A method, device and electronic equipment for predicting an urban low-altitude microscale wind field

Abstract

The present application relates to the technical field of low-altitude wind field prediction. A city low-altitude microscale wind field prediction method, device and electronic equipment are provided. The method comprises the following steps: obtaining low-altitude wind field data corresponding to a target region; dividing the low-altitude wind field data into first low-altitude wind field data and second low-altitude wind field data, wherein the data amount of the first low-altitude wind field data is less than that of the second low-altitude wind field data; obtaining wind field simulation data of the target region, inputting the low-altitude wind field data and the wind field simulation data into a pre-trained first wind field prediction model to obtain first wind field prediction data; and inputting the first wind field prediction data and the second low-altitude wind field data into a pre-trained second wind field prediction model to obtain second wind field prediction data. The present application realizes rapid prediction and high-precision prediction of the microscale wind field of the target region, thereby providing key data support for the route planning and safe flight of low-altitude aircraft.

Description

Technical Field

[0001] This invention relates to the field of low-altitude wind field prediction technology, specifically to a method, device, and electronic equipment for predicting urban low-altitude microscale wind fields. Background Technology

[0002] With the rapid development of the low-altitude economy, low-altitude aircraft (especially manned aircraft) are playing an increasingly important role in the urbanization process, and their safe flight has become a focus of attention for all sectors of society. Urban low-altitude airspace, as the main space for unmanned aerial vehicles and the development of the low-altitude economy, is most significantly affected by wind, which is highly variable. Therefore, accurately predicting wind speed and direction is crucial for ensuring safe low-altitude flight routes.

[0003] Urban low-altitude wind fields are a key factor affecting aircraft route planning and flight safety. Their complexity and variability pose a severe challenge to the stable operation of aircraft. Compared with the high-altitude wind environment, urban low-altitude wind fields are influenced by multiple factors, including urban structure, building distribution, heat emissions, and land use types. They are also affected by the superposition of atmospheric circulation and various local circulations, resulting in extremely complex wind field characteristics. Specifically, the incoming flow direction is variable and uneven, local wind phenomena are prevalent, turbulence is strong, and the wind field is significantly affected by the coupling of multiple physical field factors.

[0004] Currently, research on the observation and forecasting of complex urban wind fields mainly focuses on the mesoscale range, whose spatial resolution is far from sufficient to resolve the high-precision wind field information required by low-altitude aircraft. While mesoscale meteorological models (WRF) play an important role in weather forecasting, their spatial resolution is typically on the order of kilometers, which cannot meet the flight safety forecasting requirements of low-altitude aircraft at scales of hundreds or even tens of meters. In addition, currently available products for testing complex low-altitude wind fields, such as weather radars, anemometers, and six-component small weather stations, although they can accurately acquire wind field information, have poor spatial resolution (due to limited deployment numbers) and low temporal resolution, making it difficult to achieve high-precision resolution of complex low-altitude wind fields.

[0005] Therefore, to address the problem of insufficient temporal and spatial accuracy in low-altitude wind field prediction, a method for predicting urban low-altitude microscale wind fields is developed, which has important practical significance and application value for ensuring the route planning and flight safety of low-altitude aircraft. Summary of the Invention

[0006] This invention provides a method, device, and electronic equipment for predicting urban low-altitude microscale wind fields, which addresses the shortcomings of insufficient temporal and spatial accuracy in existing low-altitude wind field prediction technologies, thereby ensuring more accurate route planning for low-altitude aircraft.

[0007] This invention provides a method for predicting urban low-altitude microscale wind fields, comprising:

[0008] Obtain low-altitude wind field data corresponding to the target area;

[0009] The low-altitude wind field data is divided into first low-altitude wind field data and second low-altitude wind field data, and the amount of data in the first low-altitude wind field data is less than the amount of data in the second low-altitude wind field data.

[0010] Obtain wind field simulation data for the target area; the wind field simulation data is obtained by simulating the target area using a nested coupling mode of mesoscale model WRF and CFD.

[0011] The first low-altitude wind field data and the wind field simulation data are input into the pre-trained first wind field prediction model to obtain the first wind field prediction data.

[0012] The first wind field prediction data and the second low-altitude wind field data are input into the pre-trained second wind field prediction model to obtain the second wind field prediction data.

