A precipitation nowcasting method fusing three-dimensional radar reflectivity and environmental element fields

Abstract

The present application relates to a kind of fusion three-dimensional radar reflectivity and environmental element field precipitation nowcasting method, comprising 1) collection radar reflectivity data, precipitation live data and environmental field element data;2) radar reflectivity data is converted into three-dimensional data, and precipitation live data is converted into two-dimensional precipitation grid field, and environmental field element data is converted into three-dimensional equidistance grid field, with radar reflectivity three-dimensional data and environmental field element data as input, two-dimensional precipitation grid field is label, and sample set is made;3) build precipitation nowcasting model;4) division training set, verification set and test set, train model on training set, carry out hyperparameter optimization on verification set, and carry out model test on test set;5) radar reflectivity data and environmental field data are as model input, then model output is precipitation nowcasting field.The present application fully considers the influence of environmental field and vertical direction's water vapor particle distribution and evolution on precipitation, improves precipitation nowcasting precision.

Description

Technical Field

[0001] The present invention belongs to the fields of meteorology and machine learning technology, and particularly relates to a precipitation nowcasting method that integrates three-dimensional radar reflectivity and environmental factor fields. Background Art

[0002] Precipitation nowcasting plays a vital role in weather forecasting and flood prevention. Its mission is to predict precipitation intensity at the pixel level within the forecast area based on meteorological observation data. Accurate precipitation nowcasting is crucial for this service and is crucial for preventing disastrous severe convective precipitation, reducing socioeconomic losses, and protecting people's lives and property.

[0003] Radar observation data offers advantages such as high temporal and spatial resolution, rich information, and wide coverage. Furthermore, radar reflectivity is widely used in meteorological operations, and its intensity is closely correlated with weather changes. Therefore, radar observation data is a crucial basis for precipitation nowcasting. Currently, mainstream precipitation nowcasting services are mostly based on CAPPI radar reflectivity data at a two-kilometer altitude. However, this single-layer radar reflectivity data only provides a rough representation of the horizontal distribution of water vapor particles at a two-kilometer altitude. Because cloud cells exist in three dimensions, the vertical distribution and evolution of water vapor particles also have a crucial impact on precipitation. Furthermore, the formation of severe convective precipitation is associated with strong vertical air motion. Therefore, using three-dimensional radar reflectivity data as model input allows the model to learn about the dynamics of convective weather across the entire three-dimensional space, thereby improving the accuracy of precipitation nowcasting.

[0004] Relying solely on radar observations while ignoring the impact of real-time environmental factors on convective weather changes will limit the accuracy of model forecasts. Storm dynamics and development trends are largely determined by thermal instability, vertical wind shear, and the vertical distribution of water vapor. Accurately predicting the formation, dissolution, splitting, and merging of storms based solely on radar observations is difficult.

[0005] Therefore, there is an urgent need to develop a precipitation nowcasting method that integrates three-dimensional radar reflectivity and environmental factor fields. Summary of the Invention

[0006] The purpose of the present invention is to overcome the shortcomings of the existing technology and provide a precipitation nowcasting method that integrates three-dimensional radar reflectivity and environmental factor fields. It fully utilizes the three-dimensional radar reflectivity and environmental field factor information detected by meteorological radar. At the same time, a specific structure is introduced into the model to make it pay more attention to the three-dimensional cloud clusters in the radar reflectivity data that are directly related to precipitation, thereby comprehensively improving the accuracy and interpretability of precipitation nowcasting and improving the level of precipitation nowcasting.

[0007] The present invention solves the technical problem by the following technical solutions:

[0008] A precipitation nowcasting method integrating three-dimensional radar reflectivity and environmental factor fields, the method comprising the following steps:

[0009] S1. Collect radar reflectivity data and the corresponding precipitation data for the next hour on an hourly basis. At the same time, collect environmental field element data corresponding to the radar reflectivity data, including divergence, vertical velocity, potential vorticity, potential height, specific humidity, relative humidity, and temperature.

[0010] S2. Convert the radar reflectivity data at each radar scanning moment from a polar coordinate system into three-dimensional data in a Cartesian coordinate system. Use interpolation to convert the matching real-time precipitation data of the next hour into a two-dimensional precipitation grid field. Use a bilinear interpolation algorithm to convert the environmental field element data into a three-dimensional equidistant grid field. Use the three-dimensional radar reflectivity data and the environmental field element data as input and the corresponding two-dimensional precipitation grid field of the next hour as labels to create a sample set.

