Stratosphere wind field simulation method

Abstract

The invention discloses a stratosphere wind field simulation method, which comprises the following steps: taking stratosphere wind field sample data and a condition control vector as input, extracting features from the stratosphere wind field sample data through a condition encoder, and mapping the features to a low-dimensional hidden space vector; gradually adding random noise to the hidden space vector to obtain a noise hidden space vector; taking the condition control vector and the noise hidden space vector as input, predicting noise through a denoising neural network model of the hidden space diffusion model, and performing a reverse denoising process to obtain a denoised hidden space vector; inputting the denoising hidden space vector and the condition control vector into a condition decoder for decoding to obtain stratosphere wind field simulation data; and taking the stratospheric wind field simulation data as input, and obtaining stratospheric wind field simulation data with higher resolution through the space-time super-resolution network model. The stratosphere wind field simulation data can be efficiently generated.

Description

Technical Field

[0001] The present invention relates to the fields of deep learning and wind field simulation, and in particular to a stratospheric wind field simulation method. Background Art

[0002] As an important platform for high-resolution earth observation systems, stratospheric aerostats have the ability to perform tasks for a long time, in all weather conditions and in real time, and are of great strategic significance to promoting social, economic, national defense and scientific and technological development. With the continuous development of artificial intelligence technology, the flight trajectory of stratospheric aerostats with intelligent navigation capabilities has become controllable, and the market application prospects are broad, which is undoubtedly the leading direction of the future development of stratospheric aerostats.

[0003] The research on intelligent navigation technology of stratospheric aerostats relies on a large amount of flight test data. However, stratospheric aerostats are expensive. It is slow and expensive to conduct stratospheric flight experiments to obtain flight data for intelligent navigation of stratospheric aerostats. In extreme cases, stratospheric aerostats may need weeks of maneuvering flights to recover from control decision errors. Therefore, it is very important to establish a simulation environment to train the intelligent navigation controller of stratospheric aerostats. Through flight experiments in a simulated environment, the training cost of the intelligent navigation controller can be greatly reduced, while saving a lot of time.

[0004] In constructing a flight simulation environment for stratospheric aerostats, the simulation of stratospheric wind fields is a key link. The simulated stratospheric wind field must not only conform to the characteristics of the real stratospheric wind field, but also have randomness and temporal and spatial correlation with the real stratospheric wind field. Considering the need for a large number of simulated flight experiments, when generating stratospheric wind field simulation data, it is necessary not only to balance the simulation quality and diversity, but also to take into account the efficiency of stratospheric wind field simulation.

[0005] Currently, there are three main methods for simulating wind fields: one is the numerical simulation method based on computational fluid dynamics (CFD), the second is to construct a simulated wind field based on spectral representation, and the third is to construct a simulated wind field based on deep learning methods.

[0006] The numerical simulation method based on CFD has many advantages in simulating the fine flow field of the boundary layer under complex terrain conditions, such as short calculation time, high calculation efficiency, and the ability to simulate the characteristics of the real wind field. However, since this method needs to consider physical processes of multiple scales to simulate the wind field, it is necessary to calculate various fluid dynamics equations when using this method to simulate the wind field. The calculation complexity is high and requires a lot of computing resources and time. Moreover, the characteristics of the wind field generated in the end are difficult to control, and the parameters need to be adjusted repeatedly to obtain a suitable simulated wind field. The numerical simulation method based on CFD first needs to set initial conditions and boundary conditions. Secondly, the numerical simulation method based on CFD usually involves a large amount of numerical calculations to generate a simulated wind field. Especially when a large amount of stratospheric wind field simulation data needs to be generated, the efficiency of the numerical simulation method based on CFD is greatly reduced.

[0007] The simulated wind field is constructed based on the spectral representation method, which mainly includes Fourier synthesis method, orthogonal decomposition method, numerical filtering method, etc. The power spectrum of a specific wind field is discretized into multiple segments and then combined with the random sequence synthesis method to generate a simulated wind field, which can meet the requirements of turbulence, spectral characteristics, etc. for wind field simulation, and is particularly suitable for the simulation of a steady wind field. In order to improve the efficiency of wind field simulation, this method usually needs to integrate the fast Fourier transform (FFT) technology. A key challenge of integrating FFT technology is how to effectively decouple the time-frequency coupled functions. Currently, existing methods include proper orthogonal decomposition (POD), wavelet decomposition, and non-negative matrix decomposition. However, with the significant increase in the number of simulation points, the computational complexity of these decoupling processes will expand dramatically. Moreover, when the coherence function of the simulated wind field has time-varying characteristics, a large number of spectral matrix decomposition calculations need to be performed additionally. These additional calculations further weaken the overall efficiency of wind field simulation. In addition, this method is usually based on limited wind field characteristics. Considering the complexity and variability of wind field characteristics in reality, there is always a certain gap between the simulated wind field characteristics generated by such methods and the real wind field characteristics. The simulated wind field constructed based on the spectral representation is mainly used to generate a simulated wind field that meets the characteristics of a specific wind field, and lacks universality. For the task of generating a large amount of stratospheric wind field simulation data, it is necessary not only to meet the efficiency requirements, but also to require the generated stratospheric wind field simulation data to be diverse.

[0008] The simulated wind field is constructed based on the deep learning method. It is mainly based on generative networks such as adversarial generative networks (GAN) or variational autoencoders (VAE) to generate stratospheric wind field simulation data. However, GAN is prone to unstable effects and mode collapse when generating stratospheric wind field simulation data. The training process of GAN involves two networks, the generator and the discriminator, which are trained in a competitive manner. This adversarial training makes the training process of GAN very unstable, prone to oscillation and non-convergence, which may cause GAN to fail to stably generate samples that meet the expectations when generating stratospheric wind field simulation data. GAN may have mode collapse problems during training, that is, the generator can only generate a limited number of samples and cannot cover the entire data distribution. In the stratospheric wind field simulation data task, this may lead to the lack of diversity of the generated stratospheric wind field simulation data samples, which cannot accurately reflect the complexity and variability of the actual stratospheric wind field. VAE tends to learn the potential representation of the input data during training and try to generate samples similar to the training data. However, stratospheric wind field simulation data is a complex and changeable system, and its data distribution may be highly complex and uncertain. VAE may not be able to fully capture this complex distribution, resulting in a large difference between the generated stratospheric wind field simulation data samples and the actual stratospheric wind field conditions. Furthermore, since the training goal of VAE is to minimize the error between the output data and the input data, it tends to generate samples that are closer to the training data, which may lead to a lack of sufficient diversity in the generated stratospheric wind field simulation data samples.

[0009] In view of the shortcomings of existing wind field simulation methods, it is of great significance to study and develop a more accurate and efficient wind field simulation method. Summary of the invention

[0010] In view of the deficiencies in the prior art, the present application provides a stratospheric wind field simulation method that can simultaneously meet the accuracy and efficiency of stratospheric wind field simulation.

