Radar echo data processing method and system based on multi-elevation subspace coding

Abstract

The present invention discloses a radar echo data processing method and system based on multi-elevation subspace encoding, which relates to the field of meteorological data processing technology. The method comprises the following steps: preprocessing multi-elevation radar echo data; independently encoding the radar echo reflectivity at each elevation angle into the corresponding subspace to obtain the subspace feature representation for each elevation angle; integrating the subspace feature representations corresponding to each elevation angle to form a complete latent vector space; integrating the latent vector space with spatial position embedding information and time period embedding information, and inputting the information into a pre-trained time series model to capture the spatiotemporal dependencies and evolution patterns of convective weather systems and predict the multi-elevation radar echo reflectivity within the next two hours; the time series model is constructed based on a deep learning network with a self-attention mechanism. The present invention fully utilizes the radar echo reflectivity at different elevation angles, captures the complex evolution of the meteorological system, and significantly improves the accuracy of weather forecasts.

Description

Technical Field

[0001] The present invention relates to the technical field of meteorological data processing, and in particular to a radar echo data processing method and system based on multi-elevation subspace coding. Background Art

[0002] Meteorological radar echo data plays a vital role in weather forecasting and disaster monitoring. Doppler weather radars typically scan at multiple elevation angles in modes such as VCP21 and VCP11, acquiring radar echo reflectivity, radial velocity, and spectral width at each elevation angle (VCP21: 0.5°, 1.5°, 2.4°, 3.4°, 4.3°, 6.0°, 9.9°, 14.6°, and 19.5°). This data provides high-resolution spatiotemporal structure of the occurrence and development of convective weather systems, providing crucial support for short-term weather forecasting. Existing radar data processing methods typically process multi-elevation angle data uniformly, generating radar echo composite reflectivity and multi-layer CAPPI radar echo reflectivity through projection transformation and interpolation. This results in information loss and interpolation errors. Furthermore, due to the complexity of meteorological systems and limited computational resources, traditional methods are unable to predict radar echoes at high spatiotemporal resolution (0-2 hours, 6 minutes per scan, 500 meters in length, and 9 elevation angles). Summary of the Invention

[0003] The present invention provides a radar echo data processing method and system based on multi-elevation subspace coding, which can efficiently utilize radar data at different elevation angles and combine geographic location and time period information to achieve high temporal and spatial resolution multi-elevation radar echo reflectivity prediction.

[0004] In order to solve the above problems, the technical solutions adopted by the present invention are as follows:

[0005] In a first aspect, the present invention provides a radar echo data processing method based on multi-elevation subspace coding, comprising the following steps:

[0006] S1. Preprocessing multi-elevation-angle weather radar base data;

[0007] S2. For the pre-processed weather radar base data, independently encode the radar echo reflectivity at each elevation angle into the corresponding subspace to obtain the subspace feature representation of each elevation angle;

[0008] S3, integrating the subspace feature representations corresponding to each elevation angle to form a complete latent vector space;

[0009] S4. Integrate the latent vector space with the spatial position embedding information and the time period embedding information as the input vector, and input it into a pre-trained time series model to capture the spatiotemporal dependencies and evolution patterns of convective weather systems and predict the multi-elevation angle radar echo reflectivity within the next 2 hours; the time series model is constructed based on a deep learning network with a self-attention mechanism.

[0010] As a further description of the above technical solution: In step S1, the method for preprocessing the weather radar base data includes decoding the FMT format base data, reading the multi-elevation radar echo reflectivity (ZH) data, and selecting the elevation layer of VCP21: 0.5°, 1.5°, 2.4°, 3.4°, 4.3°, 6.0°, 9.9°, 14.6°, 19.5° (a total of 9 layers). Each layer takes the original library length (S-band radar: 500 meters), with a maximum of 300 library lengths, to obtain the radar echo reflectivity data of the elevation layer. Because the starting azimuth angle of each elevation angle does not necessarily start exactly at 0°, it is necessary to further align and interpolate the data of each elevation layer to normalize the azimuth angle of 0°-359°, with an equal interval of 1°. Finally, after preprocessing, each meteorological radar base data generates standard multi-elevation radar echo reflectivity data with the dimensions of elevation (9) × storage length (300) × azimuth (360); the high temporal and spatial resolution multi-elevation radar echo reflectivity data for 2 consecutive hours is: forecast time (20) × elevation (9) × storage length (300) × azimuth (360).

[0011] As a further description of the above technical solution: in step S2, the radar echo reflectivity at each elevation angle (library length × azimuth angle) corresponds to an independent subspace encoder, and the subspace encoder is a convolution encoder, including a convolution layer, a pooling layer and an activation function layer.

