Radar echo prediction method and device, equipment and medium

Abstract

The invention provides a radar echo prediction method and device, equipment and a medium, and relates to the technical field of radar echo prediction, and the method comprises the steps: inputting four-dimensional time series data of a target region into a generative radar extrapolation echo prediction model comprising a Transform-GAN network, a ConvLSTM network and a fusion network, and obtaining a prediction image of radar echoes; the Transform-GAN network is used for performing feature generation on the four-dimensional time series data to obtain an initial radar echo prediction image and prediction accuracy; the ConvLSTM network is used for carrying out feature extraction on the initial radar echo prediction image and the corresponding prediction accuracy to obtain spatial-temporal features of the initial radar echo prediction image; and the fusion network is used for carrying out feature fusion to obtain a prediction image of the radar echo. According to the invention, accurate and clear time sequence prediction of radar echoes can be realized, and the precision, definition and reality of the predicted image are improved.

Description

Technical Field

[0001] The present application relates to the technical field of radar echo prediction, and in particular to a radar echo prediction method, device, equipment and medium. Background Art

[0002] Existing radar echo extrapolation mainly includes traditional radar echo extrapolation methods and deep learning-based radar echo extrapolation methods. Among them, traditional radar echo extrapolation methods are mostly based on linear extrapolation. When the weather conditions are complex and change drastically, especially when small and medium-scale convective weather occurs, the forecast error will increase significantly. Although the current deep learning-based radar echo extrapolation method can make up for the defect of traditional methods in that they cannot perform nonlinear extrapolation to a certain extent, it still has the following defects: First, the RNN-based model has the function of temporal memory and the characteristics of biological neural networks. The back propagation algorithm is used to learn parameters between neural units in the recurrent neural network. When the input time series data is long, gradient explosion and disappearance will occur. The second type, based on models based on sequence-to-sequence (Seq2Seq) architecture, is ambiguous in short-term extrapolation and has difficulty in making longer-term predictions; The third type is that the convolutional layer in the CNN-based model is conducive to the reading of spatial information, but lacks the ability to learn temporal information; Fourth, models based on generative adversarial networks (GANs) lack the ability to discriminate small-scale information.

[0003] In the radar echo field, the echo of layered clouds has a large spatiotemporal scale and is more predictable, while the strong echo caused by convective clouds has a small spatiotemporal scale and is less predictable. In addition, the radar echo image is quite different from ordinary spatiotemporal series data, which makes it difficult to directly apply the methods in the field of spatiotemporal series prediction to radar echo extrapolation. Due to the limitations of the model structure and the particularity of radar data, radar echo extrapolation still needs to be improved in terms of clarity, prediction timeliness and distortion. The non-rigid motion characteristics of radar images cause their statistical characteristics to change over time and have high-order non-stationarity, that is, there are significant differences in the echo distribution at different local locations at the same time and the same local location at different times. Many current models do not fully consider the typical characteristics of radar images, lack the ability to model high-order non-stationary information, and cannot accurately model their long-term motion. This results in low prediction accuracy, insufficient robustness, poor adaptability, low prediction efficiency, and inability to apply the above models to radar echo prediction in complex scenarios.

[0004] The existing radar echo extrapolation prediction method uses ConvLSTM alone. Although it can capture spatiotemporal features, its receptive field is limited and it is difficult to effectively capture global information. Secondly, when processing long-time series data, ConvLSTM is prone to gradient vanishing or gradient exploding problems, which will lead to its limited prediction ability. Finally, the feature extraction ability of ConvLSTM is limited by the size of the convolution kernel, which leads to its insufficient ability to express complex spatial structures and texture information. The generator of traditional GAN ​​is usually based on convolutional networks, but GAN is very prone to mode collapse and gradient vanishing problems during training. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a radar echo prediction method, device, equipment and medium to solve the above-mentioned problems existing in the prior art and to quickly and accurately predict radar echoes.