[0013] Based on the second wind field prediction data, the wind field prediction result for the target area is determined.

[0014] According to the urban low-altitude microscale wind field prediction method provided by the present invention, the step of acquiring low-altitude wind field data corresponding to the target area includes:

[0015] Wind field data of the target area is obtained using weather radar, anemometer, or a six-component small weather station; the wind field data includes wind speed and wind direction.

[0016] According to the urban low-altitude microscale wind field prediction method provided by the present invention, the step of obtaining wind field simulation data of the target area includes:

[0017] Obtain a 3D solid model of the building complex corresponding to the target area;

[0018] The mesoscale model WRF was used to simulate the low-altitude wind field data of the target area to obtain the initial wind field simulation results.

[0019] The initial wind field simulation results are used as boundary conditions for CFD simulation. Based on these boundary conditions, a secondary simulation is performed on the three-dimensional solid model of the building complex to obtain the wind field simulation data of the target area.

[0020] According to the urban low-altitude micro-scale wind field prediction method provided by the present invention, obtaining the three-dimensional solid model of the building complex corresponding to the target area includes:

[0021] Acquire GIS building vector data and terrain elevation DEM data of the target area; the vector data includes the building's planar location, outline, floor area, and height;

[0022] A three-dimensional solid model of the building complex is generated based on the GIS building vector data and the terrain elevation DEM data.

[0023] According to the urban low-altitude microscale wind field prediction method provided by the present invention, the first wind field prediction model and the second wind field prediction model are constructed using XGBoost model, CNN model, LSTM model, Transformer model, LightGBM model, or CatBoost model.

[0024] According to the urban low-altitude microscale wind field prediction method provided by the present invention, before dividing the low-altitude wind field data into first low-altitude wind field data and second low-altitude wind field data, the method further includes:

[0025] The low-altitude wind field data corresponding to the acquired target area is preprocessed. The preprocessing includes data cleaning to remove outliers and noise from the data, and data normalization to unify wind field data of different magnitudes into the same numerical range.

[0026] The present invention also provides a device for predicting urban low-altitude microscale wind fields, comprising:

[0027] The acquisition unit is used to acquire low-altitude wind field data corresponding to the target area.

[0028] A partitioning unit is used to divide the low-altitude wind field data into first low-altitude wind field data and second low-altitude wind field data, wherein the amount of data in the first low-altitude wind field data is less than the amount of data in the second low-altitude wind field data.

[0029] The acquisition unit is further configured to acquire wind field simulation data of the target area; the wind field simulation data is obtained by simulating the target area using a nested coupling mode of mesoscale model WRF and CFD.

[0030] The prediction unit is used to input the first low-altitude wind field data and the wind field simulation data into a pre-trained first wind field prediction model to obtain the first wind field prediction data.

[0031] The prediction unit is also used to input the first wind field prediction data and the second low-altitude wind field data into a pre-trained second wind field prediction model to obtain the second wind field prediction data.

[0032] The determining unit is used to determine the wind field prediction result of the target area based on the second wind field prediction data.

[0033] The present invention provides a method, device, and electronic equipment for predicting urban low-altitude microscale wind fields. By using data obtained from simulating a target area using a nested coupling mode of mesoscale model WRF and CFD, and using the corresponding first low-altitude wind field data of the target area as input to a first wind field prediction model, rapid prediction of the microscale wind field of the target area is achieved. Then, by using the first wind field prediction data and the second low-altitude wind field data as input to a second wind field prediction model, high-precision prediction of the microscale wind field of the target area is achieved, thereby providing key data support for the route planning and safe flight of low-altitude aircraft. Attached Figure Description

[0034] Figure 1 One of the flowcharts for the urban low-altitude microscale wind field prediction method provided by the present invention;

[0035] Figure 2 The second flowchart of the method for predicting urban low-altitude microscale wind fields provided by this invention;

[0036] Figure 3 This is a schematic diagram of the process for modeling and simulating microscale wind fields in urban areas according to an embodiment of the present invention;

[0037] Figure 4 A schematic diagram of the urban low-altitude microscale wind field prediction device provided by the present invention;

[0038] Figure 5 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0040] Figure 1 This is one of the flowcharts for the urban low-altitude microscale wind field prediction method provided by the present invention. Figure 2 The second flowchart of the urban low-altitude microscale wind field prediction method provided by this invention is as follows. Figure 1 As shown, the method includes:

[0041] Step 101: Obtain the low-altitude wind field data corresponding to the target area.