[0011] The technical solutions provided in this application are:

[0012] In a first aspect, the present application provides a stratospheric wind field simulation method, comprising:

[0013] Step S1: construct a conditional control network, input the conditional information for controlling the stratospheric wind field into the conditional control network, and obtain a conditional control vector;

[0014] Step S2: taking the stratospheric wind field sample data and the conditional control vector as input, extracting features from the stratospheric wind field sample data through the conditional encoder in the pre-trained encoder-decoder model, and mapping it to a low-dimensional latent space vector; wherein the encoder-decoder model includes two parts: a conditional encoder and a conditional decoder;

[0015] Step S3: gradually add random noise to the latent space vector (gradually diffuse the latent space vector) to obtain a noisy latent space vector; take the conditional control vector and the noisy latent space vector as input, predict the noise through a pre-trained latent space diffusion model (Latent Diffusion Model, LDM) denoising neural network model, perform a reverse denoising process, and obtain a denoised latent space vector; input the denoised latent space vector and the conditional control vector into the conditional decoder in the pre-trained encoder-decoder model for decoding, and obtain the first stratospheric wind field simulation data;

[0016] Step S4: taking the first stratospheric wind field simulation data as input, and obtaining second stratospheric wind field simulation data through a pre-trained spatiotemporal super-resolution network model; wherein the resolution of the second stratospheric wind field simulation data is higher than the resolution of the first stratospheric wind field simulation data.

[0017] Based on the spatiotemporal super-resolution network model, high-resolution stratospheric wind field simulation data can be obtained from low-resolution stratospheric wind field simulation data. Therefore, the present application can obtain high-resolution stratospheric wind field simulation data.

[0018] In a possible implementation, the conditional control network in step S1 includes a numerical coding layer, a non-numerical coding layer and three linear layers, wherein the numerical coding layer is used to encode numerical conditions, and the non-numerical coding layer is used to encode non-numerical conditions, and the outputs of the numerical coding layer and the non-numerical coding layer are concatenated and input into the three linear layers to obtain the conditional control vector; among the three linear layers, the first linear layer serves as an input layer to receive the output of the numerical coding layer and the non-numerical coding layer, the second linear layer serves as a hidden layer, and the third linear layer serves as an output layer to output the conditional control vector.

[0019] Among them, the numerical conditions include time, etc.; the non-numerical conditions include the initial state of the wind farm.

[0020] In a possible implementation, the conditional encoder includes a plurality of groups of spatiotemporal downsampling modules and spatiotemporal attention modules connected in sequence; each group of spatiotemporal downsampling modules and spatiotemporal attention modules includes a spatiotemporal downsampling module and a spatiotemporal attention module connected in sequence;

[0021] Each spatiotemporal downsampling module includes a spatial downsampling unit and a temporal downsampling unit connected in sequence;

[0022] The spatial downsampling unit includes a plurality of three-dimensional spatial convolutional layers connected in sequence, which are used to process the spatial dimension information of the stratospheric wind field sample data; the temporal downsampling unit includes a one-dimensional temporal convolutional layer, which is used to process the temporal dimension information of the stratospheric wind field sample data; each convolutional layer is followed by a residual layer;

[0023] Each spatiotemporal attention module includes a sequentially connected spatial attention layer and a temporal attention layer, which are used to process the spatial dimension information and the temporal dimension information of the stratospheric wind field sample data respectively;

[0024] The sequential connection means that the output of the previous module, layer or unit is used as the input of the next module or layer;

[0025] Since the stratospheric wind field sample data contains both spatial dependencies and temporal dependencies, the method described in the present invention performs attention calculations on space and time respectively. The spatial attention layer only processes the spatial dimension information of the stratospheric wind field sample data, and the temporal attention layer only processes the temporal dimension information of the stratospheric wind field sample data. While simplifying the calculation complexity, it can also capture the spatiotemporal dependencies of the stratospheric wind field sample data.

[0026] The conditional encoder receives the conditional control vector and the stratospheric wind field sample data as input, and the stratospheric wind field sample data is input into the first three-dimensional spatial convolution layer in the conditional encoder; the other three-dimensional spatial convolution layers except the first three-dimensional spatial convolution layer in the conditional encoder, and the one-dimensional temporal convolution layer, combine the output of the previous module, layer or unit and the conditional control vector as input;

[0027] In one possible implementation, the conditional encoder includes two sets of spatiotemporal downsampling modules and a spatiotemporal attention module. The spatial downsampling unit includes two three-dimensional spatial convolutional layers. The following details the input-output relationship between each module, layer, and unit.

[0028] The conditional encoder receives the conditional control vector and the stratospheric wind field sample data as input. The stratospheric wind field sample data is first input into the first spatiotemporal downsampling module of the conditional encoder, and is first processed by the first three-dimensional spatial convolution layer of the spatial downsampling unit, and then passes through the residual layer. The output obtained is combined with the conditional control vector and input into the second three-dimensional spatial convolution layer and the second residual layer to obtain the output of the spatial downsampling unit. The output of the spatial downsampling unit is combined with the conditional control vector and input into the time downsampling unit to obtain the output of the first spatiotemporal downsampling module. The output of the first spatiotemporal downsampling module is input into the first spatiotemporal attention module of the conditional encoder, first passes through the spatial attention layer of the first spatiotemporal attention module, and then passes through the time attention layer of the first spatiotemporal attention module to obtain the output of the first spatiotemporal attention module. The output of the first spatiotemporal attention module is input into the second spatiotemporal downsampling module of the conditional encoder to obtain the output of the second spatiotemporal downsampling module, and the output of the second spatiotemporal downsampling module is input into the second spatiotemporal attention module of the conditional encoder to obtain the output of the conditional encoder, that is, the latent space vector. The process of processing data by the second spatiotemporal downsampling module and the second spatiotemporal attention module is the same as that of the first spatiotemporal downsampling module and the first spatiotemporal attention module.

[0029] The conditional decoder comprises a plurality of groups of sequentially connected spatiotemporal upsampling modules and spatiotemporal attention modules; each group of spatiotemporal upsampling modules and spatiotemporal attention modules comprises a sequentially connected spatiotemporal upsampling module and a spatiotemporal attention module;

[0030] The spatiotemporal upsampling module includes a spatial upsampling unit and a temporal upsampling unit; the spatial upsampling unit includes a plurality of three-dimensional spatial convolutional layers connected in sequence, which are used to perform upsampling operations on the spatial information of the stratospheric wind field sample data; the temporal upsampling unit includes a one-dimensional temporal convolutional layer, which is used to perform upsampling operations on the temporal information of the stratospheric wind field sample data; a residual layer is arranged behind each convolutional layer; and four-dimensional spatiotemporal stratospheric wind field simulation data is obtained through the spatiotemporal upsampling module.

[0031] In some embodiments, the conditional decoder includes two groups of spatiotemporal upsampling modules and a spatiotemporal attention module. The spatial upsampling unit includes two three-dimensional spatial convolutional layers. The input-output relationship between each module, layer and unit is described in detail below.

[0032] The conditional decoder accepts the conditional control vector and the denoised latent space vector as inputs. The denoised latent space vector is first input into the first three-dimensional spatial convolution layer of the spatial upsampling unit of the first spatiotemporal upsampling module of the conditional decoder, passes through the residual layer, and then is input into the second three-dimensional spatial convolution layer and the second residual layer in combination with the conditional control vector, and then is processed by the temporal upsampling unit to obtain the output of the first spatiotemporal upsampling module, and the output of the first spatiotemporal upsampling module is input into the first spatiotemporal attention module of the conditional decoder, and the obtained output is input into the second spatiotemporal upsampling module of the conditional decoder to obtain the output of the second spatiotemporal upsampling module, which is input into the second spatiotemporal attention module of the conditional decoder to obtain the output of the conditional decoder, i.e., the first stratospheric wind field simulation data. The process of processing data by the second spatiotemporal upsampling module and the second spatiotemporal attention module is the same as that of the first spatiotemporal upsampling module and the first spatiotemporal attention module.