[0006] In a first aspect, the present invention provides a method for predicting radar echoes, the method comprising: Acquire four-dimensional time series data of the target area; wherein the four-dimensional time series data includes meteorological data and radar data of multiple target location points in the target area at multiple consecutive moments; Inputting the four-dimensional time series data into a pre-trained generative radar extrapolation echo prediction model to obtain a predicted image of the radar echo; Among them, the generative radar extrapolation echo prediction model includes a Transformer-GAN network, a ConvLSTM network and a fusion network; the Transformer-GAN network is used to generate features for the input four-dimensional time series data to obtain an initial radar echo prediction image and a corresponding prediction accuracy; the ConvLSTM network is used to extract features from the initial radar echo prediction image and the corresponding prediction accuracy output by the Transformer-GAN network to obtain the spatiotemporal characteristics of the initial radar echo prediction image; the fusion network is used to fuse the initial radar echo prediction image with the spatiotemporal characteristics to obtain a predicted image of the radar echo.

[0007] In an optional implementation, the method for acquiring the four-dimensional time series data includes: Acquire meteorological data collected at a plurality of first locations within the target area at intervals of a first preset time period, and radar data collected at a plurality of second locations within the target area at intervals of a second preset time period; Based on the acquisition time of the radar data and the second position point, the radar data and the meteorological data are synchronized in time and space to obtain four-dimensional time series data of the target area.

[0008] In an optional implementation, the Transformer-GAN network includes: a Transformer encoder, a Transformer generator, and a discriminator; The Transformer encoder is used to perform feature processing on the input four-dimensional time series data to obtain first feature data; The Transformer generator is used to extract and map the first feature data output by the Transformer encoder to obtain an initial radar echo prediction image; The discriminator is used to determine the prediction accuracy of the initial radar echo prediction image output by the Transformer generator.

[0009] In an optional embodiment, the Transformer encoder comprises: a first input layer, a self-attention layer and a feedforward layer; The first input layer is used to receive the four-dimensional time series data; The self-attention layer is used to perform global feature extraction on the four-dimensional time series data to obtain second feature data; The feedforward layer is used to perform feature processing on the second feature data to obtain first feature data.

[0010] In an optional embodiment, the Transformer generator includes: a second input layer, a multi-layer Transformer encoder, a first fully connected layer and a first output layer; The second input layer is used to receive the first feature data; The multi-layer Transformer encoder is used to perform deep feature extraction on the first feature data through a multi-layer encoder to obtain third feature data; The first fully connected layer is used to perform feature mapping on the third feature data to obtain an initial radar echo prediction image; The first output layer is used to output the initial radar echo prediction image.

[0011] In an optional implementation, the discriminator includes: a third input layer, a second fully connected layer, and a second output layer; The third input layer is used to receive the initial radar echo prediction image; The second fully connected layer is used to determine the prediction accuracy of the initial radar echo prediction image; The second output layer is used to output the initial radar echo prediction image and the corresponding prediction accuracy.

[0012] In an optional implementation, the ConvLSTM network comprises: a fourth input layer and a ConvLSTM2D layer; The fourth input layer is used to receive the initial radar echo prediction image and the corresponding prediction accuracy; The ConvLSTM2D layer is used to extract the spatiotemporal features of the initial radar echo prediction image.

[0013] In a second aspect, the present invention provides a radar echo prediction device, the device comprising: An acquisition unit, used to acquire four-dimensional time series data of a target area; wherein the four-dimensional time series data includes meteorological data and radar data of multiple target location points in the target area at multiple consecutive moments; A prediction unit, used for inputting the four-dimensional time series data into a pre-trained generative radar extrapolation echo prediction model to obtain a predicted image of the radar echo; Among them, the generative radar extrapolation echo prediction model includes a Transformer-GAN network, a ConvLSTM network and a fusion network; the Transformer-GAN network is used to generate features for the input four-dimensional time series data to obtain an initial radar echo prediction image and a corresponding prediction accuracy; the ConvLSTM network is used to extract features from the initial radar echo prediction image and the corresponding prediction accuracy output by the Transformer-GAN network to obtain the spatiotemporal characteristics of the initial radar echo prediction image; the fusion network is used to fuse the initial radar echo prediction image with the spatiotemporal characteristics to obtain a predicted image of the radar echo.

[0014] In a third aspect, the present invention provides an electronic device, the electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; The processor is used to implement the method described in any of the above-mentioned embodiments when executing the program stored in the memory.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the aforementioned embodiments is implemented.

