flooded water depth of each grid point river exceeds the corresponding flood warning water depth (i.e., flood control standard) is defined as the risk area. The flood warning water depth can be obtained based on the flood control standard data. The flood control standard data includes but is not limited to the daily runoff data of the hydrological station controlling the outlet section of the flood inundation prediction basin, topography, river network, basin electronic boundary file, geographic information system and flood control standards.

[0060] It should be added that in deriving Rish After H, the relative change of the flood magnitude at the basin scale can be further determined, which can characterize the change in the intensity of flood inundation. The calculation process of the relative change of the flood magnitude at the basin scale is expressed by the following formula:

[0061] ;

[0062] Where: is the relative change in the magnitude of inundation at the basin scale under the mth global climate model; is the magnitude of inundation at the basin scale in the future period under the mth global climate model; is the flooding magnitude at the basin scale in the historical period under the mth global climate model.

[0063] As an example, the determination of the flood depth of the river channel during the flood season under the global climate model includes:

[0064] The simulated runoff depth series for each grid point in the predicted basin under different global climate models were obtained respectively;

[0065] Obtain the flood season ENSO index under different global climate models;

[0066] Based on the global hydrodynamic model CamaFlood, the flood depth of the river channel during the flood season under the global climate model is determined according to the simulated runoff depth series and the flood season ENSO index.

[0067] Here, as a reference implementation method, the simulated runoff depth series of each grid point in the predicted watershed is obtained, including:

[0068] Based on a predefined artificial intelligence model for simulating runoff depth, a simulated runoff depth is obtained;

[0069] Based on the quantile mapping model, the corrected runoff depth is obtained;

[0070] According to the simulated runoff depth and the corrected runoff depth, a simulated runoff depth series for each grid point in the predicted watershed is determined.

[0071] Here, the training input data of the artificial intelligence model is the ERA5 meteorological and hydrological dataset of the grid point. Here, ERA5 is the fifth-generation atmospheric reanalysis dataset from the European Centre for Medium-Range Weather Forecasts. The ERA5 meteorological and hydrological dataset covers hourly meteorological and hydrological observation data, including 2m temperature, air pressure, dew point temperature, snowfall, precipitation, runoff depth, shortwave radiation and longwave radiation, and obtains the daily average 2m temperature, daily average dew point temperature, daily snowfall, daily precipitation, daily average air pressure, daily runoff depth, daily shortwave radiation and daily longwave radiation through time scale conversion.

[0072] As a calculation process of a more extensive artificial intelligence model, the regional average meteorological variables can be calculated first and then used to calibrate the artificial intelligence model. The present invention uses the meteorological and hydrological variables of all grid points in the study area as input, which is more in line with the spatiotemporal correlation physical mechanism of daily runoff depth.

[0073] As another preferred calculation process of the artificial intelligence model, multiple artificial intelligence models can be used, and the types of these artificial intelligence models include but are not limited to convolutional neural networks, long short-term memory models, support vector machines, random forests and artificial neural networks. These artificial intelligence models are trained using methods such as gradient descent to obtain calibrated artificial intelligence models. The calibration method of the artificial intelligence model is a conventional technology in the art.

[0074] In the implementation of multiple artificial intelligence models, the weight parameter can be set to 0.25 to obtain multi-model weighted results.

[0075] As an example, the corrected runoff depth is obtained based on the quantile mapping model, which is performed by the following formula:

[0076] ;

[0077] ;

[0078] in, T Represents air temperature, specific humidity, relative humidity, shortwave radiation and longwave radiation, P Represents precipitation, snowfall, and runoff depth, adj represents the corrected series, obs represents the observed data, ref and fut Represent the historical reference period and the future forecast period respectively, d Represents daily data,Q Represents each quantile.

[0079] It should be noted that the construction process of the quantile mapping model is to first calculate the difference between the output variables of the global climate models (GCMs) in the historical period (1940-2014) and the observed meteorological variables at each quantile (0.01-0.99), and then remove the difference from the quantiles of the GCMs output in the future period (2030-2100).

[0080] In the calculation formula for the corrected runoff depth, the relative humidity involved is determined by the following formula,

[0081] ;

[0082] In the above formula, T dew is the dew point temperature, T 2m The temperature at 2m, e sat (T.) represents the Clausius-Clapeyron thermodynamic equation;

[0083] In the calculation formula for the corrected runoff depth, the specific humidity involved is determined by the following formula,

[0084] ;

[0085] In the above formula, p represents the ERA5 near-ground pressure, T dew is the dew point temperature, e sat (T.) represents the Clausius-Clapeyron thermodynamic equation.