[0042] Specifically, the target area of ​​this invention is the urban low-altitude wind field area. The wind field data for this area is based on existing sparse meteorological observation data, specifically core wind field parameters such as wind speed and direction directly acquired using existing meteorological observation equipment (such as weather radar, anemometers, and six-component small weather stations). While the data acquired by these devices has low temporal and spatial resolution and is limited by factors such as the number of low-altitude airspace deployments and operating costs, resulting in insufficient resolution for complex low-altitude wind fields, the data is highly reliable and can reflect the true characteristics of the local wind field.

[0043] Step 102: Divide the low-altitude wind field data into first low-altitude wind field data and second low-altitude wind field data, wherein the amount of data in the first low-altitude wind field data is less than the amount of data in the second low-altitude wind field data.

[0044] Specifically, this application divides the data into "a small amount of sparse data (first low-altitude wind field data)" and "a relatively large amount of data (second low-altitude wind field data)," and uses these two parts of data as inputs to the first wind field prediction model and the second wind field prediction model, respectively. This allows the first low-altitude wind field data to be used to initially fuse simulation information to cover the whole, thereby improving the prediction efficiency of the first wind field prediction model. At the same time, the second low-altitude wind field data is used to finely correct the prediction accuracy of the model.

[0045] Step 103: Obtain wind field simulation data for the target area; the wind field simulation data is obtained by simulating the target area using a nested coupling mode of mesoscale model WRF and CFD.

[0046] Specifically, current numerical simulations struggle to accurately determine weather boundary conditions, leading to significant deviations between simulation results and actual data; furthermore, they fail to effectively integrate with meteorological test data. Numerical simulation models used for weather forecasting, when reaching the space required by low-altitude aircraft, incur extremely high computational demands and struggle to guarantee timeliness. This application employs the mesoscale model WRF to provide a kilometer-scale regional circulation background (also considering the influence of physical processes such as water vapor, longwave and shortwave radiation, cumulus, and underlying surface), while CFD (Computational Fluid Dynamics) offers advantages such as high spatiotemporal resolution and the ability to establish high-precision realistic building and terrain models. By combining the advantages of both, this application obtains more accurate and refined wind field information. Specifically, WRF provides realistic boundary conditions for CFD, while CFD outputs high-precision wind field data in the core region (e.g., 2km × 2km) to construct a high-resolution wind field database covering the target area.

[0047] Furthermore, the data obtained by simulating the target area using the nested coupling mode of mesoscale model WRF and CFD can cover areas where sensors are not deployed, thus making up for the spatial gaps in the observation data. Moreover, it realizes the details of wind field at the meter scale (such as the influence of building flow and terrain undulation), thereby improving the prediction capability of complex wind field characteristics. The accurate low-altitude microscale wind field prediction results can directly serve the route planning of low-altitude aircraft, helping aircraft to avoid dangerous wind environments (such as strong turbulence, sudden gusts, etc.), reduce the risk of flight accidents, and ensure the operational safety of manned aircraft and other aircraft.

[0048] Step 104: Input the first low-altitude wind field data and wind field simulation data into the pre-trained first wind field prediction model to obtain the first wind field prediction data.

[0049] Specifically, the first wind field prediction model can be constructed using machine learning methods such as XGBoost, CNN, LSTM, Transformer, LightGBM, or CatBoost. In this embodiment of the invention, the first wind field prediction model constructed using the XGBoost model will be used as an example for illustration.

[0050] This invention utilizes the XGBoost model as the first wind field prediction model to fuse first low-altitude wind field data with wind field simulation data. This achieves an effective fusion of the realism of the observed data and the high resolution of the simulation data, allowing the observed data to correct the deviations in the simulation data and the simulation data to supplement the spatial coverage of the observed data, thereby initially reconstructing the global wind field characteristics of the target area.

[0051] Step 105: Input the first wind field prediction data and the second low-altitude wind field data into the pre-trained second wind field prediction model to obtain the second wind field prediction data.

[0052] Specifically, the second wind field prediction model of this application is based on the first wind field prediction data and inputs a large amount of second low-altitude wind field data, so that the second wind field prediction model can further correct the error of the wind field data, thereby improving the prediction accuracy of the wind field in the target area.