[0016] The generative radar extrapolation echo prediction model of this application integrates Transformer, GAN network and ConvLSTM network. Transformer has a self-attention mechanism, which can effectively obtain global information and map it to multiple spaces, thereby enhancing the expression ability of the model; GAN network does not contain convolution at all, and the generator relies on the advantages of Transformer, which can better capture low-level textures while improving feature resolution. Combining the spatiotemporal feature capture capability of ConvLSTM and the image generation capability of Transformer-GAN, the final generative radar extrapolation echo prediction model (TG-ConvLSTM) is obtained, which can accurately obtain spatial information features while predicting the time series of radar echoes.

[0017] This application can achieve accurate and clear time series prediction of radar echoes, improving the accuracy, clarity and realism of the predicted images. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 A flow chart of a radar echo prediction method provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a generative radar extrapolation echo prediction model provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of a radar echo prediction device provided in an embodiment of the present application; Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0021] This application uses Transformer instead of traditional convolutional network as the generator, which can better capture low-level texture and detail information. The self-attention mechanism of Transformer can alleviate the mode collapse problem in the GAN training process and can better improve the training stability. At the same time, the self-attention mechanism of Transformer can capture global spatial dependencies and effectively make up for the shortcomings of the local receptive field of ConvLSTM.

[0022] The radar echo prediction method provided in the embodiment of the present application can be applied in a server or in a terminal with strong computing power. The server can be a physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms. The terminal can be a user equipment (User Equipment, UE) such as a mobile phone, a smart phone, a laptop, a digital broadcast receiver, a personal digital assistant (PDA), a tablet computer (PAD), a handheld device, a vehicle-mounted device, a wearable device, a computing device or other processing equipment connected to a wireless modem, a mobile station (Mobile Station, MS), a mobile terminal (Mobile Terminal), etc. The terminal and the server can be directly or indirectly connected through a wired or wireless communication method, which is not limited in this application.

[0023] The preferred embodiments of the present application are described below in conjunction with the drawings in the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. In addition, the embodiments and features in the embodiments of the present application may be combined with each other if there is no conflict.

[0024] Figure 1 A schematic diagram of a radar echo prediction method provided in an embodiment of the present application. Figure 1 As shown, the method may include: S110, acquiring four-dimensional time series data of the target area, wherein the four-dimensional time series data includes meteorological data and radar data of multiple target location points in the target area at multiple consecutive moments.

[0025] In the embodiment of the present application, the multiple consecutive moments may be 5 consecutive moments.

[0026] In an embodiment of the present application, a method for acquiring four-dimensional time series data includes: Acquire meteorological data collected at multiple first position points in the target area every first preset time period, and radar data collected at multiple second position points in the target area every second preset time period; based on the collection time of the radar data and the second position point, perform spatiotemporal synchronization on the radar data and the meteorological data to obtain four-dimensional time series data of the target area.

[0027] In the embodiment of the present application, the radar data and the meteorological data are synchronized in time and space based on the first acquisition time and the second position point of the radar data to obtain four-dimensional time series data of the target area, including: For any second position point, obtain a preset number of first position points closest to the second position point to obtain a third position point; use the radar data of the second position point corresponding to different first acquisition times as the first time series data; use the meteorological data of the third position point corresponding to different second acquisition times as the second time series data; For any first collection time in the first time series data, a preset number of second collection times closest to the first collection time are selected from the second time series data as target collection times; linearly interpolate the meteorological data of the target collection time to obtain meteorological data of the third position point at the first collection time; Based on the meteorological data and radar data of different third position points at the first acquisition time, the meteorological data and radar data of the second position point at the first acquisition time are obtained; based on the meteorological data and radar data of different second position points at the first acquisition time, the four-dimensional time series data of the target area is obtained.

[0028] In an embodiment of the present application, obtaining meteorological data and radar data of a second location point at a first collection time based on meteorological data and radar data of different third location points at a first collection time includes: The weight of each third position point is determined according to the distance between different third position points and the second position point; the meteorological data and radar data of each third position point at the first collection time are weightedly summed to obtain the meteorological data and radar data of the second position point at the first collection time.