[0011] S3. Build a precipitation nowcasting model using the three-dimensional radar reflectivity data integrated with environmental field elements within one hour as input and the precipitation grid field within the next hour as output;

[0012] S4. Selecting samples in the sample set with areas of strong radar reflectivity and dividing them into a training set, a validation set, and a test set, training the precipitation nowcasting model on the training set, performing hyperparameter tuning on the validation set, and performing model testing on the test set;

[0013] S5. Using the environmental field data and radar reflectivity data within any hour, the radar reflectivity data at each radar scanning moment is converted from a polar coordinate system to three-dimensional data in a Cartesian coordinate system using the method in S2, and the environmental field of each hour is converted from equal longitude and latitude to equal-distance three-dimensional grid field data. The radar reflectivity data and environmental field data within the hour are used as inputs to the model, and the model output is the precipitation nowcast field corresponding to the next hour.

[0014] Moreover, the data collected by S1 include radar reflectivity data within one hour, the longitude, latitude, hourly precipitation data of the ground rain gauge corresponding to the radar scanning area, and environmental field data corresponding to the radar scanning area.

[0015] Moreover, the S2 converts the radar reflectivity data from the polar coordinate system to three-dimensional data in the Cartesian coordinate system, which means that the radar base data is first converted from the polar coordinate system to the Cartesian coordinate system using the bilinear interpolation method in the horizontal dimension, and then interpolated in the vertical dimension to obtain three-dimensional equidistant grid field data with a horizontal resolution of 4km×4km and a vertical resolution of 0.5km.

[0016] Moreover, the S2 converts the original environmental field data of the 0.25°×0.25° equal longitude and latitude grid field into a three-dimensional equidistant grid environmental field, which means first establishing a three-dimensional equidistant grid field in the target area, where the grid center is the location of the radar site, and for each grid point to be interpolated, selecting the four nearest equal longitude and latitude grid points nearby and using bilinear interpolation to obtain the final equidistant grid field data.

[0017] Furthermore, the S2 converts the matched actual precipitation data into a two-dimensional precipitation grid field by using an interpolation method, which means using an inverse distance interpolation method to interpolate precipitation record points into a two-dimensional precipitation grid field with a horizontal resolution of 4 km×4 km.

[0018] Moreover, the S3 precipitation nowcasting model uses a three-layer ConvLSTM network based on 3D convolution to extract features from the three-dimensional radar reflectivity data every six minutes every hour, and uses the convolutional attention module CBAM to improve the spatiotemporal receptive field of the convolution module, so that the model pays more attention to areas with strong reflectivity and three-dimensional clouds related to precipitation. Upsampling and 3D convolution are used to process and extract the features of environmental field elements, so that the feature size of the environmental field matches the feature size of the three-dimensional radar reflectivity output by the last layer of ConvLSTM and then fuses them. Then, upsampling is used to fuse with the output result of the previous layer, and they are processed in sequence to finally output a two-dimensional precipitation grid field with a resolution of 4km×4km.

[0019] Moreover, the S4 training of the precipitation nowcasting model shields the influence of precipitation in the ocean area on the results, and uses the weighted mean square loss MWMSE with mask as the loss function of the model, which is defined as follows:

[0020]

[0021] Where, I (x,y) Represents the precipitation intensity at (x, y) in the observed image, I' (x,y) Represents the precipitation intensity at (x, y) in the predicted image, Mask (x,y) is a land mask, where the land points within the radar scanning range are 1 and the rest are 0. (x,y) is the weight corresponding to this point. Different weights are set according to the actual precipitation so that the model pays more attention to the heavy precipitation area.

[0022] The positive effects that the present invention can produce are:

[0023] The present invention fully considers the impact of the distribution and evolution of water vapor particles in the environmental field and the vertical direction on precipitation, uses 3D convolution to extract features related to the environmental field, uses ConvLSTM based on 3D convolution to extract the changes in radar reflectivity at different times and the hidden layer features of the impact on precipitation, and uses the convolutional attention module CBAM to make the model pay more attention to the three-dimensional spatial cloud bodies related to precipitation. Compared with the existing precipitation nowcasting model based on the CAPPI map at an altitude of 2km, the present invention fully considers the impact of the distribution and evolution of water vapor particles in the environmental field and the vertical direction on precipitation, thereby improving the accuracy of precipitation nowcasting. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a flow chart of the present invention;

[0025] Figure 2 Schematic diagram of the structure of the precipitation nowcasting model of the present invention;

[0026] Figure 3 A distribution map of radar stations at 15 different locations in North and East China used in the present invention;

[0027] Figure 4 This is a diagram showing an example of precipitation nowcasting in different environmental fields according to the present invention. DETAILED DESCRIPTION

[0028] The present invention will be further described in detail below through specific examples. The following examples are only illustrative and not restrictive, and the scope of protection of the present invention cannot be limited thereto.