[0053] Step 106: Determine the wind field prediction result for the target area based on the second wind field prediction data.

[0054] Specifically, the second wind field prediction data includes parameters such as wind speed and wind direction at any location within the target area, which can be directly used to reflect the spatiotemporal distribution characteristics of the wind field, such as turbulence intensity and wind profile changes.

[0055] The urban low-altitude microscale wind field prediction method provided by this invention achieves rapid prediction of the microscale wind field of the target area by using data obtained from simulating the target area using a nested coupling mode of mesoscale model WRF and CFD, and the corresponding low-altitude wind field data of the target area as input to the first wind field prediction model; then, by using the first wind field prediction data and the second low-altitude wind field data as input to the second wind field prediction model, high-precision prediction of the microscale wind field of the target area is achieved.

[0056] Furthermore, the present invention obtains wind field simulation data of the target area by: obtaining a three-dimensional solid model of the building complex corresponding to the target area; simulating the low-altitude wind field data of the target area using the mesoscale model WRF to obtain initial simulation results; using the initial simulation results as the boundary conditions for CFD simulation, and performing a secondary simulation of the three-dimensional solid model of the building complex based on the boundary conditions, thereby obtaining the wind field simulation data of the target area.

[0057] Specifically, firstly, a 3D solid model of the building complex corresponding to the target area is collected and constructed. This process requires the use of professional surveying techniques, Geographic Information System (GIS) data, and architectural design materials to ensure that the model can realistically represent the actual shape, relative position, and spatial distribution of all buildings within the target area, laying the foundation for subsequent accurate simulation of the interaction between wind fields and buildings. In this embodiment of the invention, the 3D solid model of the building complex is obtained through the following methods:

[0058] First, obtain GIS building vector data and terrain elevation DEM data for the target area; the vector data includes the building's planar location, outline, floor area, and height; based on the GIS building vector data and terrain elevation DEM data, generate a three-dimensional solid model of the building complex.

[0059] Secondly, the mesoscale model WRF was used to simulate the low-level wind field data of the target area, thus obtaining low-resolution initial simulation results. The mesoscale model WRF is a numerical simulation tool widely used in atmospheric science. It can consider various physical processes and dynamic mechanisms of atmospheric motion, and by setting and calculating relevant meteorological parameters, it generates macroscopic simulation results of the low-level wind field in the target area. These results reflect the trends and characteristics of wind field changes on a larger spatial scale.

[0060] Then, the initial wind field simulation results are used as boundary conditions for the computational fluid dynamics (CFD) simulation. CFD simulation focuses on studying the flow details of fluids (air in this embodiment) within local complex geometries (i.e., building complexes). Inputting the initial wind field simulation results as boundary conditions into the CFD model is equivalent to setting external atmospheric environmental constraints for the CFD simulation, enabling it to accurately simulate airflow around the building complex while considering the macroscopic meteorological background.

[0061] Finally, CFD simulation was performed on the three-dimensional solid model of the building complex based on the set boundary conditions. By numerically solving the fluid dynamics equations, the physical processes such as air flow, turbulence generation and diffusion on and around the building surfaces were simulated, thereby obtaining detailed wind field distribution information of the target area. This information constitutes the wind field simulation data of the target area.

[0062] The following is combined Figure 3 The solution provided by the present invention will be further described below:

[0063] First, this application acquires Geographic Information System (GIS) building vector data and Digital Elevation Model (DEM) data of the target area. The vector data includes the planar location, outline, floor area, and height of the buildings, while the DEM data reflects the terrain elevation information. Using the Grasshopper (GH) plugin in Rhino software as the development tool, a first GH program is created to batch generate 3D solid models of urban building complexes based on the aforementioned GIS building vector data and terrain elevation DEM data. Simultaneously, a second GH program is created to construct a terrain surface model based on the DEM data, achieving automatic calibration of the relative positions of the 3D solid model of the building complex and the terrain surface model. Based on the ground roughness category determination criteria in the building structure load code, a third GH program is created to automatically acquire the ground roughness category of the target area under different wind directions, forming a 3D solid model of the building complex containing information on the building complex, terrain, and ground roughness. Then, using the acquired 3D solid model of the building complex, a nested coupling mode of the mesoscale meteorological model WRF (Weather Research and Forecasting Model) and computational fluid dynamics (CFD) is adopted to simulate the wind field of the target area, as follows:

[0064] WRF simulations were used to analyze mesoscale circulation information within a kilometer-scale range in the target area, encompassing physical processes such as water vapor, longwave and shortwave radiation, cumulus clouds, and underlying surface. The output results were used as boundary conditions for CFD simulations. Based on these boundary conditions, high-resolution (meter-level) numerical simulations were performed on a 3D solid model of the building complex in the core area of ​​the target area (e.g., a 2km × 2km scale). Combined with high-precision terrain elevation data, microscale wind field data including wind speed, wind direction, and turbulence characteristics were output. The WRF simulation results with different assimilation schemes were compared and analyzed to optimize the boundary condition settings. A high-resolution wind field database for the target area was constructed through the above coupled simulations, and this high-resolution wind field database was used as the wind field simulation data for the target area.

[0065] This application pre-constructs 3D solid models of building clusters based on GIS and DEM data, accurately reproducing the microscopic features of the target area, such as building distribution and terrain undulations. This provides realistic geometric boundary conditions for wind field simulation, solving the simulation bias problem caused by the neglect of local building details in traditional mesoscale models. Furthermore, the mesoscale model WRF can provide a macroscopic circulation background (including physical processes such as water vapor and radiation) over a kilometer-scale area, providing reliable boundary conditions for CFD; while CFD excels at high-resolution (meter-scale) microscale simulation, finely depicting local wind field characteristics such as building-around-flow and terrain influence. The nested coupling of these two models ensures the global rationality of the simulation while achieving meter-level accuracy in the core area (e.g., 2km × 2km), overcoming the resolution limitations of single models.

[0066] Since urban low-altitude wind fields are significantly affected by factors such as building distribution and topography, this application accurately incorporates these local factors through a three-dimensional solid model of building clusters, and combines the WRF-CFD nested coupling mode to simulate the superposition effect of "atmospheric circulation + local circulation", which is more in line with the actual characteristics of urban low-altitude wind fields such as "variable incoming flow, strong turbulence, and multi-physics coupling", and solves the problem that traditional mesoscale models (such as WRF alone) cannot capture the details of microscale wind fields.

[0067] This invention achieves a unified approach of high-resolution, high-fidelity, and high-applicability wind field simulation data through high-precision modeling and mode coupling, thereby providing core data support for the accurate prediction of urban low-altitude micro-scale wind fields.

[0068] The first wind field prediction model provided by this invention is constructed using a machine learning model and is trained using a loss function.

[0069] Specifically, taking the first wind field prediction model built with the XGBoost model as an example: Urban low-altitude wind field observation data is often sparse due to limited sensor deployment (e.g., only covering take-off and landing points or key flight paths). The XGBoost model, through an ensemble learning framework (iterative optimization of multiple decision trees), can effectively handle high-dimensional sparse data, mining potential patterns from the fusion of limited observation data and wind field simulation data, avoiding overfitting caused by data sparsity, and improving the generalization prediction ability for wind field characteristics in unobserved areas. Moreover, XGBoost is more robust to missing and outlier values, making it more suitable for real-world scenarios in complex urban wind fields. Furthermore, the XGBoost model controls model complexity through regularization terms and optimizes split node selection using parallel computing, resulting in fast training speed and high computational efficiency. It can quickly fuse "sparse observation data + WRF-CFD nested coupled simulation data" and output the first wind field prediction data. This feature solves the problem of "large computational load and high time consumption" in traditional CFD simulations and avoids the excessive dependence of complex deep learning models on computing power, meeting the timeliness requirements of low-altitude aircraft for wind field prediction. The core objective of wind field prediction is to accurately output continuous physical quantities such as wind speed and direction. A typical loss function, represented by mean squared error (E), can effectively measure the deviation between the predicted and actual values, assigning higher weights to larger errors (such as sudden changes in wind speed caused by turbulence). Using E as the training metric, the XGBoost model can be driven to focus on optimizing the prediction accuracy of key wind field features (such as peak wind speed and sudden changes in wind direction), avoiding the impact of error accumulation on the safety assessment of low-altitude aircraft.