[0029] In an embodiment of the present application, the four-dimensional time series data of the target area includes: meteorological data and radar data of each second position point in the target area at different first acquisition times.

[0030] In an embodiment of the present application, the meteorological data includes: radar combined reflectivity, first brightness temperature data and second brightness temperature data; wherein the first water vapor content is the brightness temperature value of FY4B AGRI channel 10, i.e., the middle-layer water vapor channel; the second water vapor content is the brightness temperature value of FY4B AGRI channel 11, i.e., the low-layer water vapor channel; the radar data is radar combined emissivity data provided by the meteorological station, and the prediction factor is a four-dimensional data. For example, the meteorological data is for an area with a spatial range of 20 meters * 20 meters for three consecutive time periods, and the dimension of the prediction factor is expressed as 5*20*20*3, 5 represents 5 consecutive time periods, 20*20 represents the spatial area range of the data, and 3 represents the radar combined reflectivity, the first brightness temperature data and the second brightness temperature data.

[0031] In practical applications, the horizontal resolution of radar data is 0.1°*0.1°, and the temporal resolution is 6 minutes; the spatial resolution of meteorological data is 4 km, and the temporal resolution is 15 minutes; due to the different temporal and spatial resolutions of the two, it is necessary to unify the temporal and spatial resolutions of meteorological data and radar data.

[0032] For example, meteorological data is collected every 15 minutes for every 20m*20m area, and radar data is collected every 6 minutes for every 1m*1m area. Every 1m*1m area of ​​radar data is considered as one location point. For any location point (i.e., the second location point), four adjacent location points (i.e., multiple third location points) are selected from the meteorological data. The four third location points form a square or rectangle, and the target point is located inside it.

[0033] For each third position point, the first acquisition time of the radar data corresponding to the second position point is the 0th minute, the 6th minute and the 12th minute respectively; the second acquisition time of the meteorological data corresponding to the third position point is the 0th minute and the 15th minute respectively; for the 6th minute, the meteorological data of the 0th minute and the 15th minute are linearly interpolated to obtain the meteorological data of the third position point at the 6th minute; The weights of the four third position points are determined according to the distances between the four third position points and any second position point; interpolation calculation is performed based on the meteorological data of the four third position points at the 6th minute and the weights of the four third position points to obtain the four-dimensional time series data of the second position points at the 6th minute; the four-dimensional time series data of all second position points at all first acquisition times are the four-dimensional time series data of the target area.

[0034] Unlike other methods that use radar echoes as input, this application introduces two infrared channel data from satellites, which are usually used to observe atmospheric temperature and cloud top characteristics at different altitudes. Channel 10 is mainly used to observe the temperature of the surface and cloud tops, and is sensitive to mid- and low-level clouds and surface temperature. Channel 11 is mainly used to observe the water vapor distribution and cloud top characteristics at mid- and high-levels of the atmosphere, and is sensitive to high-level clouds and water vapor content. The brightness temperature data of channels 10 and 11 can help identify precipitation clouds and non-precipitation clouds. By combining radar data, precipitation clouds can be more accurately separated from non-precipitation clouds, thereby improving the inversion accuracy.

[0035] S120, inputting the four-dimensional time series data into a pre-trained generative radar extrapolation echo prediction model to obtain a predicted image of the radar echo.

[0036] In an embodiment of the present application, the generative radar extrapolation echo prediction model includes a Transformer-GAN network, a ConvLSTM network and a fusion network.

[0037] In an embodiment of the present application, a Transformer-GAN network includes: a Transformer encoder, a Transformer generator, and a discriminator; Transformer encoder, used for performing feature processing on the input four-dimensional time series data to obtain first feature data; A Transformer generator, used for performing feature extraction and mapping on the first feature data output by the Transformer encoder to obtain an initial radar echo prediction image; The discriminator is used to determine the prediction accuracy of the initial radar echo prediction image output by the Transformer generator.

[0038] In an embodiment of the present application, a Transformer encoder includes: a first input layer, a self-attention layer, and a feedforward layer; The first input layer is used to receive four-dimensional time series data; The self-attention layer is used to extract global features from the four-dimensional time series data to obtain the second feature data; The feedforward layer is used to perform feature processing on the second feature data to obtain the first feature data.