[0086] Here, the Clausius-Clapeyron thermodynamic equation is defined as follows:

[0087] ;

[0088] in, is the first integration constant, which is taken as 273.16 K; is the second integral constant, which is 611 Pa; is the latent heat of vaporization constant, taken as 2.5×10 6 J·kg -1 ; is the water vapor gas constant, which is 461 J·kg -1 ·K -1 ; T is the air temperature, which is the input variable of the Clausius-Clapeyron thermodynamic equation.

[0089] An exemplary implementation of the above “determining the simulated runoff depth series for each grid point in the predicted watershed based on the simulated runoff depth and the corrected runoff depth” is to use the arithmetic mean of the simulated runoff depth and the corrected runoff depth as the simulated runoff depth series for each grid point.

[0090] The ENSO index mentioned in the previous article "Obtaining the ENSO index for flood season under different global climate models" refers to the El Nino Southern Oscillation. The ENSO index can cover the time series of four ENSO (El Nino Southern Oscillation) indices from 1950 to the present, including the NINO 1+2 area sea surface temperature anomaly index, the NINO3 area sea surface temperature anomaly index, the NINO 3.4 area sea surface temperature anomaly index, and the NINO 4 area sea surface temperature anomaly index.

[0091] Regarding the method of obtaining the flood season ENSO index, it can be deduced based on the global sea surface temperature data of the historical period (1940-2014) and the future period (2030-2100) simulated by 28 global climate models under the SSP3-70 shared socioeconomic pathway. Since this derivation method is a well-known technology, it will not be described in detail here.

[0092] In step 104, based on machine learning, the meteorological and hydrological data output by the global climate model are analyzed to obtain the key physical factors of the historical basin spatial average under the global climate model, wherein the key physical factors are important factors affecting the maximum flooding depth.

[0093] Specifically, the machine learning here can be a random forest, and of course it can also be other types of machine learning models.

[0094] It is understood that the meteorological and hydrological data here include but are not limited to the maximum daily runoff depth, maximum daily precipitation, maximum daily average temperature, average relative humidity, average specific humidity, average shortwave radiation intensity and average longwave radiation during the flood season of each grid point of each global climate model in the historical period, and the maximum flooding depth of each grid point during the flood season simulated by each global climate model. In the random forest model, the maximum flooding depth during the flood season is a simulation variable.

[0095] The random forest model can rank the importance of each input variable to the simulation variable. Therefore, based on the above random forest model, the factor with the greatest impact on the maximum flooding depth is selected as the key physical factor, which is recorded as KK factor.

[0096] It should be noted that the key physical factors of the watershed spatial average can be obtained using the Thiessen polygon method.

[0097] In step 106, an emergence constraint model is constructed based on the changing trends of the spatially averaged key physical factors of the watershed in the historical period under the global climate model and the changing trends of the flooding magnitude of the watershed at the scale in the future period.

[0098] Here, the emergence constraint model is expressed by the following formula:

[0099] ;

[0100] In the above formula, Indicates the changing trend of the flooding magnitude at the basin scale in the future period, KKtrend The spatial average of the basin under the global climate model in the historical period KK The changing trend of the factors, a and b represent the model parameters.

[0101] It should be added that the least square method is used to solve the parameters a and b of the emergence constraint model.

[0102] In step 108, based on the emergence constraint model, the changing trend of the flooding magnitude at the basin scale in the future period after correction is determined according to the key physical factors of the basin spatial average in the historical period corresponding to the ERA5-Land dataset.

[0103] The change trend of the flooding magnitude at the basin scale in the future period after correction is determined by the following formula:

[0104] ;

[0105] In the above formula, It indicates the trend of RishH index after correction in the future period. It shows the changing trends of key physical factors in the basin spatial average during the flood season in the historical period of the ERA5 dataset.

[0106] In step 110, the evolution of flood inundation events is predicted by weighted averaging the change trends of the normalized water surplus and deficit index in the future period after correction corresponding to each global climate model.

[0107] Here, the weight coefficient of weighted average can be selected according to actual needs.