[0029] like Figure 1 As shown, the present invention provides a precipitation nowcasting method that integrates three-dimensional radar reflectivity and environmental factor fields, including:

[0030] A precipitation nowcasting method integrating three-dimensional radar reflectivity and environmental factor fields is innovative in that the method comprises the following steps:

[0031] (1) S-band Doppler weather radar data were collected from May 2015 to October 2016 on an hourly basis, covering 15 radar stations in different locations in North China and East China. Detailed information such as the location of each station and the boundaries of its joint scanning range is provided in the table below. Figure 3As shown in the figure; the actual precipitation data within the effective area of ​​the designated radar station is obtained from the historical precipitation information recorded by each automatic precipitation station; the effective area of ​​the latitude and longitude information of each station is determined, and the required environmental field data is obtained from the fifth generation global atmospheric reanalysis data (ERA5) provided by the European Medium-Term Weather Forecast. The effective range of the radar reflectivity data is 512km×512km. In order to make the environmental field data better surround the effective radar reflectivity, the spatial range of the environmental field is set to 1024km×1024km.

[0032] (2) The radar reflectivity data at each radar scanning moment is converted from the polar coordinate system to three-dimensional data in the Cartesian coordinate system. The corresponding equidistant grid point environment field is constructed, where the grid point center is the location of the radar station. The longitude and latitude positions of each grid point in the equidistant grid point environment field can be calculated based on the longitude and latitude of the radar station. The calculation formula is:

[0033]

[0034] In the formula, (x r ,y r ) is the Cartesian coordinate of the radar station in the equidistant grid field, located at the center of the grid field; (x g ,y g ) is the Cartesian coordinate of the grid point to be interpolated in the equidistant grid field; (long r ,Lat r ) are the latitude and longitude coordinates of the radar station; (Long g ,Lat g ) are the latitude and longitude coordinates of the grid point to be interpolated. In order to match the radar reflectivity data of the equidistant three-dimensional grid field, the original environmental field data of equal latitude is converted into an equidistant grid environmental field using a bilinear interpolation algorithm. The bilinear interpolation method is calculated based on the latitude and longitude of the radar station as follows:

[0035]

[0036] The matching real-time precipitation data is converted into a two-dimensional precipitation grid field using interpolation. Using the three-dimensional radar reflectivity data and the corresponding environmental field data as input, and the corresponding two-dimensional precipitation grid field as the label, a sample set is generated. The 15 radars used in this example have thousands of automatic precipitation stations within their scanning ranges. Inverse distance weighted interpolation is used to interpolate the automatic station precipitation data into a precipitation grid field. The inverse distance weighted interpolation calculation method is as follows:

[0037]

[0038] Where n represents the n automatic stations closest to the grid center. In this embodiment, n=6; Ri represents the actual precipitation value provided by the i-th automatic station; k is the set power, and in this embodiment, k=2.

[0039] (3) Build a precipitation forecasting model that takes the three-dimensional radar reflectivity data and environmental field data within one hour before the forecast time as input and the precipitation field within the next hour as output. The three-dimensional radar reflectivity data of six minutes are encoded and feature extracted through the ConvLSTM network based on 3D convolution and the convolution attention module CBAM. The convolution attention module CBAM is used to improve the spatial receptive field of the model and guide the model to pay more attention to the position and change information of the three-dimensional cloud clusters related to precipitation; the environmental field encoder is composed of upsampling operations and 3D convolution. The upsampling process can make the environmental field features and radar reflectivity features match in size for feature fusion. Use upsampling and convolution to build a decoder, so that the fused features are continuously fused with the features of the previous layer through convolution, and finally a two-dimensional precipitation grid field with a resolution of 4km×4km is obtained. The model structure is as follows: Figure 2 The parameter settings are shown in Table 1.