[0039] In an embodiment of the present application, a Transformer generator includes: a second input layer, a multi-layer Transformer encoder, a first fully connected layer, and a first output layer; A second input layer, used for receiving first feature data; A multi-layer Transformer encoder is used to perform deep feature extraction on the first feature data through the multi-layer encoder to obtain third feature data; The first fully connected layer is used to perform feature mapping on the third feature data to obtain an initial radar echo prediction image; The first output layer is used to output the initial radar echo prediction image.

[0040] In one embodiment of the present application, the multi-layer Transformer encoder is a multi-layer Transformer encoder with a local self-attention mechanism, thereby enhancing the ability to capture local details; a local self-attention mechanism is introduced in each layer of the encoder, focusing only on information within a local time window, reducing computational complexity and improving the ability to capture local dependencies; a sliding window or a sparse attention matrix is ​​used to limit the attention range; a feedforward neural network in each layer of the encoder performs a nonlinear transformation on features; residual connections and layer normalization are used in each layer of the encoder to stabilize the training process; and Dropout or L2 regularization is introduced to prevent overfitting.

[0041] In one embodiment of the present application, the above-mentioned self-attention mechanism can be replaced by a sparse attention mechanism (such as Longformer, BigBird) or a local attention mechanism (such as Reformer) to reduce the computational complexity of the self-attention mechanism.

[0042] In the embodiment of the present application, the discriminator includes: a third input layer, a second fully connected layer, and a second output layer; The third input layer is used to receive the initial radar echo prediction image; The second fully connected layer is used to determine the prediction accuracy of the initial radar echo prediction image; The second output layer is used to output the initial radar echo prediction image and the corresponding prediction accuracy.

[0043] In the embodiment of the present application, the ConvLSTM network includes: a fourth input layer and a ConvLSTM2D layer; The fourth input layer is used to receive the initial radar echo prediction image and the corresponding prediction accuracy; ConvLSTM2D layer, used to extract the spatiotemporal features of the initial radar echo prediction image.

[0044] In an embodiment of the present application, a fusion network is used to perform feature fusion on the spatiotemporal features of an initial radar echo prediction image output by the first output layer of the Transformer generator and the initial radar echo prediction image output by the ConvLSTM2D layer; wherein the initial radar echo prediction image captures the global information and low-level texture details of the radar echo; and the spatiotemporal features of the initial radar echo prediction image capture the dynamic changes of the radar echo in time and space.

[0045] In the embodiment of the present application, the fusion network uses attention mechanism fusion to perform feature fusion, including: The correlation between the temporal and spatial features of the initial radar echo prediction image and the initial radar echo prediction image is calculated to generate attention weights; the temporal and spatial features of the initial radar echo prediction image and the initial radar echo prediction image are weightedly fused according to the attention weights to obtain a predicted image of the radar echo.

[0046] In the embodiment of the present application, the predicted image of the radar echo is also four-dimensional data, including: the predicted value of the radar echo of each second position point in the target area within a preset time period in the future.

[0047] In an embodiment of the present application, the number of predicted time points in a future preset time period is a multiple of the number of time points covered by multiple consecutive moments of the four-dimensional time series data, ensuring coverage of a wider time range.

[0048] For example, the meteorological data and radar data of five consecutive moments may be input to obtain the radar echo prediction value within a future preset time period consisting of the next ten consecutive moments.

[0049] This application uses Transformer instead of traditional convolutional network as the generator, which can better capture low-level texture and detail information. The self-attention mechanism of Transformer can alleviate the mode collapse problem in the GAN training process and can better improve the training stability. At the same time, the self-attention mechanism of Transformer can capture global spatial dependencies and effectively make up for the shortcomings of the local receptive field of ConvLSTM. In one embodiment of the present application, the training of the generative radar extrapolation echo prediction model is distributed to multiple GPUs or nodes to accelerate the training process.