[0012] As a further description of the above technical solution: in step S3, the subspace feature representation corresponding to each elevation angle is weighted and integrated through the attention mechanism.

[0013] As a further description of the above technical solution: in step S4, the spatial position embedding information is information obtained by encoding the geographical location data of the radar station, which is used to assist the spatial positioning of the time series model. The geographical location data of the radar station includes longitude, latitude and altitude.

[0014] As a further description of the above technical solution: encoding the geographic location data of the radar station is to embed the geographic location data of the radar station into independent vector spaces respectively, and then integrate them into a comprehensive spatial location representation.

[0015] As a further description of the above technical solution: the time period embedded information is generated by sine and cosine functions.

[0016] As a further description of the above technical solution: the time series model is built based on the Transformer network, including several self-attention layers and feedforward neural network layers, each layer captures the spatiotemporal dependencies of radar echo data through the self-attention mechanism.

[0017] In a second aspect, the present invention provides a radar echo data processing system, comprising:

[0018] Data receiving module, used for receiving multi-elevation-angle radar volume scanning data and performing pre-processing;

[0019] Subspace encoding module, used to independently encode radar echo reflectivity at different elevation angles into corresponding subspaces;

[0020] Feature integration module, used to integrate the subspace feature representations of each elevation angle into a complete latent vector space;

[0021] Position encoding module, used to generate spatial position embedding information;

[0022] A time period encoding module, used for generating time period embedding information;

[0023] The spatiotemporal sequence prediction module integrates the latent vector space, spatial position embedding information, and time period embedding information, and performs fusion prediction based on the time series model to output the multi-elevation-angle radar echo reflectivity every 6 minutes within the next 2 hours.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] The present invention can encode the data features of each elevation angle separately in the multi-elevation-angle radar echo reflectivity data processing, and improve the high-temporal-resolution radar echo prediction capability through spatial position, time periodicity information and spatiotemporal sequence modeling; the method of the present invention makes full use of the original library data of different elevation angles and normalized azimuth angles, maximizes the use of data information, captures the complex spatiotemporal evolution process of the meteorological system, and significantly improves the disaster weather monitoring and early warning capabilities.

[0026] In order to make the above-mentioned objects, features and advantages of the present invention more clearly understood, embodiments of the present invention are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0028] Figure 1 is a flow chart of multi-elevation-angle radar echo data processing in an embodiment;

[0029] Figure 2 2. It is a schematic diagram of the structure of the subspace encoder in the embodiment;

[0030] Figure 3 2. It is a schematic diagram of spatial position information encoding in an embodiment;

[0031] Figure 4 This is a schematic diagram of time period information encoding in an embodiment;

[0032] Figure 5 4 is a network structure diagram of spatiotemporal sequence modeling in an embodiment. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments.

[0034] Please refer to Figure 1 The embodiment of the present invention provides a radar echo data processing method based on multi-elevation subspace coding, which is as follows:

[0035] 1. Preprocess the weather radar base data.

[0036] Decode the FMT format base data and read the multi-elevation radar echo reflectivity (ZH) data. Select the VCP21 elevation layers: 0.5°, 1.5°, 2.4°, 3.4°, 4.3°, 6.0°, 9.9°, 14.6°, and 19.5° (9 layers total). Each layer uses the original bin length (500 meters for S-band radar), with a maximum of 300 bin lengths, to obtain radar echo reflectivity data for each elevation layer. Because the starting azimuth of each elevation angle does not necessarily start exactly at 0°, further alignment and interpolation are performed to normalize the data for each elevation layer to azimuths of 0°-359°, with equal intervals of 1°. Finally, after preprocessing, each meteorological radar base data generates standard multi-elevation radar echo reflectivity data with the dimensions of elevation (9) × storage length (300) × azimuth (360); the high temporal and spatial resolution multi-elevation radar echo reflectivity data for 2 consecutive hours is: forecast time (20) × elevation (9) × storage length (300) × azimuth (360).

[0037] 2. The radar echo data at each elevation angle is independently encoded into the corresponding subspace to obtain the subspace feature representation of each elevation angle.

[0038] Radar echo data at each elevation angle corresponds to a separate subspace encoder. This encoder is tailored for each elevation angle and employs a convolutional neural network (CNN) architecture to extract elevation-specific meteorological features. The output of the subspace encoder is represented as a high-dimensional vector, capturing the unique characteristics of each elevation angle. Figure 2 The subspace coding structure of a single elevation angle data is shown, with an emphasis on the encoding process of the convolutional neural network.

[0039] Subspace encoder design:

[0040] Suppose we choose an elevation angle of 3.4°.