[0033] In combination with the above embodiments, the encoder-decoder model may include two spatiotemporal downsampling modules and two spatiotemporal upsampling modules, each downsampling / upsampling module is followed by a spatiotemporal attention module.

[0034] In one possible implementation, the pre-training process of the encoder-decoder model includes:

[0035] Step S21: constructing an encoder-decoder model and initializing parameters of the encoder-decoder model;

[0036] Step S22: inputting the condition information for controlling the stratospheric wind field into the conditional control network to obtain a conditional control vector; inputting the stratospheric wind field sample data and the conditional control vector into the encoder-decoder model to obtain stratospheric wind field simulation data generated by the encoder-decoder model;

[0037] Step S23: calculating a first loss function value based on the stratospheric wind field simulation data and the stratospheric wind field sample data;

[0038] Step S24: updating the parameters of the encoder-decoder model based on back propagation according to the first loss function value;

[0039] Step S22: Iterate steps S22 to S24 until the iteration end condition is reached to obtain a pre-trained encoder-decoder model.

[0040] In a possible implementation, the first loss function in step S23 is calculated using the following formula:

[0041]

[0042] Among them, Loss(r,x) is the first loss function, r represents the generated stratospheric wind field simulation data, x represents the stratospheric wind field sample data, mse(r,x) represents the mean square error between r and x, σ represents the variance of the generated stratospheric wind field simulation data, KL(r,x) represents the KL divergence between r and x, and γ represents the weight of the KL divergence.

[0043] The mean square error is calculated by the following formula:

[0044]

[0045] Where N represents the number of grid points in a stratospheric wind field, r i represents the wind speed value of the i-th grid point in the generated stratospheric wind field simulation data, x i Represents the wind speed value of the i-th grid point in the stratospheric wind field sample data.

[0046] The KL divergence is calculated by the following formula:

[0047]

[0048] Among them, μ r and σ r Respectively represent the mean and variance of the generated stratospheric wind field simulation data, μ x and σ x They respectively represent the mean and variance of the corresponding stratospheric wind field sample data used for training.

[0049] The above loss function combines L2 loss (MSE) and KL divergence. L2 loss focuses on the specific difference between stratospheric wind field simulation data and stratospheric wind field sample data, while KL divergence focuses on the difference between the probability distribution of stratospheric wind field simulation data and the probability distribution of stratospheric wind field sample data. This combination helps the model strike a balance between prediction accuracy and probability distribution similarity.

[0050] In a possible implementation, the denoising neural network model of the latent space diffusion model in step S3 includes a downsampling module, an intermediate module and an upsampling module connected in sequence;

[0051] The downsampling module comprises a plurality of downsampling units connected in sequence;

[0052] Using multiple downsampling units can gradually reduce the temporal and spatial resolution of the data while retaining key feature information for easy subsequent processing. Multiple downsampling units are identical in structure but have different parameters to better adapt to the characteristics of the data at different stages.

[0053] The downsampling unit includes a three-dimensional spatial convolution layer, a one-dimensional temporal convolution layer, a residual layer, and a spatiotemporal attention module connected in sequence, which are used to process the spatial dimension information and temporal dimension information of the stratospheric wind field sample data. The three-dimensional spatial convolution layer is responsible for processing the spatial dimension information, and the one-dimensional temporal convolution layer focuses on the feature extraction of the temporal dimension. The residual layer is introduced to enhance the feature propagation capability of the network and reduce information loss. The spatiotemporal attention module further enhances the feature selection capability of the model in both spatial and temporal dimensions. The spatiotemporal attention module has the same structure as the spatiotemporal attention module in the encoder-decoder model.

[0054] The intermediate module includes a spatiotemporal attention module, and a residual layer is provided before and after the spatiotemporal attention module;

[0055] The upsampling module includes a plurality of upsampling units connected in sequence, each of which includes a four-dimensional spatiotemporal convolution module and a spatiotemporal attention module connected in sequence; the four-dimensional spatiotemporal convolution module includes a three-dimensional spatial convolution layer, a one-dimensional temporal convolution layer and a residual layer connected in sequence.

[0056] Multiple upsampling units are used to gradually restore the spatial and temporal resolution of the data lost during the downsampling process while maintaining or enhancing key features. Similar to the downsampling unit, each upsampling unit has the same structure but different parameters to adapt to the characteristic changes of the data during the inverse transformation process. The upsampling unit realizes an effective mapping from low-resolution stratospheric simulation data to high-resolution stratospheric simulation data while maintaining the spatial and temporal consistency of the data.

[0057] In a possible implementation, the downsampling module includes two downsampling units; the intermediate module includes two residual layers; and the upsampling module includes two upsampling units. The input-output relationship between each module, layer, and unit is described in detail below.

[0058] The denoising neural network model of the latent space diffusion model takes the conditional control vector and the noise latent space vector as input, the noise latent space vector is first input into the first down-sampling module of the denoising neural network model, passes through the three-dimensional spatial convolution layer, the one-dimensional temporal convolution layer and the residual layer of the down-sampling module, and then passes through the spatiotemporal attention module to obtain the output of the first down-sampling module, and is input into the second down-sampling module in combination with the conditional control vector, wherein the operation process of the second down-sampling module is the same as that of the first down-sampling module; the output of the second down-sampling module is input into the intermediate module, first passes through the first residual layer of the intermediate module, then is processed by the spatiotemporal attention module of the intermediate module, and finally passes through the second residual layer of the intermediate module to obtain the output of the intermediate module; the output of the intermediate module is input into the first up-sampling module of the denoising neural network model, first passes through the three-dimensional spatial convolution layer, the one-dimensional temporal convolution layer and the residual layer of the up-sampling module, and then passes through the spatiotemporal attention module to obtain the output of the first up-sampling module, and the output of the first up-sampling module is input into the second up-sampling module of the denoising neural network model to obtain the output of the second up-sampling module, i.e., the noise predicted by the denoising neural network model. The process of processing data in the second upsampling module of the denoising neural network model is the same as that in the first upsampling module of the denoising neural network model.

[0059] In a possible implementation, the denoising neural network model pre-training process of the latent space diffusion model includes:

[0060] Step S31: constructing a denoising neural network model of a latent space diffusion model and initializing parameters of the denoising neural network model;

[0061] Step S32: inputting the condition information for controlling the stratospheric wind field into the conditional control network to obtain a conditional control vector, inputting the stratospheric wind field sample data and the conditional control vector into the encoder part of the encoder-decoder model to obtain a latent space vector;

[0062] Step S33: gradually adding random noise to the latent space vector to obtain a noisy latent space vector; inputting the conditional control vector and the noisy latent space vector into a denoising neural network of a latent space diffusion model to obtain predicted noise, and performing a reverse denoising process based on the predicted noise to obtain a denoised latent space vector; inputting the denoised latent space vector and the conditional control vector into the conditional decoder for decoding to obtain stratospheric wind field simulation data;

[0063] Step S34: Calculating the second loss function value based on the denoising neural network and the stratospheric wind field simulation data obtained by decoding;

[0064] Step S35: updating the parameters of the denoising neural network model based on back propagation according to the second loss function value;

[0065] Step S36: Iterate steps S33 to S35 until the iteration end condition is reached to obtain a pre-trained encoder-decoder model.