[0050] In an embodiment of the present application, a method for predicting radar echoes includes: 1. Data selection: (1) China radar mosaic data uses radar basic emissivity mosaic data provided by the Central Meteorological Observatory, with a horizontal resolution of 0.1°*0.1° and a temporal resolution of 6 minutes.

[0051] (2) FY4B AGRI channels 10 and 11 represent the middle-layer water vapor channel and the lower-layer water vapor channel, respectively, with a spatial resolution of 4 km and a temporal resolution of 15 min.

[0052] 2. Data Fusion Multi-source data fusion: refers to the process of integrating and comprehensively utilizing data from different sources in terms of time, space or feature dimensions. Through this fusion, richer and more comprehensive information can be obtained from multiple angles and levels, thereby improving the accuracy and reliability of data analysis and processing. In the time dimension, the fusion of data at different time points can capture the trend of dynamic changes; in the spatial dimension, combining data from different locations helps to build a more detailed and extensive spatial distribution map; in the feature dimension, integrating multiple types of feature information can enhance the understanding and prediction capabilities of complex phenomena.

[0053] The spatial and temporal resolutions of radar data and FY4B data are unified by linear interpolation. The data used in the present invention is 4-dimensional data (5*400*400*3) of time series, which contains the time dimension information of the observation data; wherein 5 represents 5 consecutive data with a time interval of 6 minutes, and 3 represents satellite channel 10, channel 11, and radar combined reflectivity data; each sample contains observation data of 5 consecutive moments. According to experience, observation data of 5 consecutive moments can achieve a good balance between calculation time and forecast performance in the deep learning model.

[0054] (III) Model architecture design: Considering the complexity of radar echo data, a radar echo extrapolation model combining Transformer-GAN--ConvLSTM (TG-ConvLSTM) is proposed, such as Figure 2 As shown in the figure. Transformer has a self-attention mechanism that can effectively obtain global information and map it to multiple spaces, thereby enhancing the model's expressiveness. Build a GAN architecture that does not contain convolution at all. The generator of this architecture relies on the advantages of Transformer, which can better capture low-level textures while improving feature resolution. Combining the spatiotemporal feature capture capability of ConvLSTM and the image generation capability of Transformer-GAN, the final generative radar echo extrapolation model (TG-ConvLSTM) is obtained.

[0055] Transformer-GAN consists of three parts: Transformer encoder, Transformer generator, and discriminator. The Transformer encoder consists of an input layer, a self-attention layer, and a feedforward layer. The input layer is used to receive preprocessed 4D temporal data, the self-attention layer is used to extract global features, and the feedforward layer is used to further process features.

[0056] The Transformer generator includes an input layer, a multi-layer Transformer encoder, a fully connected layer, and an output layer. The input layer is used to receive the processed features. The multi-layer Transformer encoder performs deep feature extraction through the multi-layer encoder and uses the fully connected layer to map the features. The output layer generates a high-resolution radar echo image.

[0057] The discriminator includes an input layer, a fully connected layer, and an output layer. The input layer receives real or generated radar echo images, the fully connected layer is used to evaluate the authenticity of the image, and the output layer outputs the authenticity score of the image.

[0058] The ConvLSTM network includes an input layer and a ConvLSTM2D layer, which are used to receive time series four-dimensional data and capture the spatiotemporal features of images respectively.

[0059] The high-resolution image features output by the Transformer generator and the spatiotemporal features output by the ConvLSTM are fused respectively, and the typical features are further convolved to generate the final radar echo prediction image; the radar echo prediction image is a 10*400*400*1 data, 10 represents the radar combination reflectivity result with a continuous time interval of 6 minutes, that is, this application can obtain the radar echo prediction value of the next 1 hour through extrapolation prediction of 5 frames of data (satellite channels 10, 11, radar). (That is, 10 6-minute data).

[0060] In the embodiment of the present application, the authenticity score is not a fixed indicator. It can be understood as an evaluation indicator of whether the discriminator evaluates whether the input image is a real image. The range is usually between 0 and 1. It is a probability value. A value close to 0 indicates that the input image is very different from the real image, and a value close to 1 indicates that the input image is very different from the real image.