[0041] (1) Convolutional layer design

[0042] 1) Convolution kernel size: Depending on the spatial resolution and feature scale of the 3.4° elevation data, we may choose convolution kernels of different sizes, such as 3×3, stride 2, and padding 2. For example, if the data contains large-scale meteorological features (such as large clouds), we may choose a larger convolution kernel to capture these features.

[0043] 2) Number of convolution kernels: Depending on the complexity of the features, we may need multiple convolution kernels to capture features of different scales.

[0044] For example, we might use 16 convolution kernels to capture basic features and 32 convolution kernels to capture finer features.

[0045] (2) Pooling layer design

[0046] Pooling strategy: To reduce feature dimensionality and extract key information, we may use maximum pooling or average pooling after the convolution layer. The size of the pooling window can be selected according to the spatial resolution of the data and the required feature abstraction level.

[0047] (3) Activation function layer

[0048] Activation function selection: To introduce nonlinearity, we may choose ReLU or Leaky ReLU as the activation function. These functions can help the model learn more complex feature representations.

[0049] (4) Adjustment and optimization

[0050] 1) Number of layers and depth: Depending on the complexity of the elevation data, we may need to adjust the depth of the network, increasing or decreasing the number of layers to optimize performance.

[0051] 2) Regularization and Normalization: To prevent overfitting, we may add a Dropout layer or a LayerNormalization layer to the network.

[0052] In this embodiment, a convolutional subspace encoder is configured to extract features from radar echo data. The subspace encoder structure comprises convolutional layers, pooling layers, and activation function layers, which are used to extract radar signature information at corresponding elevation angles. The convolution kernel size, number of layers, and activation function can be adjusted based on the characteristics of the data at each elevation angle to enhance the model's adaptability to the characteristics of each elevation angle.

[0053] 3. Integrate the subspace feature representations corresponding to each elevation angle to form a complete latent vector space.

[0054] The complete latent vector space contains feature information at multiple elevation angles, which can represent meteorological information at different altitudes, fully express the atmospheric structure in the vertical direction, and increase the ability to capture the vertical structure of the atmosphere.

[0055] In this embodiment, a multi-head self-attention mechanism is used to weight and integrate the subspace feature representations corresponding to each elevation angle. The multi-head self-attention mechanism allows the model to weight data at different elevation angles according to their importance, ensuring that data at important elevation angles has a higher weight in the joint representation.

[0056] Multi-head self-attention mechanism:

[0057] The input of the Multi-Head Attention (MHA) mechanism consists of three vectors: a query vector (query), a key vector (key), and a value vector (value). For a given query vector, MHA performs a weighted sum of the key vectors, where the weight is calculated based on the similarity between the query vector and the key vector, and then multiplies the weighted sum by the value vector for output. The calculation formula for MHA is shown in Formula 1:

[0058] MultiHead(Q,K,V)=Concat(head1,…,head h )W O (1)

[0059] Where Q, K, V represent the query vector, key vector, and value vector respectively, h represents the number of heads, headi represents the output of the i-th head, and WO is the output transformation matrix. The output of each head headi can be expressed as Formula 2:

[0060]

[0061] in are the query, key, and value transformation matrices of the i-th head, respectively. Attention is the attention calculation function. In MHA, the self-attention mechanism is generally used to calculate attention.

[0062] The calculation of the self-attention mechanism can be expressed as the following formula 3:

[0063]

[0064] where d k is the dimension of the key vector, the softmax similarity is normalized, the weight of each key vector is calculated, and then the weight is multiplied by the value vector, and finally the weighted sum is performed to obtain the attention output.

[0065] The MHA process can be summarized into the following steps:

[0066] 1) Divide the input sequence data into multiple headers;

[0067] 2) Perform independent query, key, and value linear transformations on each header;

[0068] 3) Perform self-attention calculation on each head to obtain the output of the head;

[0069] 4) Concatenate the outputs of all heads together and perform a linear transformation on the outputs.

[0070] 4. Combination Figure 3 As shown, the geographic location data of the radar station is encoded to obtain spatial location embedding information.

[0071] The spatial location embedding information is used to assist the spatial positioning of the model. The geographic location data of the radar station includes longitude, latitude and altitude.

[0072] The geographic location data of the radar stations are embedded into independent vector spaces, which can be achieved based on methods such as embedding layers or sine and cosine functions. These vector spaces are then integrated into a comprehensive spatial position representation to enhance the spatial characteristic expression of the spatiotemporal sequence model and ensure the model's accurate spatial positioning.

[0073] 5. Combination Figure 4 As shown, the time period information is encoded to obtain the time period embedded information.