[0066] In a possible implementation, the second loss function value in step S34 is calculated using the following formula:

[0067]

[0068] Among them, Loss represents the second loss function, ε t represents the random noise added in step S33, T represents the maximum number of steps, ε θ (X t , t) represents the predicted noise obtained by the denoising neural network model in step S33, Represents ε t -ε θ (X t ,t), γ represents the proportion of the difference between the stratospheric wind field simulation data and the stratospheric wind field sample data in the loss function, O represents the stratospheric wind field simulation data decoded by the conditional decoder, and Y represents the corresponding stratospheric wind field sample data used for training.

[0069] In a possible implementation, the spatiotemporal super-resolution network model in step S4 includes an initial feature extraction module, a feature fusion module and a reconstruction module, wherein the initial feature extraction module includes a first feature extraction unit, a downsampling layer and a second feature extraction unit connected in sequence; the first feature extraction unit and the second feature extraction unit both include a three-dimensional spatial convolution layer, a spatial attention layer and a residual layer connected in sequence; the feature fusion module includes a first feature fusion processing unit and a second feature fusion processing unit connected in sequence; the first feature fusion processing unit and the second feature fusion processing unit include two sub-processing units, each of which has They all include a four-dimensional spatiotemporal convolution module and a spatiotemporal attention module connected in sequence; the second feature fusion processing unit includes a three-dimensional spatial convolution layer, a spatiotemporal attention module and a residual layer connected in sequence; the output end of the initial feature extraction module is connected to the input end of the second feature fusion processing unit in the feature fusion module; the four-dimensional spatiotemporal convolution module includes a three-dimensional spatial convolution layer, a one-dimensional temporal convolution layer and a residual layer connected in sequence; the output end of the feature fusion module is connected to the input end of the reconstruction module; the reconstruction module includes a four-dimensional spatiotemporal convolution module, a spatiotemporal attention module, an upsampling layer, a residual layer and a spatiotemporal attention module connected in sequence.

[0070] In a possible implementation, the pre-training process of the spatiotemporal super-resolution network model includes the following steps:

[0071] Step S41: constructing a spatiotemporal super-resolution network model and initializing parameters of the spatiotemporal super-resolution network model;

[0072] Step S42: inputting the three-dimensional wind field data of the first time point of the first stratospheric wind field sample data into the initial feature extraction module of the spatiotemporal super-resolution network model to obtain an initial feature vector I0;

[0073] Step S43: inputting the first stratospheric wind field sample data into the first feature fusion processing unit of the feature fusion module of the spatiotemporal super-resolution network model to obtain a second feature vector I1, concatenating the initial feature vector I0 and the second feature vector I1, and inputting the concatenated data into the second feature fusion processing unit of the feature fusion module to obtain a fused feature vector I2;

[0074] Step S44: inputting the fused feature vector I2 into the reconstruction module of the spatiotemporal super-resolution network model to obtain reconstructed third stratospheric wind field simulation data;

[0075] Step S45: calculating the L2 loss based on the second stratospheric wind field sample data corresponding to the first stratospheric wind field sample data and the third stratospheric wind field simulation data reconstructed by the spatiotemporal super-resolution network model; wherein the resolution of the third stratospheric wind field sample data is higher than the resolution of the first stratospheric wind field sample data; and the second stratospheric wind field sample data is the high-resolution stratospheric wind field sample data that actually corresponds to the first stratospheric wind field sample data;

[0076] Step S46: updating the parameters of the spatiotemporal super-resolution network model based on back propagation according to the L2 loss value;

[0077] Step S47: Iterate steps S42 to S46 until the iteration end condition is reached to obtain a pre-trained spatiotemporal super-resolution network model.

[0078] In a second aspect, the present application provides an electronic device, including: a memory and a processor;

[0079] The memory is used to store computer programs;

[0080] The processor is used to call the computer program to execute the method as described above.

[0081] In a third aspect, the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed on an electronic device, the electronic device implements the method as described above.

[0082] In a fourth aspect, the present application provides a computer program product, including a computer program, and when the computer program is executed on an electronic device, the electronic device implements the method as described above.

[0083] The specific implementation methods of the second to fourth aspects of the present application can refer to the implementation methods of the first aspect, which will not be repeated here.

[0084] The present invention is based on a latent space diffusion model for generating a simulated wind field, and the model effectively combines the generation capability of the diffusion model with the spatiotemporal characteristics of a real wind field. By using the latent space diffusion model to directly generate a simulated wind field, the complex spatiotemporal distribution characteristics of wind field data are learned, and various fluid dynamics equations are avoided as in wind field simulation based on a CFD method. At the same time, there is no need to perform multiple spectral matrix decompositions and large amounts of calculations when simulating a wind field based on a spectral representation method. The method of the present invention reduces the complexity and amount of calculations of the simulated wind field by learning the complex spatiotemporal distribution characteristics of wind field data, thereby improving the simulation efficiency, while meeting the accuracy and efficiency of stratospheric wind field simulation.

[0085] The method described in the present invention constructs a conditional control network based on a latent space diffusion model, so that the latent space diffusion model can generate simulated wind fields of different scenarios according to different input conditions, fuses numerical condition information and non-numerical condition information to obtain a conditional control vector, which is used to control the inverse denoising process of the encoder-decoder model and the diffusion model to generate simulated wind field data that meets the specified conditions.

[0086] The method of the present invention constructs a spatiotemporal super-resolution network model. The resolution of the simulated wind field data generated based on the latent space diffusion model is the same as the resolution of the original stratospheric wind field sample data used for training. The resolution of the original stratospheric wind field sample data is generally low. When the flight simulation of the stratospheric airship requires high-resolution wind field data, it is necessary to interpolate on the basis of the simulated wind field data, which will lead to cumulative errors and affect the effect of wind field simulation. Most of the existing super-resolution models are designed for image data, and the processed data is two-dimensional data. The super-resolution operation of video data also adds a time dimension on the basis of two-dimensional image data. The existing super-resolution processing of wind field data or downscaling of wind field data is only for wind speed variables at a single height. The stratospheric wind field sample data includes data at different heights, and its data dimensions include three-dimensional space and time dimensions. The spatiotemporal super-resolution network model designed by the method of the present invention improves the resolution on the basis of the simulated wind field data generated by the latent space diffusion model in order to improve the horizontal resolution of the wind field data and expand the wind field data in the time dimension, and can obtain a simulated wind field with a higher resolution and a smaller time scale as needed.

[0087] The present invention does not need to set initial conditions and boundary conditions for generating stratospheric wind field simulation data based on the latent space diffusion model, and the latent space diffusion model after training can directly generate stratospheric wind field simulation data via Gaussian noise, and the complexity and diversity of the generated data are controlled by adjusting parameters and training process, which greatly improves the generation efficiency in tasks that need to generate a large amount of stratospheric wind field simulation data. And the generation of stratospheric wind field simulation data based on the latent space diffusion model directly models and predicts complex four-dimensional spatiotemporal stratospheric dynamic wind field data, captures the spatial characteristics and time evolution characteristics of the stratospheric wind field, learns the inherent laws and distribution laws of the data, rather than only learning the characteristics of a specific stratospheric wind field, and can be applied to stratospheric wind field simulation data generation tasks in different regions and seasons.

