A rapid prediction method for urban typhoon disasters based on intelligent downscaling

Abstract

The present invention discloses a method for rapid prediction of urban typhoon disasters based on intelligent downscaling. Based on the wind field forecast results output by a coarse-resolution typhoon numerical forecast model, the present invention combines underlying surface information to construct an intelligent downscaling model, including a two-level downscaling model, to generate high-resolution local maximum wind field simulation results that take into account the influence of regional environmental characteristics. Furthermore, based on the construction of a building vulnerability assessment model to assess the impact of typhoons on buildings, the present invention comprehensively analyzes the damage risk of the target area and completes risk disaster prediction. The present invention combines high-resolution meteorological data to design a building disaster assessment model, which can efficiently assess the impact of typhoon extreme wind speeds on buildings and provide better support for urban disaster prevention decisions.

Description

Technical Field

[0001] The present invention belongs to the field of meteorological disaster prediction and urban disaster prevention, and specifically relates to a method for rapid prediction of urban typhoon disasters based on intelligent downscaling. Background Art

[0002] Typhoon is one of the main natural disasters that causes damage to urban buildings. Carrying out urban building risk disaster prediction under the background of typhoon weather can provide early warning of the risk of building damage caused by typhoons, help reduce the losses caused by disasters, and protect people’s lives and property.

[0003] Currently, methods for urban building risk assessment are primarily based on the coupling of meteorological models with building disaster assessment models. However, the spatial resolution of traditional numerical meteorological forecast models makes it difficult to accurately describe the wind field characteristics in urban microenvironments, especially in complex terrain and high-density built-up areas. High-resolution numerical models, on the one hand, require extensive computing resources, increasing forecasting costs and complexity; on the other hand, due to their lengthy computational time, they struggle to meet the demands of rapid forecasting, resulting in a slow response when an actual typhoon approaches, making it difficult to provide timely support for urban disaster prevention and mitigation. Furthermore, the accuracy of classic building disaster assessment models designed based on coarse-resolution meteorological data in typhoon risk and disaster forecasting needs to be improved. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for rapid prediction of urban typhoon disasters based on intelligent downscaling, so as to solve the problems of insufficient spatial resolution, low computational efficiency, or insufficient consideration of physical characteristics (such as traditional assessment models usually only consider wind without considering the additional impact of precipitation) in existing technologies, which lead to insufficient effectiveness of disaster response.

[0005] The present invention comprises the following steps:

[0006] Obtain coarse-resolution typhoon weather forecast data;

[0007] Using the coarse-resolution typhoon weather forecast data, high-resolution wind field data and precipitation data are generated through an intelligent downscaling model;

[0008] Using the high-resolution wind field data, high-resolution wind pressure information on urban building surfaces is generated;

[0009] Design a building risk assessment model to quickly predict the damage risk of urban buildings in typhoon weather based on urban building surface wind pressure data and high-resolution precipitation data;

[0010] The intelligent downscaling model includes at least two levels of downscaling models, and the at least two levels of downscaling models are used to generate local maximum wind field simulation results under extreme weather conditions taking into account the influence of regional environmental characteristics.

[0011] Preferably, the coarse-resolution typhoon weather forecast data includes wind speed, wind direction, temperature, air pressure, humidity and precipitation data.

[0012] Preferably, the intelligent downscaling model includes:

[0013] A first-level downscaling model is used to convert coarse-resolution typhoon weather forecast data into first-level fine-resolution weather data;

[0014] The second-level downscaling model is used to convert meteorological data with a first-level fine resolution into meteorological data with a second-level fine resolution.

[0015] Preferably, a first-level fine resolution meteorological numerical forecast model is used, the model resolution needs to reach 6 km, and the meteorological data of the first-level fine resolution is obtained by performing numerical simulation.

[0016] Preferably, when training the first-level downscaling model, its input is: historical typhoon event data and coarse-resolution meteorological data for a recent complete two years; and its output is: first-level fine-resolution meteorological data for the corresponding time period.