[0108] Please refer to Figure 2 , which shows a block diagram of the flood inundation event prediction device provided by the present application. The device 200 includes:

[0109] The first determination module 202 is used to determine the flooding magnitude of the watershed scale in the predicted watershed according to the flood warning water depth and the flooding depth of the river channel in the flood season under the global climate model;

[0110] An analysis module 204 is used to analyze the meteorological and hydrological data output by the global climate model based on machine learning to obtain the key physical factors of the basin spatial average in the historical period under the global climate model, wherein the key physical factors are important factors affecting the maximum flooding depth;

[0111] A construction module 206 is used to construct an emergence constraint model according to the change trend of the key physical factors of the basin spatial average in the historical period under the global climate model and the change trend of the flood magnitude of the basin in the future period;

[0112] The second determination module 208 is used to determine the change trend of the flooding magnitude at the watershed scale in the future period after correction based on the emergence constraint model and the key physical factors of the watershed space average corresponding to the ERA5-Land dataset;

[0113] The prediction module 210 is used to predict the evolution of flood inundation events by weighted averaging the change trends of the corrected basin-scale inundation magnitudes in the future period corresponding to each global climate model.

[0114] Since the above methods have been discussed in detail, the specific implementation of the above modules will not be repeated here.

[0115] Next, an execution device provided by an embodiment of the present application is introduced. Figure 3 , Figure 3 This is a schematic diagram of a structure of an execution device provided in an embodiment of the present application. The execution device 300 can be specifically manifested as an autonomous driving vehicle, a mobile phone, a tablet, a laptop computer, a desktop computer, a monitoring data processing device, etc., which is not limited here. Figure 1 The functions of the execution device in the corresponding embodiment. Specifically, the execution device 300 includes: a receiver 301, a transmitter 302, a processor 303 and a memory 304 (wherein the number of the processor 303 in the execution device 300 can be one or more, Figure 3 In the example of FIG. 3 , the processor 303 may include an application processor 3031 and a communication processor 3032. In some embodiments of the present application, the receiver 301, the transmitter 302, the processor 303 and the memory 304 may be connected via a bus or other means.

[0116] The memory 304 may include a read-only memory and a random access memory, and provides instructions and data to the processor 303. A portion of the memory 304 may also include a non-volatile random access memory (NVRAM). The memory 304 stores processor and operation instructions, executable modules or data structures, or subsets thereof, or extended sets thereof, wherein the operation instructions may include various operation instructions for implementing various operations.

[0117] The processor 303 controls the operation of the execution device. In a specific application, the various components of the execution device are coupled together through a bus system, wherein the bus system includes not only a data bus but also a power bus, a control bus, and a status signal bus, etc. However, for the sake of clarity, various buses are referred to as bus systems in the figure.

[0118] The method disclosed in the above embodiment of the present application can be applied to the processor 303, or implemented by the processor 303. The processor 303 can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 303. The above processor 303 can be a general-purpose processor, a digital signal processor (digital signal processing, DSP), a microprocessor or a microcontroller, and can further include an application specific integrated circuit (application specific integrated circuit, ASIC), a field programmable gate array (field-programmable gate array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The processor 303 can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be combined and executed. The software module may be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 304, and the processor 303 reads the information in the memory 304 and completes the steps of the above method in combination with its hardware.

[0119] The receiver 301 can be used to receive inputted digital or symbol information, and generate signal input related to the relevant settings and function control of the execution device. The transmitter 302 can be used to output the digital or symbol information through the first interface; the transmitter 302 can also be used to send instructions to the disk group through the first interface to modify the data in the disk group; the transmitter 302 can also include a display device such as a display screen.

[0120] In the embodiment of the present application, the processor 303 is used to execute Figure 1 The specific manner in which the application processor 3031 in the processor 303 performs the above steps is the same as that in the present application. Figure 1 The corresponding method embodiments are based on the same concept, and the technical effects they bring are the same as those in this application. Figure 1 The corresponding method embodiments are the same. For specific contents, please refer to the description in the method embodiments shown above in this application, which will not be repeated here.

[0121] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed in the present application should be covered within the protection scope of the present application.