[0088] The present invention uses a latent space diffusion model to generate stratospheric wind field simulation data. The latent space diffusion model can learn the intrinsic representation of stratospheric wind field sample data by gradually adding noise and denoising process in the latent space, so as to better capture the complex distribution of stratospheric wind field sample data. Compared with VAE and GAN, the latent space diffusion model has higher flexibility in modeling high-dimensional, nonlinear and complex distributed data. The latent space diffusion model is generated by a step-by-step denoising process, which helps to retain more original data features. In addition, the latent space diffusion model can maintain a high diversity when generating samples, avoiding the mode collapse problem that may occur in GAN. The training process of GAN is usually unstable because it involves adversarial training of two networks. In contrast, the training process of the latent space diffusion model is more stable because it does not need to optimize the generator and the discriminator at the same time. Although VAE is relatively stable in training, it is not as effective as the latent space diffusion model when processing complex data.

[0089] The present invention uses a latent space diffusion model to learn the distribution of the stratospheric wind field in three-dimensional space and its changes over time through stratospheric wind field data to simulate the stratospheric wind field. The present invention can provide important support for establishing a stratospheric simulation environment and for training intelligent navigation controllers for stratospheric aerostats. It has the following advantages:

[0090] (1) High simulation accuracy: By introducing spatial convolution layer, temporal convolution layer and spatiotemporal attention layer, the temporal and spatial information of stratospheric wind field sample data are processed respectively. The latent space diffusion model can better capture the spatiotemporal variation characteristics of the stratospheric wind field, thereby improving the accuracy and reliability of the latent space diffusion model in generating stratospheric wind field simulation data. The introduction of super-resolution network makes the method based on the latent space diffusion model to generate stratospheric wind field simulation data not limited to the resolution of the stratospheric wind field sample data used for training, and can obtain higher resolution stratospheric wind field simulation data;

[0091] (2) High computational efficiency: This method directly generates simulated wind fields from Gaussian noise, avoiding the use of large-scale numerical models and the calculation of various fluid dynamics equations. This allows the model to complete large-scale simulations in a shorter time, improving computational efficiency and response speed. At the same time, DDIM is used to accelerate sampling. Compared with typical diffusion models such as DDPM, the method can generate the same high-quality stratospheric wind field simulation data with fewer steps.

[0092] (3) Strong scalability: This method is not limited to a specific region or time scale. It has the ability to adapt to different regions and time scales and can be widely used in stratospheric wind field simulation under various environmental conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0093] Figure 1 A flowchart of an embodiment of the present invention;

[0094] Figure 2 A conditional control network structure diagram of an embodiment of the present invention;

[0095] Figure 3 A structural diagram of a conditional encoder according to an embodiment of the present invention;

[0096] Figure 4 A denoising neural network structure diagram of a latent space diffusion model according to an embodiment of the present invention;

[0097] Figure 5 A schematic diagram of a pre-training process of a latent space diffusion model according to an embodiment of the present invention;

[0098] Figure 6 A diagram showing a super-resolution network model structure according to an embodiment of the present invention;

[0099] Figure 7 A comparative analysis diagram of stratospheric wind field simulation data and real wind field generated by using latent space diffusion model in one embodiment of the present invention;

[0100] Figure 8 This is a visualization diagram of stratospheric wind field sample data used for training a spatiotemporal super-resolution network model in an embodiment of the present invention; wherein, Figure 8 (a) shows the visualization of low-resolution stratospheric wind field sample data obtained after artificial coarsening. Figure 8 (b) is a visualization of high-resolution stratospheric wind field sample data before coarsening;

[0101] Fig. 9 This is a rendering of high-resolution stratospheric wind field simulation data generated using a spatiotemporal super-resolution network model in an embodiment of the present invention. DETAILED DESCRIPTION

[0102] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and implementation cases. It should be understood that the specific implementation cases described herein are used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in each embodiment of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0103] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application 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 comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0104] In addition, the terms "installed", "set", "provided with", "connected", "connected", and "socketed" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral structure; it can be a mechanical connection or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be an internal connection between two devices, elements, or components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0105] Reference Figures 1 to 8 The present invention provides a method for generating stratospheric wind field simulation data based on a latent space diffusion model, and its flow chart is as follows Figure 1 shown.

[0106] Using the method provided by the present invention to simulate the stratospheric wind field requires collecting stratospheric wind field sample data for training the neural network. Optionally, this embodiment takes the stratosphere in Hunan area (longitude range: 108°E~114°E, latitude range: 24°N~30°N) as an example, and collects part of the stratospheric wind field sample data in the fifth generation atmospheric reanalysis data set (ECMWFReanalysis v5, ERA5) from the European Centre for Medium-Range Weather Forecasts (ECMWF) in this area (the maximum pressure is 150hPa, the minimum pressure is 50hPa, and there are 5 different pressure levels).

[0107] The collected stratospheric wind field sample data are processed. In this embodiment, the stratospheric wind field sample data is divided into 29 parts in the longitude and latitude directions, and into 5 different levels in the height direction. The time period is 24 hours. The wind field data is expressed in the form of meridional wind speed u and zonal wind speed v, and the dimension of the data is 2. Finally, a four-dimensional spatiotemporal stratospheric dynamic wind field data set for training the stratospheric wind field simulation data generation model is constructed. The data set is data of (29, 29, 5, 24, 2) dimensions, that is, the simulated wind field is divided into a three-dimensional grid of (29, 29, 5), and is divided into 24 different time points in time. The wind speed is divided into two components, the meridional wind speed and the zonal wind speed. Optionally, this embodiment stores the processed four-dimensional stratospheric dynamic wind field in the format of a pickle file.

[0108] In addition, in order to train the super-resolution network model, the collected data are first interpolated to obtain a second stratospheric wind field sample data set with a data dimension of (32, 32, 5, 24, 2) to make downsampling and upsampling operations more convenient. Then the collected stratospheric wind field sample data are coarsened to obtain a first stratospheric wind field sample data set with a data dimension of (16, 16, 5, 24, 2). The low-resolution stratospheric wind field sample data and its corresponding second stratospheric wind field sample data are used as training data sets to train the super-resolution network model.

[0109] Specifically, an embodiment of the present invention provides a stratospheric wind field simulation method, comprising the following steps:

[0110] Step S1: construct a conditional control network, input the conditional information for controlling the stratospheric wind field into the conditional control network, and obtain a conditional control vector.

[0111] In some embodiments, in order to better encode the conditions for controlling the stratospheric wind field, a conditional control network is designed, and the network structure is as follows: Figure 2 As shown, it includes two coding layers and three linear layers, wherein a numerical coding layer is used to encode numerical conditions such as time, etc., and a non-numerical coding layer is used to encode non-numerical conditions such as the initial state of the wind field, etc. The outputs of the two coding layers are spliced ​​and input into the three linear layers to obtain the conditional control vector. Among the three linear layers, the first linear layer serves as an input layer to receive the outputs of the numerical coding layer and the non-numerical coding layer, the second linear layer serves as a hidden layer, and the third linear layer serves as an output layer to output the conditional control vector.