[0017] Preferably, a second-level fine-resolution meteorological numerical forecast model is used, and the model resolution needs to reach 1 km. The second-level fine-resolution meteorological data is obtained by conducting numerical simulations, and the second-level fine-resolution meteorological data is used for vulnerability assessment based on corrected building data; the second-level fine-resolution meteorological numerical forecast model is a meteorological forecast model that can move with the typhoon, and the grid center position of the model is the typhoon center position in the first-level fine-resolution meteorological simulation results.

[0018] Preferably, when training the secondary downscaling model, its input is: extracting the moments when the maximum wind speed of the typhoon on land reaches 30m / s or above, and using the meteorological data of the first-level fine resolution at these moments as input; the output is: the meteorological data of the second-level fine resolution of the corresponding time period.

[0019] Preferably, before generating high-resolution urban building surface wind pressure information, the method further includes:

[0020] Construction of urban CFD models;

[0021] Construction of AI urban building wind pressure model;

[0022] AI urban building wind pressure model optimization;

[0023] In the step of constructing the urban CFD model, the wind speed data obtained by the secondary downscaling model is used to fit a logarithmic curve of wind speed and height, wind shear is calculated, and the wind speed is corrected theoretically using the equivalent roughness of the building;

[0024] In the step of constructing the AI ​​city building wind pressure model, the building surface wind field pressure obtained by simulating the urban CFD model is used as output to establish the AI ​​city building wind pressure model.

[0025] Preferably, in the risk assessment model for designing buildings, a fragility function is used to assess the damage probability of a building under a typhoon, and the additional impact of precipitation is taken into account to correct the fragility function.

[0026] Preferably, based on the probability distribution of damage to each building obtained from the modified fragility function, the dominant damage level of all buildings in the area is calculated and summarized to obtain the regional risk disaster level result.

[0027] Beneficial effects of the invention: The invention provides a method for rapid prediction of urban typhoon disasters based on intelligent downscaling. This method combines high-resolution meteorological data to design a building disaster assessment model, which can efficiently assess the impact of typhoon extreme wind speeds on buildings and provide better support for urban disaster prevention decision-making, which is of great significance. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 This is a flow chart of an embodiment of the present application.

[0029] Figure 2 This is a specific flow chart of step S6 in the embodiment of this application. DETAILED DESCRIPTION

[0030] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are merely examples, and those skilled in the art may conceive of other obvious variations.

[0031] This application is based on the wind field forecast results output by the coarse-resolution typhoon numerical forecast model, combined with the underlying surface information, to construct an intelligent downscaling model, including a two-level downscaling model, to generate high-resolution local maximum wind field simulation results that take into account the influence of regional environmental characteristics. On the basis of constructing a building vulnerability assessment model to evaluate the impact of typhoons on buildings, the damage risk of the target area is comprehensively analyzed to complete the risk disaster prediction.

[0032] like Figure 1 As shown, this embodiment provides a method for rapid prediction of urban typhoon disasters based on intelligent downscaling, which includes the following steps.

[0033] Step S1: Coarse-resolution meteorological simulation, used to obtain coarse-resolution typhoon meteorological forecast data.

[0034] Carry out meteorological numerical simulation covering China with a resolution of 0.25° (about 28km), and obtain coarse-resolution meteorological data including wind speed V0, wind direction θ0, temperature T0, and air pressure P a0 , humidity Hu0, precipitation Pr0 data.

[0035] Step S2: First-level fine resolution meteorological simulation, used to obtain first-level fine resolution meteorological data.

[0036] According to the typhoon-affected areas in China, a set of independent or multiple combined first-level fine-resolution meteorological numerical forecast models are constructed, and the model resolution needs to reach 6km. Through numerical simulation, the meteorological data of the first-level fine resolution including wind speed V1, wind direction θ1, temperature T1, air pressure P a1 , humidity Hu1, precipitation Pr1 data.

[0037] Step S3: A first-level downscaling model is constructed to convert the coarse-resolution typhoon weather forecast data into first-level fine-resolution weather data.