[0070] Furthermore, before dividing the low-altitude wind field data into first low-altitude wind field data and second low-altitude wind field data, the method further includes: preprocessing the low-altitude wind field data corresponding to the acquired target area, wherein the preprocessing includes data cleaning to remove outliers and noise from the data; and data normalization to unify wind field data of different magnitudes into the same numerical range.

[0071] Specifically, urban low-altitude wind fields are susceptible to anomalies (such as sudden increases in wind speed to physically unreasonable levels) or noise (such as high-frequency random fluctuations) due to sensor malfunctions, electromagnetic interference, and instantaneous fluctuations caused by extreme weather. By cleaning and removing these interferences, abnormal data can be prevented from misleading model training, ensuring that the wind field data (wind speed and direction) input into the model is more consistent with reality, thereby improving the model's prediction accuracy.

[0072] The urban low-altitude microscale wind field prediction device provided by the present invention is described below. The urban low-altitude microscale wind field prediction device described below can be referred to in correspondence with the urban low-altitude microscale wind field prediction method described above.

[0073] Figure 4 A schematic diagram of the urban low-altitude microscale wind field prediction device provided by the present invention includes:

[0074] Acquisition unit 401 is used to acquire low-altitude wind field data corresponding to the target area;

[0075] The partitioning unit 402 is used to divide the low-altitude wind field data into first low-altitude wind field data and second low-altitude wind field data, wherein the amount of data in the first low-altitude wind field data is less than the amount of data in the second low-altitude wind field data.

[0076] The acquisition unit 401 is further configured to acquire wind field simulation data of the target area; the wind field simulation data is data obtained by simulating the target area using a nested coupling mode of mesoscale model WRF and CFD.

[0077] Prediction unit 403 is used to input the first low-altitude wind field data and the wind field simulation data into a pre-trained first wind field prediction model to obtain the first wind field prediction data;

[0078] The prediction unit 403 is also used to input the first wind field prediction data and the second low-altitude wind field data into the pre-trained second wind field prediction model to obtain the second wind field prediction data.

[0079] The determining unit 404 is used to determine the wind field prediction result of the target area based on the second wind field prediction data.

[0080] Figure 5 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 5 As shown, the electronic device may include a processor 510, a communication interface 520, a memory 530, and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 can call logical instructions in the memory 530 to execute a method for predicting urban low-altitude micro-scale wind fields, which includes: acquiring low-altitude wind field data corresponding to the target area;

[0081] The low-altitude wind field data is divided into first low-altitude wind field data and second low-altitude wind field data, and the amount of data in the first low-altitude wind field data is less than the amount of data in the second low-altitude wind field data.

[0082] Obtain wind field simulation data for the target area; the wind field simulation data is obtained by simulating the target area using a nested coupling mode of mesoscale model WRF and CFD.

[0083] The first low-altitude wind field data and the wind field simulation data are input into the pre-trained first wind field prediction model to obtain the first wind field prediction data.

[0084] The first wind field prediction data and the second low-altitude wind field data are input into the pre-trained second wind field prediction model to obtain the second wind field prediction data.

[0085] Based on the second wind field prediction data, the wind field prediction result for the target area is determined.

[0086] Furthermore, the logical instructions in the aforementioned memory 530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0087] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the urban low-altitude microscale wind field prediction method provided by the above methods, the method comprising:

[0088] Obtain low-altitude wind field data corresponding to the target area;

[0089] The low-altitude wind field data is divided into first low-altitude wind field data and second low-altitude wind field data, and the amount of data in the first low-altitude wind field data is less than the amount of data in the second low-altitude wind field data.

[0090] Obtain wind field simulation data for the target area; the wind field simulation data is obtained by simulating the target area using a nested coupling mode of mesoscale model WRF and CFD.

[0091] The first low-altitude wind field data and the wind field simulation data are input into the pre-trained first wind field prediction model to obtain the first wind field prediction data.

[0092] The first wind field prediction data and the second low-altitude wind field data are input into the pre-trained second wind field prediction model to obtain the second wind field prediction data.

[0093] Based on the second wind field prediction data, the wind field prediction result for the target area is determined.

[0094] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the urban low-altitude microscale wind field prediction method provided by the above methods, the method comprising: acquiring low-altitude wind field data corresponding to a target area;

[0095] The low-altitude wind field data is divided into first low-altitude wind field data and second low-altitude wind field data, and the amount of data in the first low-altitude wind field data is less than the amount of data in the second low-altitude wind field data.