[0061] Corresponding to the above method, the embodiment of the present application also provides a radar echo prediction device, such as Figure 3 As shown, the radar echo prediction device includes: An acquisition unit 310 is used to acquire four-dimensional time series data of a target area; wherein the four-dimensional time series data includes meteorological data and radar data of multiple target locations in the target area at multiple consecutive moments; The prediction unit 320 is used to input the four-dimensional time series data into a pre-trained generative radar extrapolation echo prediction model to obtain a predicted image of the radar echo; Among them, the generative radar extrapolation echo prediction model includes Transformer-GAN network, ConvLSTM network and fusion network; the Transformer-GAN network is used to generate features for the input four-dimensional time series data to obtain the initial radar echo prediction image and the corresponding prediction accuracy; the ConvLSTM network is used to extract features from the initial radar echo prediction image and the corresponding prediction accuracy output by the Transformer-GAN network to obtain the spatiotemporal characteristics of the initial radar echo prediction image; the fusion network is used to fuse the initial radar echo prediction image and the spatiotemporal characteristics to obtain the predicted image of the radar echo.

[0062] The functions of each functional unit of the radar echo prediction device provided in the above embodiments of the present application can be achieved through the above method steps. Therefore, the specific working process and beneficial effects of each unit in the radar echo prediction device provided in the embodiments of the present application will not be repeated here.

[0063] The present application also provides an electronic device, such as Figure 4 As shown, it includes a processor 410 , a communication interface 420 , a memory 430 and a communication bus 440 , wherein the processor 410 , the communication interface 420 , and the memory 430 communicate with each other via the communication bus 440 .

[0064] Memory 430, for storing computer programs; The processor 410 is used to execute the program stored in the memory 430 to implement the following steps: Acquire four-dimensional time series data of the target area; wherein the four-dimensional time series data includes meteorological data and radar data of multiple target location points in the target area at multiple consecutive moments; Input the four-dimensional time series data into the pre-trained generative radar extrapolation echo prediction model to obtain the predicted image of the radar echo; Among them, the generative radar extrapolation echo prediction model includes Transformer-GAN network, ConvLSTM network and fusion network; the Transformer-GAN network is used to generate features for the input four-dimensional time series data to obtain the initial radar echo prediction image and the corresponding prediction accuracy; the ConvLSTM network is used to extract features from the initial radar echo prediction image and the corresponding prediction accuracy output by the Transformer-GAN network to obtain the spatiotemporal characteristics of the initial radar echo prediction image; the fusion network is used to fuse the initial radar echo prediction image and the spatiotemporal characteristics to obtain the predicted image of the radar echo.

[0065] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0066] The communication interface is used for communication between the above electronic device and other devices.

[0067] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0068] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0069] The implementation methods and beneficial effects of the components of the electronic device in the above embodiments to solve the problems can be found in Figure 1 The various steps in the illustrated embodiment are implemented, therefore, the specific working process and beneficial effects of the electronic device provided by the embodiment of the present application are not repeated here.

[0070] In another embodiment provided in the present application, a computer-readable storage medium is provided, in which instructions are stored. When the computer-readable storage medium is executed on a computer, the computer executes the radar echo prediction method described in any one of the above embodiments.

[0071] In another embodiment provided in the present application, a computer program product including instructions is also provided. When the computer program product is executed on a computer, the computer executes the radar echo prediction method described in any one of the above embodiments.

[0072] Those skilled in the art will appreciate that the embodiments in the present application can be provided as methods, systems, or computer program products. Therefore, the embodiments in the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments in the present application can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0073] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0074] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0075] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0076] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present application.

[0077] Obviously, those skilled in the art can make various changes and modifications to the embodiments in the present application without departing from the spirit and scope of the embodiments in the present application. Thus, if these modifications and variations of the embodiments in the present application fall within the scope of the claims and their equivalents in the embodiments of the present application, the embodiments of the present application are also intended to include these modifications and variations.