[0038] Statistics are collected for historical typhoons that have affected China. An appropriate number of typhoon events, as well as a recent two-year period, are selected. The coarse-resolution meteorological data from this period (from step S1) is used as input. The differences in surface information between the first-level fine resolution and the coarse resolution, including terrain elevation difference and roughness ratio, are combined. The first-level fine resolution meteorological data from this period (from step S2) is used as output to construct a first-level downscaling model for training. This ensures that the coarse-resolution meteorological data can be used to obtain the first-level fine resolution meteorological data.

[0039] Step S4: Second-level fine-resolution meteorological simulation, used to obtain second-level fine-resolution meteorological data.

[0040] To effectively reduce computational complexity and ensure sufficient data for the typhoon region, a meteorological forecast model that follows the typhoon's movement is established. The model grid is typically set to 180 km × 180 km with a resolution of 1 km. The center of the model grid is the typhoon center position from the first-level fine-resolution meteorological simulation results (from step S2 or S3). Second-level fine-resolution meteorological data, including wind speed V2, wind direction θ2, and precipitation Pr2, are obtained through numerical simulation.

[0041] Since wind speed is affected by multiple meteorological factors, the second-level fine resolution meteorological simulation still requires complete first-level fine resolution meteorological data including wind speed V1, wind direction θ1, temperature T1, air pressure P a1, humidity Hu1, and precipitation Pr1 data are used as input, but at this time only wind data and precipitation data need to be output for vulnerability assessment based on the corrected building data.

[0042] Step S5: constructing a second-level downscaling model, which is used to convert meteorological data with a first-level fine resolution into meteorological data with a second-level fine resolution.

[0043] Based on the selected influential historical typhoons, the moments when the maximum wind speed of the typhoon over China reached 30 m / s or above are extracted. The first-level fine-resolution meteorological data (from step S2 or S3) at these moments is used as input. Combined with terrain information, roughness information, and building information, the second-level fine-resolution meteorological data (from step S4) during these periods is used as output to construct a second-level downscaling model for training. This ensures that the first-level fine-resolution meteorological data can be input to obtain the second-level fine-resolution meteorological data.

[0044] Furthermore, the construction logic of the first-level downscaling model in this embodiment is to map a fixed area, primarily used to improve resolution to capture convective effects, which is a common practice. Because second-level fine-resolution meteorological simulations require precise capture of wind and precipitation characteristics in typhoon regions, high resolution is required. Directly downscaling methods using fixed-area methods would require excessive computational effort. Furthermore, the typhoon duration within each grid area is short, and non-typhoon data in many areas is redundant. Therefore, tracking is centered around the typhoon, using a moving grid.

[0045] Step S6: Risk disaster prediction: Based on meteorological data and combined with building information, conduct building vulnerability assessment to complete the prediction of urban risk disasters. The specific steps include: S6-1 Urban CFD model construction, S6-2 AI urban building wind pressure model construction, S6-3 AI urban building wind pressure model optimization, S6-4 Building vulnerability assessment and S6-5 Regional risk disaster assessment, see Figure 2 .

[0046] Step S6-1: Construction of city CFD model.

[0047] A set of urban CFD models with a grid area of ​​about 5km×5km and a resolution of about 5m is established. The model uses the corrected wind data of the second-level fine resolution (from step S5) including the wind speed V 2f and wind direction θ2 as initial conditions and boundary conditions, and output the wind field pressure P on the building surface.

[0048] In a preferred example, the wind data is specifically corrected as follows:

[0049] 1. Using the wind speed data V2 obtained by the two-level downscaling model (the wind speed varies at different heights, k is the layer number, and the total number of layers is N), a logarithmic curve of wind speed and height is fitted to calculate the wind shear α:

[0050]

[0051]

[0052]

[0053] Where V is the symbol of the velocity variable and H is the symbol of the height variable.

[0054] 2. Use the equivalent roughness z of the building B , calculate the theoretical corrected wind speed V 2f1 :

[0055]

[0056] Where z0 is the environmental roughness.

[0057] 3. Combined with empirical parameters , if 0.1 is taken, calculate the corrected wind speed V 2f :

[0058]

[0059] Step S6-2: Constructing an AI urban building wind pressure model.