[0096] Obtain wind field simulation data for the target area; the wind field simulation data is obtained by simulating the target area using a nested coupling mode of mesoscale model WRF and CFD.

[0097] The first low-altitude wind field data and the wind field simulation data are input into the pre-trained first wind field prediction model to obtain the first wind field prediction data.

[0098] The first wind field prediction data and the second low-altitude wind field data are input into the pre-trained second wind field prediction model to obtain the second wind field prediction data.

[0099] Based on the second wind field prediction data, the wind field prediction result for the target area is determined.

[0100] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0101] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting urban low-altitude microscale wind fields, characterized in that, include: Obtain low-altitude wind field data corresponding to the target area; The low-altitude wind field data is divided into first low-altitude wind field data and second low-altitude wind field data, and the amount of data in the first low-altitude wind field data is less than the amount of data in the second low-altitude wind field data. Obtain wind field simulation data for the target area; The wind field simulation data is obtained by simulating the target area using a nested coupling model of mesoscale model WRF and CFD. The first low-altitude wind field data and the wind field simulation data are input into the pre-trained first wind field prediction model to obtain the first wind field prediction data. The first wind field prediction data and the second low-altitude wind field data are input into the pre-trained second wind field prediction model to obtain the second wind field prediction data. Based on the second wind field prediction data, the wind field prediction result for the target area is determined; The acquisition of wind field simulation data for the target area includes: Obtain a 3D solid model of the building complex corresponding to the target area; The mesoscale model WRF was used to simulate the low-altitude wind field data of the target area to obtain the initial wind field simulation results. The initial wind field simulation results are used as boundary conditions for CFD simulation. Based on these boundary conditions, a secondary simulation is performed on the three-dimensional solid model of the building complex to obtain the wind field simulation data of the target area. The process of obtaining the 3D solid model of the building complex corresponding to the target area includes: Acquire GIS building vector data and terrain elevation DEM data of the target area; the vector data includes the building's planar location, outline, floor area, and height; A three-dimensional solid model of the building complex is generated based on the GIS building vector data and the terrain elevation DEM data.

2. The method for predicting urban low-altitude microscale wind fields according to claim 1, characterized in that, The acquisition of low-altitude wind field data corresponding to the target area includes: Wind field data of the target area is obtained using weather radar, anemometer, or a six-component small weather station; the wind field data includes wind speed and wind direction.

3. The method for predicting urban low-altitude microscale wind fields according to claim 1, characterized in that, The first wind field prediction model and the second wind field prediction model are constructed using XGBoost model, CNN model, LSTM model, Transformer model, LightGBM model, or CatBoost model.

4. The method for predicting urban low-altitude microscale wind fields according to claim 1, characterized in that, Before dividing the low-altitude wind field data into first low-altitude wind field data and second low-altitude wind field data, the method further includes: The low-altitude wind field data corresponding to the acquired target area is preprocessed. The preprocessing includes data cleaning to remove outliers and noise from the data, and data normalization to unify wind field data of different magnitudes into the same numerical range.

5. An apparatus for performing the urban low-altitude microscale wind field prediction method according to claim 1, characterized in that, include: The acquisition unit is used to acquire low-altitude wind field data corresponding to the target area. A partitioning unit is used to divide the low-altitude wind field data into first low-altitude wind field data and second low-altitude wind field data, wherein the amount of data in the first low-altitude wind field data is less than the amount of data in the second low-altitude wind field data. The acquisition unit is also used to acquire wind field simulation data of the target area; The wind field simulation data is obtained by simulating the target area using a nested coupling model of the mesoscale model WRF and CFD. The prediction unit is used to input the first low-altitude wind field data and the wind field simulation data into a pre-trained first wind field prediction model to obtain the first wind field prediction data. The prediction unit is also used to input the first wind field prediction data and the second low-altitude wind field data into a pre-trained second wind field prediction model to obtain the second wind field prediction data. The determining unit is used to determine the wind field prediction result of the target area based on the second wind field prediction data.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the urban low-altitude microscale wind field prediction method as described in any one of claims 1 to 4.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the urban low-altitude microscale wind field prediction method as described in any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the urban low-altitude microscale wind field prediction method as described in any one of claims 1 to 4.

Images