Claims

1. A method for predicting radar echoes, characterized in that: The method comprises: Acquire four-dimensional time series data of the target area; wherein the four-dimensional time series data includes meteorological data and radar data of multiple target location points in the target area at multiple consecutive moments; Inputting the four-dimensional time series data into a pre-trained generative radar extrapolation echo prediction model to obtain a predicted image of the radar echo; Among them, the generative radar extrapolation echo prediction model includes a Transformer-GAN network, a ConvLSTM network and a fusion network; the Transformer-GAN network is used to generate features for the input four-dimensional time series data to obtain an initial radar echo prediction image and a corresponding prediction accuracy; the ConvLSTM network is used to extract features from the initial radar echo prediction image and the corresponding prediction accuracy output by the Transformer-GAN network to obtain the spatiotemporal characteristics of the initial radar echo prediction image; the fusion network is used to fuse the initial radar echo prediction image with the spatiotemporal characteristics to obtain a predicted image of the radar echo.

2. The method according to claim 1, characterized in that The method for acquiring four-dimensional time series data includes: Acquire meteorological data collected at a plurality of first locations within the target area at intervals of a first preset time period, and radar data collected at a plurality of second locations within the target area at intervals of a second preset time period; Based on the acquisition time of the radar data and the second position point, the radar data and the meteorological data are synchronized in time and space to obtain four-dimensional time series data of the target area.

3. The method according to claim 1, characterized in that The Transformer-GAN network includes: a Transformer encoder, a Transformer generator and a discriminator; The Transformer encoder is used to perform feature processing on the input four-dimensional time series data to obtain first feature data; The Transformer generator is used to extract and map the first feature data output by the Transformer encoder to obtain an initial radar echo prediction image; The discriminator is used to determine the prediction accuracy of the initial radar echo prediction image output by the Transformer generator.

4. The method according to claim 3, characterized in that The Transformer encoder comprises: a first input layer, a self-attention layer and a feedforward layer; The first input layer is used to receive the four-dimensional time series data; The self-attention layer is used to perform global feature extraction on the four-dimensional time series data to obtain second feature data; The feedforward layer is used to perform feature processing on the second feature data to obtain first feature data.

5. The method according to claim 4, characterized in that The Transformer generator comprises: a second input layer, a multi-layer Transformer encoder, a first fully connected layer and a first output layer; The second input layer is used to receive the first feature data; The multi-layer Transformer encoder is used to perform deep feature extraction on the first feature data through a multi-layer encoder to obtain third feature data; The first fully connected layer is used to perform feature mapping on the third feature data to obtain an initial radar echo prediction image; The first output layer is used to output the initial radar echo prediction image.

6. The method according to claim 5, characterized in that The discriminator comprises: a third input layer, a second fully connected layer and a second output layer; The third input layer is used to receive the initial radar echo prediction image; The second fully connected layer is used to determine the prediction accuracy of the initial radar echo prediction image; The second output layer is used to output the initial radar echo prediction image and the corresponding prediction accuracy.

7. The method according to claim 1, characterized in that The ConvLSTM network includes: a fourth input layer and a ConvLSTM2D layer; The fourth input layer is used to receive the initial radar echo prediction image and the corresponding prediction accuracy; The ConvLSTM2D layer is used to extract the spatiotemporal features of the initial radar echo prediction image.

8. A radar echo prediction device, characterized in that: The device comprises: An acquisition unit, used to acquire four-dimensional time series data of a target area; wherein the four-dimensional time series data includes meteorological data and radar data of multiple target location points in the target area at multiple consecutive moments; A prediction unit, used for inputting the four-dimensional time series data into a pre-trained generative radar extrapolation echo prediction model to obtain a predicted image of the radar echo; Among them, the generative radar extrapolation echo prediction model includes a Transformer-GAN network, a ConvLSTM network and a fusion network; the Transformer-GAN network is used to generate features for the input four-dimensional time series data to obtain an initial radar echo prediction image and a corresponding prediction accuracy; the ConvLSTM network is used to extract features from the initial radar echo prediction image and the corresponding prediction accuracy output by the Transformer-GAN network to obtain the spatiotemporal characteristics of the initial radar echo prediction image; the fusion network is used to fuse the initial radar echo prediction image with the spatiotemporal characteristics to obtain a predicted image of the radar echo.

9. An electronic device, characterized in that: The electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; A processor, for implementing any of the methods described in claims 1-7 when executing a program stored in a memory.

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 by a processor, the method according to any one of claims 1 to 7 is implemented.

Images