[0112] Step S2: Taking the stratospheric wind field sample data and the conditional control vector as input, extracting features from the stratospheric wind field sample data through the conditional encoder in the pre-trained encoder-decoder model, and mapping it to a low-dimensional latent space vector; wherein the encoder-decoder model includes two parts: a conditional encoder and a conditional decoder.

[0113] In some embodiments, the encoder-decoder model network structure diagram is as follows Figure 3 As shown, by using a three-dimensional spatial convolution layer to process the spatial dimension information of the original stratospheric wind field sample data, and using a one-dimensional convolution layer to process the time dimension information of the original stratospheric wind field sample data, the encoder model first processes the spatial dimension information of the input original stratospheric wind field sample data, and then processes the result obtained by the three-dimensional spatial convolution layer as the input of the time convolution layer, thereby obtaining an encoder model that can separate the time and space information, and can respectively extract the spatial dimension features and the time dimension features of the original stratospheric wind field sample data, and can learn the distribution characteristics of the stratospheric wind field while learning its dynamic change characteristics.

[0114] The pre-training process of the encoder model includes the following steps:

[0115] Step S21: constructing an encoder-decoder model and initializing parameters of the encoder-decoder model;

[0116] Step S22: inputting the condition information for controlling the stratospheric wind field into the conditional control network to obtain a conditional control vector; inputting the stratospheric wind field sample data and the conditional control vector into the encoder-decoder model to obtain stratospheric wind field simulation data generated by the encoder-decoder model;

[0117] Step S23: calculating a first loss function value based on the stratospheric wind field simulation data and the stratospheric wind field sample data;

[0118] Step S24: updating the parameters of the encoder-decoder model based on back propagation according to the first loss function value;

[0119] Step S22: Iterate steps S22 to S24 until the iteration end condition is reached to obtain a pre-trained encoder-decoder model.

[0120] In some embodiments, the first loss function used to train the encoder-decoder model is calculated using the following formula:

[0121]

[0122] Among them, Loss(r,x) is the first loss function, r represents the generated stratospheric wind field simulation data, x represents the stratospheric wind field sample data, mse(r,x) represents the mean square error between r and x, σ represents the variance of the generated stratospheric wind field simulation data, KL(r,x) represents the KL divergence between r and x, and γ represents the weight of the KL divergence.

[0123] The mean square error is calculated by the following formula:

[0124]

[0125] Where N represents the number of grid points in a stratospheric wind field, r i represents the wind speed value of the i-th grid point in the generated stratospheric wind field simulation data, x i Represents the wind speed value of the i-th grid point in the stratospheric wind field sample data.

[0126] The KL divergence is calculated by the following formula:

[0127]

[0128] Among them, μ r and σ r Respectively represent the mean and variance of the generated stratospheric wind field simulation data, μ x and σ x They respectively represent the mean and variance of the corresponding stratospheric wind field sample data used for training.

[0129] Step S3: gradually add random noise to the latent space vector (gradually diffuse the latent space vector) to obtain a noisy latent space vector; take the conditional control vector and the noisy latent space vector as input, predict the noise through a denoising neural network model of a pre-trained latent space diffusion model, perform a reverse denoising process, and obtain a denoised latent space vector; input the denoised latent space vector and the conditional control vector into a conditional decoder in a pre-trained encoder-decoder model for decoding, and obtain the first stratospheric wind field simulation data.

[0130] In some embodiments, the denoising neural network model of the latent space diffusion model in step S3 includes a downsampling module, an intermediate module and an upsampling module. The specific network structure is as follows: Figure 4 As shown, the pre-training process includes the following steps:

[0131] Step S31: constructing a denoising neural network model of a latent space diffusion model and initializing parameters of the denoising neural network model;

[0132] Step S32: inputting the condition information for controlling the stratospheric wind field into the conditional control network to obtain a conditional control vector, inputting the stratospheric wind field sample data and the conditional control vector into the encoder part of the encoder-decoder model to obtain a latent space vector;

[0133] Step S33: gradually adding random noise to the latent space vector to obtain a noisy latent space vector; inputting the conditional control vector and the noisy latent space vector into a denoising neural network of a latent space diffusion model to obtain predicted noise, and performing a reverse denoising process based on the predicted noise to obtain a denoised latent space vector; inputting the denoised latent space vector and the conditional control vector into the conditional decoder for decoding to obtain stratospheric wind field simulation data;

[0134] Step S34: Calculating the second loss function value based on the denoising neural network and the stratospheric wind field simulation data obtained by decoding;

[0135] Step S35: updating the parameters of the denoising neural network model based on back propagation according to the second loss function value;

[0136] Step S36: Iterate steps S33 to S35 until the iteration end condition is reached to obtain a pre-trained encoder-decoder model.

[0137] The second loss function value in S34 is calculated using the following formula:

[0138]

[0139] Among them, Loss represents the second loss function, ε t represents the random noise added in step S33, T represents the maximum number of steps, ε θ (X t , t) represents the predicted noise obtained by the denoising neural network model in step S33, Represents ε t -ε θ (X t ,t), γ represents the proportion of the difference between the stratospheric wind field simulation data and the stratospheric wind field sample data in the loss function, O represents the stratospheric wind field simulation data decoded by the conditional decoder, and Y represents the corresponding stratospheric wind field sample data used for training.

[0140] The pre-training process of the latent space diffusion model is as follows Figure 5As shown, the original stratospheric wind field sample data is mapped to a low-dimensional latent space for diffusion process, which greatly reduces the data dimension that the diffusion model needs to learn. The forward diffusion process of the latent space diffusion model is to add noise to the latent variables in the latent space, and the reverse diffusion process is to denoise the latent variables. Considering that the diffusion model requires a very long Markov process to generate high-quality stratospheric wind field simulation data, this is a very slow reverse diffusion process. Therefore, the latent space diffusion model described in step S3 uses DDIM for the reverse diffusion process. In this way, the number of sampling steps in the process of generating stratospheric wind field simulation data can be significantly reduced.

[0141] Step S4: taking the first stratospheric wind field simulation data as input, and obtaining second stratospheric wind field simulation data through a pre-trained spatiotemporal super-resolution network model; wherein the resolution of the second stratospheric wind field simulation data is higher than the resolution of the first stratospheric wind field simulation data.

[0142] In some embodiments, the spatiotemporal super-resolution network model in step S4 includes an initial feature extraction module, a feature fusion module and a reconstruction module. The specific network structure is as follows: Figure 6 As shown, the pre-training process of the spatiotemporal super-resolution network model includes the following steps:

[0143] Step S41: constructing a spatiotemporal super-resolution network model and initializing parameters of the spatiotemporal super-resolution network model;

[0144] Step S42: inputting the three-dimensional wind field data of the first time point of the first stratospheric wind field sample data into the initial feature extraction module of the spatiotemporal super-resolution network model to obtain an initial feature vector I0;

[0145] Step S43: inputting the first stratospheric wind field sample data into the first feature fusion processing unit of the feature fusion module of the spatiotemporal super-resolution network model to obtain a second feature vector I1, concatenating the initial feature vector I0 and the second feature vector I1, and inputting the concatenated data into the second feature fusion processing unit of the feature fusion module to obtain a fused feature vector I2;

[0146] Step S44: inputting the fused feature vector I2 into the reconstruction module of the spatiotemporal super-resolution network model to obtain reconstructed third stratospheric wind field simulation data;

[0147] Step S45: calculating the L2 loss based on the second stratospheric wind field sample data corresponding to the first stratospheric wind field sample data and the third stratospheric wind field simulation data reconstructed by the spatiotemporal super-resolution network model; wherein the resolution of the third stratospheric wind field sample data is higher than the resolution of the first stratospheric wind field sample data; and the second stratospheric wind field sample data is the high-resolution stratospheric wind field sample data that actually corresponds to the first stratospheric wind field sample data;

[0148] Step S46: updating the parameters of the spatiotemporal super-resolution network model based on back propagation according to the L2 loss value;

[0149] Step S47: Iterate steps S42 to S46 until the iteration end condition is reached to obtain a pre-trained spatiotemporal super-resolution network model.