[0040] The 3D convolution-based ConvLSTM network is derived from the 2D convolution-based ConvLSTM to extract features of three-dimensional radar reflectivity data at multiple times. The 3D convolution-based ConvLSTM network replaces the convolution in ConvLSTM with a 3D convolution operation to process the 3D radar reflectivity data obtained from the radar scan at each moment, and uses the loop structure of ConvLSTM to extract and fuse features of the 3D radar reflectivity data for six minutes in an hour. The 3D convolution-based ConvLSTM network unit has three inputs and two outputs, just like the 2D convolution-based ConvLSTM network unit. The inputs are the input x at the current moment and the output x at the current moment. t , long-term memory unit c t-1 And the state variable output h at the previous moment t-1 , the output is the updated long-term memory unit c t And the current state variable output h t Enter x t The state variable output of the previous moment is stacked on the channel dimension and then convolved. The convolution result is then sent to the forget gate f, update gate i, activation gate a, and output gate o respectively. The forget gate, update gate, activation gate, and output gate will output the corresponding feature matrix, which is then Hadamard-producted with the memory unit to update the long-term memory unit. The operations performed by the above four gates are consistent with the output c t and h t is calculated as follows:

[0041] f=Sigmoid(h t-1 / w fh +x t *w fx +b f )

[0042] i=Sigmoid(h t-1 *w ih +x t *w ix +b i )

[0043] a=Tanh(h t-1 *w ah +x t *w ax +b a )

[0044] o=Sigmoid(h t-1 *w oh +x t *w ox +b o )

[0045]

[0046]

[0047] Among them, * represents the 3D convolution operation; w represents the corresponding convolution kernel weight; Represents Hadamard.

[0048] The CBAM convolutional attention module is composed of a CAM channel attention module and a SAM spatial attention module connected in series. The channel attention module maintains the channel dimension unchanged and compresses the spatial dimension, allowing the model to focus more on meaningful information in the input data. The spatial attention module maintains the spatial dimension unchanged and compresses the channel dimension, allowing the model to focus more on the location of the target. The CBAM convolutional attention module adaptively learns channel and spatial attention weights to improve the representational capabilities of the neural network model.

[0049] The network structure of the present invention is as follows Figure 2As shown, the system consists of three parts: a radar echo sequence encoder based on a 3D convolution-based ConvLSTM network and a convolutional attention module (CBAM); an environmental field encoder constructed using 3D convolution and upsampling; and a decoder using 3D convolution. In the radar echo sequence encoder, the spatial scale of each layer's feature map varies. To make the model more sensitive to three-dimensional cloud volumes, a convolutional attention module (CBAM) is added, placing greater emphasis on areas related to rainfall. The environmental field encoder extracts environmental field features and aligns their spatial scale with that of the third-layer feature map extracted from the radar echo sequence, facilitating decoding of the fused features. These fused features are then processed through a two-dimensional convolution to produce the precipitation nowcast output.

[0050] Table 1 Encoder and decoder parameter settings

[0051]

[0052]

[0053] (4) Dividing the sample set into a training set, a validation set, and a test set, training the precipitation nowcasting model on the training set, performing hyperparameter tuning on the validation set, and performing model testing on the test set.

[0054] Each radar completes an average scan every six minutes, and environmental field data is recorded every hour. Three-dimensional radar echo data from ten consecutive moments within an hour and environmental field data from two adjacent moments are used as inputs for the precipitation nowcasting model. The gridded field of accumulated precipitation within the following hour serves as the label. A total of 7,229 samples are randomly divided into training, validation, and test sets in a 4:1:1 ratio. The resulting training set contains 4,811 samples, and the validation and test sets each contain 1,209 samples.

[0055] The precipitation nowcasting model is trained using the masked weighted squared error (MWMSE) as the model loss function to distinguish between land precipitation and ocean precipitation. The MWMSE is defined as follows:

[0056]

[0057] Where, I (x,y) Represents the precipitation intensity at (x, y) in the observed image, I' (x,y) Represents the precipitation intensity at (x, y) in the predicted image, Mask (x,y) The land mask is a mask where the land points within the radar scanning range are 1 and the rest are 0. (x,y)is the weight corresponding to the point. Different weights can be set according to the actual precipitation, so that the model pays more attention to the heavy precipitation area. (x,y) The settings are as follows:

[0058]