[0060] Since this embodiment mainly targets cities in fixed locations, significant changes in cities over short periods of time are generally not considered. Therefore, one or more urban CFD models can be established based on the urban area to be analyzed. The second-level fine-resolution meteorological data used for training the second-level downscaling model is classified according to different typhoon levels to establish a typhoon environment dataset. The wind data in this dataset is used as the input of the urban CFD model after data correction. The building surface wind field pressure obtained by simulating the urban CFD model is used as the output to establish an AI urban building wind pressure model, thereby enabling the rapid determination of urban building surface wind pressure based on the results of the second-level downscaling model.

[0061] Step S6-3: Optimizing the AI ​​urban building wind pressure model.

[0062] When the number and types of simulated urban areas are rich enough, the geometric parameters of the buildings in the area (such as height, width / aspect ratio, building orientation, relative position of buildings, etc.) can be further used as features to directly input the second-level fine-resolution meteorological data and building layout conditions, and directly obtain the surface wind pressure distribution of urban buildings under the building layout conditions.

[0063] Step S6-4: Building vulnerability assessment.

[0064] After obtaining high-resolution wind pressure maps, we apply the fragility function to assess the probability of building damage during a typhoon. The specific process involves categorizing buildings into a limited number of categories (e.g., multi-story brick-concrete residential buildings, frame office buildings, high-rise steel structures, etc.) based on attributes such as height, structural system, age, and functional use. Each building category is then assigned a specific fragility function.

[0065] The fragility function in this embodiment describes the probability of a building reaching or exceeding a certain damage level under a given disaster load (such as wind pressure). The expression of the fragility function is as follows:

[0066]

[0067] Among them, P b Indicates that under a given wind pressure (unit: Pa), the building damage level D reaches or exceeds level d k The probability of reaching the damage level d k The median wind pressure at 1000 km / h is 100 km / h; β represents the standard deviation of the log-normal distribution (reflecting uncertainty); Φ represents the cumulative distribution function of the standard normal distribution; there are 4 levels of building damage level D, including no damage, slight, moderate, severe, and complete destruction. k It is a specific level (such as "medium").

[0068] Heavy rainfall accompanied by strong winds increases the possibility of building damage. Therefore, this embodiment further improves the classic fragility function and designs a precipitation correction factor λ. The value of this factor is related to the precipitation (data from step S5) and the building damage level D. For example, the default value of λ is 1. When the precipitation is greater than 25mm, λ for slight, moderate, severe, and complete damage increases by 0.2; when the precipitation is greater than 50mm, λ for moderate, severe, and complete damage increases by another 0.3; when the precipitation is greater than 100mm, λ for severe and complete damage increases by another 0.5; when the precipitation is greater than 250mm, λ for complete damage increases by another 1. The specific value needs to be adjusted according to actual and regional conditions. The modified fragility function P bf The expression is as follows:

[0069]

[0070] For each building, the damage probability of each level is calculated using the formula based on the modified fragility function that matches the category to which it belongs: the level corresponding to the maximum probability is taken as the predicted damage level.

[0071] Step S6-5: Regional risk and disaster assessment.

[0072] Based on the modified fragility function, the probability distribution of damage to each building can be obtained. Then, the proportion of buildings in each damage level is statistically analyzed at the regional scale. According to the probability of damage level of each building, the maximum probability method is used (the level with the highest probability is selected as the damage level of the building) to calculate its dominant level. The dominant damage levels of all buildings in the area are summarized, and the result is the regional risk disaster level result.

[0073] Because the prediction method of this embodiment does not require extensive on-site surveys or physical modeling, it offers the advantages of high efficiency, low cost, and scalability. It relies on existing data and models, eliminating the need for expensive field measurements or wind tunnel testing, and can rapidly complete damage prediction for large-scale building complexes. Furthermore, it leverages remote sensing and building parameters to enable widespread classification and risk prediction of large-scale building complexes. This method is particularly suitable for scenarios such as city-level or regional typhoon disaster emergency warnings, risk surveys, insurance claims assessments, and urban planning support, providing scientific and efficient technical support for disaster prevention and mitigation.