[0150] The embodiment of the present invention evaluates the effect of simulating the wind field by comparing the stratospheric wind field simulation data with the actual average wind speed profile of the stratospheric wind field. The difference between the generated stratospheric wind field simulation data and the stratospheric wind field sample data, the difference in the average wind speed profiles of the two should be as small as possible.

[0151] The comparison between the average wind speed profile of the simulated wind field generated by the latent space diffusion model in this embodiment and the real wind field is as follows: Figure 7 As shown, in this embodiment, the overall average wind speed of the stratospheric wind field sample data (real stratospheric wind field data) used for training is 31.29 m / s, while the overall average wind speed of the simulated wind field generated using the latent space diffusion model is 34.17 m / s.

[0152] Figure 8 (a) shows the visualization of low-resolution stratospheric wind field sample data obtained after artificial coarsening. Figure 8 (b) is a visualization of high-resolution stratospheric wind field sample data before coarsening. Fig. 9 This is a visualization effect diagram of the low-resolution stratospheric wind field sample data obtained after coarsening based on this embodiment after using the spatiotemporal super-resolution network to enhance the resolution. The structural similarity index (SSIM) of the high-resolution stratospheric wind field simulation data obtained by this embodiment using the spatiotemporal super-resolution network and the high-resolution stratospheric wind field sample data can reach up to 0.99, and the peak signal-to-noise ratio (PSNR) can reach up to 60.

[0153] The embodiment of the present application also provides an electronic device, including: a memory and a processor;

[0154] The memory is used to store computer programs;

[0155] The processor is used to call the computer program to execute the method as described above.

[0156] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed on an electronic device, the electronic device implements the method as described above.

[0157] An embodiment of the present application further provides a computer program product, including a computer program. When the computer program is executed on an electronic device, the electronic device implements the method as described above.

[0158] The embodiments of the present application also provide a system, an electronic device, a computer-readable storage medium, and a computer program product. The specific implementation methods can refer to the specific embodiments of the above methods and will not be repeated here.

[0159] Obviously, those skilled in the art should understand that the above-mentioned units or steps of the present application can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the present application is not limited to any specific combination of hardware and software.

[0160] The above description of the embodiments of the present application is only a partial embodiment of the present application, which is used to enable professionals in the field to implement or use the content of the present application, and is not used to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A stratospheric wind field simulation method, characterized in that: The method includes: Step S1: construct a conditional control network, input the conditional information for controlling the stratospheric wind field into the conditional control network, and obtain a conditional control vector; Step S2: taking the stratospheric wind field sample data and the conditional control vector as input, extracting features from the stratospheric wind field sample data through the conditional encoder in the pre-trained encoder-decoder model, and mapping it to a low-dimensional latent space vector; wherein the encoder-decoder model includes two parts: a conditional encoder and a conditional decoder; Step S3: gradually adding random noise to the latent space vector to obtain a noisy latent space vector; taking the conditional control vector and the noisy latent space vector as input, predicting the noise through a denoising neural network model of a pre-trained latent space diffusion model, and performing a reverse denoising process to obtain a denoised latent space vector; inputting the denoised latent space vector and the conditional control vector into a conditional decoder in a pre-trained encoder-decoder model for decoding to obtain first stratospheric wind field simulation data; Step S4: taking the first stratospheric wind field simulation data as input, and obtaining second stratospheric wind field simulation data through a pre-trained spatiotemporal super-resolution network model; wherein the resolution of the second stratospheric wind field simulation data is higher than the resolution of the first stratospheric wind field simulation data.

2. The method according to claim 1, characterized in that Step S1: The conditional control network includes a numerical coding layer, a non-numerical coding layer and three linear layers, wherein the numerical coding layer is used to encode numerical conditions, and the non-numerical coding layer is used to encode non-numerical conditions. The outputs of the numerical coding layer and the non-numerical coding layer are concatenated and input into the three linear layers to obtain the conditional control vector. Among the three linear layers, the first linear layer serves as an input layer to receive the outputs of the numerical coding layer and the non-numerical coding layer, the second linear layer serves as a hidden layer, and the third linear layer serves as an output layer to output the conditional control vector.

3. The method according to claim 1, characterized in that The conditional encoder comprises a plurality of groups of spatiotemporal downsampling modules and spatiotemporal attention modules connected in sequence; each group of spatiotemporal downsampling modules and spatiotemporal attention modules comprises a spatiotemporal downsampling module and a spatiotemporal attention module connected in sequence; Each spatiotemporal downsampling module includes a spatial downsampling unit and a temporal downsampling unit connected in sequence; The spatial downsampling unit includes a plurality of three-dimensional spatial convolutional layers connected in sequence, which are used to process the spatial dimension information of the stratospheric wind field sample data; the temporal downsampling unit includes a one-dimensional temporal convolutional layer, which is used to process the temporal dimension information of the stratospheric wind field sample data; each convolutional layer is followed by a residual layer; Each spatiotemporal attention module includes a sequentially connected spatial attention layer and a temporal attention layer, which are used to process the spatial dimension information and the temporal dimension information of the stratospheric wind field sample data respectively; The sequential connection means that the output of the previous module, layer or unit is used as the input of the next module or layer; The conditional encoder receives the conditional control vector and the stratospheric wind field sample data as input, and the stratospheric wind field sample data is input into the first three-dimensional spatial convolution layer in the conditional encoder; the other three-dimensional spatial convolution layers except the first three-dimensional spatial convolution layer in the conditional encoder, and the one-dimensional temporal convolution layer, combine the output of the previous module, layer or unit and the conditional control vector as input; The conditional decoder comprises a plurality of groups of sequentially connected spatiotemporal upsampling modules and spatiotemporal attention modules; each group of spatiotemporal upsampling modules and spatiotemporal attention modules comprises a sequentially connected spatiotemporal upsampling module and a spatiotemporal attention module; The spatiotemporal upsampling module includes a spatial upsampling unit and a temporal upsampling unit; the spatial upsampling unit includes a plurality of three-dimensional spatial convolutional layers connected in sequence, which are used to perform upsampling operations on the spatial information of the stratospheric wind field sample data; the temporal upsampling unit includes a one-dimensional temporal convolutional layer, which is used to perform upsampling operations on the temporal information of the stratospheric wind field sample data; a residual layer is arranged behind each convolutional layer; and four-dimensional spatiotemporal stratospheric wind field simulation data is obtained through the spatiotemporal upsampling module.