[0074] In this embodiment, the time period information includes months and hours. This time period information is periodically encoded, i.e., the months and hours are converted into time period embedding information using sine and cosine functions. This time period information is then converted into a vector representation to represent the periodic characteristics of the months and hours. The generated time period embedding information can help the model understand periodic weather phenomena such as seasonality and diurnal variations, providing support for long-term forecasting of weather systems.

[0075] The specific formula for generating time period embedded information includes:

[0076] Month code: Use and Perform periodic representation;

[0077] Hour coding: Use and Perform periodic representation.

[0078] 6. Integrate the latent vector space with the spatial position embedding information and the time period embedding information as the input vector to the pre-trained time series model to capture the temporal and spatial dependencies and evolution laws of convective weather systems and predict the multi-elevation angle radar echo reflectivity within the next 2 hours.

[0079] In this embodiment, if Figure 5 As shown in the figure, the time series model is built based on the Transformer network, which includes several self-attention layers and feedforward neural network layers. Each layer captures the spatiotemporal dependencies of radar echo data through the self-attention mechanism and decodes and generates the multi-elevation-angle radar echo reflectivity within the next 2 hours.

[0080] The embodiments of the present invention achieve high-temporal-spatial resolution radar echo reflectivity forecasting through subspace coding, feature integration, and the assistance of spatial position and time period information, combined with spatiotemporal sequence modeling, and maximize the application of radar detection data information. This lays a solid foundation for research on the identification, tracking, and early warning of severe convective weather systems based on multi-elevation-angle radar echo reflectivity, and has significant innovation and application prospects.

[0081] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A radar echo data processing method based on multi-elevation subspace coding, characterized in that: The following steps are involved: S1. Preprocessing multi-elevation-angle weather radar base data; S2. For the pre-processed weather radar base data, independently encode the radar echo reflectivity at each elevation angle into the corresponding subspace to obtain the subspace feature representation of each elevation angle; S3, integrating the subspace feature representations corresponding to each elevation angle to form a complete latent vector space; S4. Integrating the latent vector space with spatial position embedding information generated by encoding the geographic location data of the radar station and periodic time embedding information generated by sine and cosine functions according to the month and hour as input vectors into a pre-trained time series model to capture the spatiotemporal dependencies and evolution patterns of convective weather systems and forecast the multi-elevation radar echo reflectivity within the next two hours; the time series model is constructed based on a deep learning network with a self-attention mechanism; The geographical location data of the radar station includes longitude, latitude and altitude.

2. The method according to claim 1, characterized in that In step S1, the method for preprocessing the multi-elevation-angle weather radar base data includes radar base data decoding and elevation angle data normalization processing.

3. The method according to claim 1, characterized in that In step S2, the radar echo reflectivity at each elevation angle corresponds to an independent subspace encoder, and the subspace encoder is a convolutional encoder including a convolution layer, a pooling layer, and an activation function layer.

4. The method according to claim 1, wherein In step S3, the subspace feature representation corresponding to each elevation angle is weighted and integrated through the attention mechanism.

5. The method according to claim 1, characterized in that The encoding of the radar station's geographic location data is to embed the radar station's geographic location data into independent vector spaces respectively, and then integrate them into a comprehensive spatial location representation.

6. The method according to claim 1, characterized in that The time series model is built based on the Transformer network, which includes several self-attention layers and feedforward neural network layers. Each layer captures the temporal dependency of radar echo data through the self-attention mechanism.

7. The method according to claim 1, characterized in that The multi-elevation-angle radar echo reflectivity within the next 2 hours has a time resolution of 6 minutes and a spatial resolution of the radar echo library length. The multiple elevation angles specifically include: 0.5°, 1.5°, 2.4°, 3.4°, 4.3°, 6.0°, 9.9°, 14.6° and 19.5°.

8. A radar echo data processing system, characterized in that: include: Data receiving module, used for receiving multi-elevation-angle radar volume scanning data and performing pre-processing; Subspace encoding module, used to independently encode radar echo reflectivity at different elevation angles into corresponding subspaces; Feature integration module, used to integrate the subspace feature representations of each elevation angle into a complete latent vector space; A position encoding module, configured to generate spatial position embedding information based on the geographic location data of the radar station, wherein the geographic location data of the radar station includes longitude, latitude, and altitude; Time period encoding module, used to generate periodic time embedding information based on months and hours through sine and cosine functions; The spatiotemporal sequence prediction module integrates the latent vector space, spatial position embedding information, and time period embedding information, and performs fusion prediction based on the time series model to output the multi-elevation-angle radar echo reflectivity every 6 minutes within the next 2 hours.

Images