[0074] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions merely illustrate the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A rapid prediction method for urban typhoon disasters based on intelligent downscaling, characterized by: The method comprises the following steps: Obtain coarse-resolution typhoon weather forecast data; Using the coarse-resolution typhoon weather forecast data, high-resolution wind field data and precipitation data are generated through an intelligent downscaling model; Using the high-resolution wind field data, high-resolution wind pressure information on urban building surfaces is generated; Design a building risk assessment model to quickly predict the damage risk of urban buildings in typhoon weather based on urban building surface wind pressure data and high-resolution precipitation data; The intelligent downscaling model includes two levels of downscaling models, which are used to generate local maximum wind field simulation results under extreme weather conditions, taking into account the influence of regional environmental characteristics; wherein: A first-level downscaling model is used to convert coarse-resolution typhoon weather forecast data into first-level fine-resolution weather data; A second-level downscaling model is used to convert meteorological data with a first-level fine resolution into meteorological data with a second-level fine resolution; Before generating high-resolution urban building surface wind pressure information, the following steps are included: Construction of urban CFD models; Construction of AI urban building wind pressure model; AI urban building wind pressure model optimization; In the step of constructing the urban CFD model, the wind speed data obtained by the secondary downscaling model is used to fit a logarithmic curve of wind speed and height, wind shear is calculated, and the wind speed is corrected theoretically using the equivalent roughness of the building; In the step of constructing the AI ​​city building wind pressure model, the building surface wind field pressure obtained by simulating the urban CFD model is used as output to establish the AI ​​city building wind pressure model.

2. The method for rapid prediction of urban typhoon disasters based on intelligent downscaling according to claim 1 is characterized in that: The coarse-resolution typhoon weather forecast data includes wind speed, wind direction, temperature, air pressure, humidity and precipitation data.

3. The method for rapid prediction of urban typhoon disasters based on intelligent downscaling according to claim 1, characterized in that: A first-level fine-resolution meteorological numerical forecast model is used, and the model resolution needs to reach 6km. The meteorological data of the first-level fine-resolution is obtained by conducting numerical simulation.

4. The method for rapid prediction of urban typhoon disasters based on intelligent downscaling according to claim 3 is characterized in that: When training the first-level downscaling model, its input is: historical typhoon event data and coarse-resolution meteorological data for a complete two-year period in the recent period; and its output is: first-level fine-resolution meteorological data for the corresponding time period.

5. The method for rapid prediction of urban typhoon disasters based on intelligent downscaling according to claim 1, characterized in that: A second-level fine-resolution meteorological numerical forecast model with a resolution of 1 km is used. Numerical simulations are performed to obtain meteorological data with the second-level fine-resolution. The meteorological data with the second-level fine-resolution is used for vulnerability assessment based on the corrected building data. The second-level fine-resolution meteorological numerical forecast model is a meteorological forecast model that can follow the movement of a typhoon. The grid center position of the model is the typhoon center position in the first-level fine-resolution meteorological simulation results.

6. The method for rapid prediction of urban typhoon disasters based on intelligent downscaling according to claim 5, characterized in that: When training the two-level downscaling model, its input is: extracting the moments when the maximum wind speed of the typhoon on land reaches 30m / s or above, and using the first-level fine resolution meteorological data at these moments as input; the output is: the second-level fine resolution meteorological data for the corresponding time period.

7. The method for rapid prediction of urban typhoon disasters based on intelligent downscaling according to claim 1, characterized in that: In the risk assessment model for designing buildings, a fragility function is used to assess the damage probability of a building under a typhoon, and the additional impact of precipitation is taken into account to modify the fragility function.

8. The method for rapid prediction of urban typhoon disasters based on intelligent downscaling according to claim 7, characterized in that: Based on the probability distribution of damage to each building obtained from the modified fragility function, the dominant damage level of all buildings in the region is calculated, and the regional risk disaster level results are summarized.

Images