4. The method according to claim 1, characterized in that: The pre-training process of the encoder-decoder model includes: Step S21: constructing an encoder-decoder model and initializing parameters of the encoder-decoder model; Step S22: inputting the condition information for controlling the stratospheric wind field into the conditional control network to obtain a conditional control vector; inputting the stratospheric wind field sample data and the conditional control vector into the encoder-decoder model to obtain stratospheric wind field simulation data generated by the encoder-decoder model; Step S23: calculating a first loss function value based on the stratospheric wind field simulation data and the stratospheric wind field sample data; Step S24: updating the parameters of the encoder-decoder model based on back propagation according to the first loss function value; Step S22: iterate steps S22 to S24 until the iteration end condition is reached to obtain a pre-trained encoder-decoder model; Preferably, the first loss function in step S23 is calculated using the following formula: Wherein, Loss(r,x) is the first loss function, r represents the generated stratospheric wind field simulation data, x represents the stratospheric wind field sample data, mse(r,x) represents the mean square error between r and x, σ represents the variance of the generated stratospheric wind field simulation data, KL(r,x) represents the KL divergence between r and x, and γ represents the weight of the KL divergence; The mean square error is calculated by the following formula: Where N represents the number of grid points in a stratospheric wind field, r i represents the wind speed value of the i-th grid point in the generated stratospheric wind field simulation data, x i Represents the wind speed value of the i-th grid point in the stratospheric wind field sample data; The KL divergence is calculated by the following formula: Among them, μ r and σ r Respectively represent the mean and variance of the generated stratospheric wind field simulation data, μ x and σ x They respectively represent the mean and variance of the corresponding stratospheric wind field sample data used for training.

5. The method according to claim 1, characterized in that The denoising neural network model of the latent space diffusion model in step S3 includes a downsampling module, an intermediate module and an upsampling module connected in sequence; The downsampling module comprises a plurality of downsampling units connected in sequence; The downsampling unit includes a three-dimensional spatial convolution layer, a one-dimensional temporal convolution layer, a residual layer, and a spatiotemporal attention module connected in sequence; The intermediate module includes a spatiotemporal attention module, and a residual layer is provided before and after the spatiotemporal attention module; The upsampling module includes a plurality of upsampling units connected in sequence, each of which includes a four-dimensional spatiotemporal convolution module and a spatiotemporal attention module connected in sequence; the four-dimensional spatiotemporal convolution module includes a three-dimensional spatial convolution layer, a one-dimensional temporal convolution layer and a residual layer connected in sequence.

6. The method according to claim 1, characterized in that The denoising neural network model pre-training process of the latent space diffusion model includes: Step S31: constructing a denoising neural network model of a latent space diffusion model and initializing parameters of the denoising neural network model; Step S32: inputting the condition information for controlling the stratospheric wind field into the conditional control network to obtain a conditional control vector, inputting the stratospheric wind field sample data and the conditional control vector into the encoder part of the encoder-decoder model to obtain a latent space vector; Step S33: gradually adding random noise to the latent space vector to obtain a noisy latent space vector; inputting the conditional control vector and the noisy latent space vector into a denoising neural network of a latent space diffusion model to obtain predicted noise, and performing a reverse denoising process based on the predicted noise to obtain a denoised latent space vector; inputting the denoised latent space vector and the conditional control vector into the conditional decoder for decoding to obtain stratospheric wind field simulation data; Step S34: Calculating the second loss function value based on the denoising neural network and the stratospheric wind field simulation data obtained by decoding; Step S35: updating the parameters of the denoising neural network model based on back propagation according to the second loss function value; Step S36: iterate steps S33 to S35 until the iteration end condition is reached to obtain a pre-trained encoder-decoder model; Preferably, the second loss function value in step S34 is calculated using the following formula: Among them, Loss represents the second loss function, ε t represents the random noise added in step S33, T represents the maximum number of steps, ε θ (X t , t) represents the predicted noise obtained by the denoising neural network model in step S33, Represents ε t -ε θ (X t ,t), γ represents the proportion of the difference between the stratospheric wind field simulation data and the stratospheric wind field sample data in the loss function, O represents the stratospheric wind field simulation data decoded by the conditional decoder, and Y represents the corresponding stratospheric wind field sample data used for training.

7. The method according to claim 1, characterized in that The spatiotemporal super-resolution network model in step S4 includes an initial feature extraction module, a feature fusion module and a reconstruction module; the initial feature extraction module includes a first feature extraction unit, a downsampling layer and a second feature extraction unit connected in sequence; the first feature extraction unit and the second feature extraction unit both include a three-dimensional spatial convolution layer, a spatial attention layer and a residual layer connected in sequence; the feature fusion module includes a first feature fusion processing unit and a second feature fusion processing unit connected in sequence; the first feature fusion processing unit and the second feature fusion processing unit include two sub-processing units, each of which includes a first sub-processing unit connected in sequence The output end of the initial feature extraction module is connected to the input end of the second feature fusion processing unit in the feature fusion module; the four-dimensional space-time convolution module includes a three-dimensional space convolution layer, a one-dimensional time convolution layer and a residual layer connected in sequence; the output end of the feature fusion module is connected to the input end of the reconstruction module; the reconstruction module includes a four-dimensional space-time convolution module, a space-time attention module, an upsampling layer, a residual layer and a space-time attention module connected in sequence.

8. The method according to claim 1, characterized in that The pre-training process of the spatiotemporal super-resolution network model includes the following steps: Step S41: constructing a spatiotemporal super-resolution network model and initializing parameters of the spatiotemporal super-resolution network model; Step S42: inputting the three-dimensional wind field data of the first time point of the first stratospheric wind field sample data into the initial feature extraction module of the spatiotemporal super-resolution network model to obtain an initial feature vector I0; Step S43: inputting the first stratospheric wind field sample data into the first feature fusion processing unit of the feature fusion module of the spatiotemporal super-resolution network model to obtain a second feature vector I1, concatenating the initial feature vector I0 and the second feature vector I1, and inputting the concatenated data into the second feature fusion processing unit of the feature fusion module to obtain a fused feature vector I2; Step S44: inputting the fused feature vector I2 into the reconstruction module of the spatiotemporal super-resolution network model to obtain reconstructed third stratospheric wind field simulation data; Step S45: calculating the L2 loss based on the second stratospheric wind field sample data corresponding to the first stratospheric wind field sample data and the third stratospheric wind field simulation data reconstructed by the spatiotemporal super-resolution network model; wherein the resolution of the third stratospheric wind field sample data is higher than the resolution of the first stratospheric wind field sample data; and the second stratospheric wind field sample data is the high-resolution stratospheric wind field sample data that actually corresponds to the first stratospheric wind field sample data; Step S46: updating the parameters of the spatiotemporal super-resolution network model based on back propagation according to the L2 loss value; Step S47: Iterate steps S42 to S46 until the iteration end condition is reached to obtain a pre-trained spatiotemporal super-resolution network model.

9. An electronic device, characterized in that: include: Memory and processor; The memory is used to store computer programs; The processor is configured to call the computer program to execute the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed on an electronic device, the electronic device implements the method according to any one of claims 1 to 8.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed on an electronic device, the electronic device implements the method according to any one of claims 1 to 8.

Images