Claims

1. A flood inundation event prediction method, characterized in that: include: Determine the flooding magnitude at the basin scale within the forecast basin based on the flood warning water depth and the flood season river inundation depth under the global climate model; Based on machine learning, the meteorological and hydrological data output by the global climate model are used to analyze the key physical factors of the basin spatial average in the historical period under the global climate model. The key physical factors are important factors that affect the maximum flooding depth. According to the change trend of the key physical factors of the basin spatial average in the historical period and the change trend of the flooding magnitude at the basin scale in the future period under the global climate model, an emergence constraint model is constructed; Based on the emergence constraint model, the trend of the flooding magnitude at the basin scale in the future period after correction is determined according to the key physical factors of the basin spatial average in the historical period corresponding to the ERA5-Land dataset; The evolution of flood inundation events is predicted by taking a weighted average of the changing trends of the corrected basin-scale inundation magnitudes in the future period corresponding to each global climate model, and predicting the evolution of flood inundation events.

2. The method according to claim 1, characterized in that The flooding magnitude of the watershed scale in the predicted basin is determined based on the flood warning water depth and the flood season river inundation depth under the global climate model, and is implemented by the following formula: ； In the above formula, Rish H is the basin-scale inundation magnitude of the flood-inundation forecast basin in a certain year; is the flooding depth of the g-th grid point on the d-th day of this year, is the flood warning water depth of the g-th grid point.

3. The method according to claim 2, characterized in that The determination of flood depth of river channel during flood season under the global climate model includes: The simulated runoff depth series for each grid point in the predicted basin under different global climate models were obtained respectively; Obtain the flood season ENSO index under different global climate models; Based on the global hydrodynamic model CamaFlood, the flood depth of the river channel during the flood season under the global climate model is determined according to the simulated runoff depth series and the flood season ENSO index.

4. The method according to claim 3, characterized in that Get the simulated runoff depth series for each grid point in the predicted watershed, including: Based on a predefined artificial intelligence model for simulating runoff depth, a simulated runoff depth is obtained; Based on the quantile mapping model, the corrected runoff depth is obtained; A simulated runoff depth series for each grid point in the predicted watershed is determined based on the simulated runoff depth and the corrected runoff depth.

5. The method according to claim 4, characterized in that The corrected runoff depth is obtained based on the quantile mapping model and is implemented by the following formula: ； ； in, T Represents air temperature, specific humidity, relative humidity, shortwave radiation and longwave radiation, P Represents precipitation, snowfall, and runoff depth, adj represents the corrected series, obs represents observational data, GCM stands for global climate model, ref represents the historical reference period, d Represents daily data, Q Represents each quantile.

6. The method according to claim 5, characterized in that The relative humidity is determined by the following formula, ； In the above formula, T dew is the dew point temperature, T 2m The temperature at 2m, e sat (T.) represents the Clausius-Clapeyron thermodynamic equation; The specific humidity is determined by the following formula, ； In the above formula, p stands for ERA5 Earth's atmospheric pressure, T dew is the dew point temperature, e sat (.) represents the Clausius-Clapeyron thermodynamic equation.

7. The method according to claim 1, characterized in that The emergence constraint model is expressed by the following formula: ； In the above formula, Indicates the changing trend of the flooding magnitude at the basin scale in the future period, KKtrend Table 2 shows the changing trends of key physical factors of the basin spatial average in the historical period under the global climate model, where a and b represent model parameters.

8. A flood inundation event prediction device, characterized in that: include: The first determination module is used to determine the flood magnitude of the watershed scale in the predicted watershed according to the flood warning water depth and the flood depth of the river channel in the flood season under the global climate model; An analysis module, for analyzing the meteorological and hydrological data output by the global climate model based on machine learning to obtain the key physical factors of the basin spatial average of the historical period under the global climate model, wherein the key physical factors are important factors affecting the maximum flooding depth; A construction module is used to construct an emergence constraint model according to the change trend of the key physical factors of the basin spatial average in the historical period under the global climate model and the change trend of the flooding magnitude of the basin at the scale in the future period; The second determination module is used to determine the change trend of the flooding magnitude at the basin scale in the future period after correction based on the emergence constraint model and the key physical factors of the basin spatial average of the historical period corresponding to the ERA5-Land data set; The prediction module is used to predict the evolution of flood inundation events by weighted averaging the changing trends of the corrected basin-scale inundation magnitudes in the future period corresponding to each global climate model.

9. A computer-readable storage medium, characterized in that: The invention comprises a program, which, when being executed on a computer, causes the computer to execute the method according to any one of claims 1 to 7.

10. An execution device, characterized in that: comprising a processor and a memory, wherein the processor is coupled to the memory; The memory is used to store programs; The processor is configured to execute the program in the memory so that the execution device executes the method according to any one of claims 1 to 7.

Images