[0059] (5) This embodiment uses the critical success index (CSI), the fairness skill score (ETS), and the Heidke skill score (HSS) to measure the degree of consistency between the proportion of predicted precipitation exceeding a certain precipitation threshold and the proportion of actual precipitation exceeding the threshold, and uses the root mean square error (RMSE) to measure the difference between the predicted precipitation and the actual precipitation. The larger the values ​​of CSI, ETS, and HSS, the better the model performance, and the smaller the value of RMSE, the better the model performance. CSI, ETS, HSS, and RMSE are defined as follows:

[0060]

[0061]

[0062] Where y i represents the actual grid precipitation, Represents the predicted grid point precipitation, N represents the total number of grid points in the precipitation grid map, and the calculation formula of REF is as follows:

[0063]

[0064] Among them, TP, FN, FP, and TN are defined by the confusion matrix shown in Table 2:

[0065] Table 2 Confusion matrix

[0066]

[0067] In this embodiment, the corresponding precipitation nowcasting model is trained by integrating radar echo data of environmental fields such as divergence, vertical velocity, potential vorticity, potential height, specific humidity, relative humidity, and temperature. The training process is implemented based on the Pytorch architecture, and the Adams optimizer is used for parameter update. The learning rate is 0.0001, the decay coefficient is (0.9, 0.999), the batch size is 4, and each model is trained for 50 rounds. The model with the lowest MWMSE corresponding to the round on the validation set is selected as the final model for testing. The test results are shown in Table 3, and the individual examples are shown as follows: Figure 4 shown.

[0068] Table 3 Pixel-level prediction scores under different precipitation thresholds in different environmental fields

[0069]

[0070]

[0071]

[0072] From Table 3 and Figure 4 It can be seen that:

[0073] (1) Due to the characteristics of severe convective weather such as strong suddenness, fast movement speed and irregular changes, in general, whether there is an environmental field or not, with the increase of precipitation threshold, the RMSE shows an upward trend, the critical success index CSI gradually decreases, and the HSS score and ETS score gradually decrease; with the increase of precipitation threshold, the error of precipitation nowcasting also increases significantly.

[0074] (2) According to the comparison of the above experimental results, in addition to the potential height, the introduction of environmental field factors can improve the accuracy of the precipitation nowcasting model. Among them, if the precipitation threshold is set between 1mm and 20mm, the root mean square error (RMSE) is relatively reduced by 5%-27.1%, the critical success index (CSI) is relatively increased by 3%-34.7%, the HSS score is relatively increased by 2.2%-21.8%, and the ETS score is relatively increased by 3.6%-35.1%. If the precipitation threshold exceeds 20mm, the root mean square error (RMSE) is relatively reduced by 4.6%-37.1%, the critical success index (CSI) is relatively increased by 41.1%-1989%, the HSS score is relatively increased by 2.2%-141.1%, and the ETS score is relatively increased by 10.4%-198.9%. Therefore, the introduction of environmental field factors can improve the accuracy of precipitation nowcasting in heavy rainfall areas.

[0075] (3) When the precipitation threshold is below 20 mm, the precipitation nowcasting model that introduces vertical velocity significantly improves the accuracy of precipitation nowcasting better than the precipitation nowcasting model that introduces other environmental field factors, followed by the precipitation nowcasting model that introduces divergence. The precipitation nowcasting model that introduces geopotential height performs the worst, with test results similar to those of the precipitation nowcasting model without an environmental field. When the precipitation threshold exceeds 20 mm, the precipitation nowcasting model that introduces divergence performs outstandingly, maintaining relatively low error and high prediction accuracy, with RMSE and CSI of 5.6959, 7.8406, 0.5307, and 0.4111, respectively.

[0076] (4) By Figure 4 From the individual case studies, it can be seen that the precipitation nowcasting model that introduces divergence and vertical velocity is relatively accurate in predicting heavy rainfall areas compared with other models, and the precipitation intensity is roughly the same.

[0077] Although the embodiments and drawings of the present invention are disclosed for illustrative purposes, those skilled in the art will understand that various substitutions, changes and modifications are possible without departing from the spirit and scope of the present invention and the appended claims. Therefore, the scope of the present invention is not limited to the contents disclosed in the embodiments and drawings.

Claims

1. A precipitation nowcasting method integrating three-dimensional radar reflectivity and environmental factor fields, characterized by: The steps of the method are: S1. Collect radar reflectivity data and the corresponding precipitation data for the next hour on an hourly basis. At the same time, collect environmental field element data corresponding to the radar reflectivity data, including divergence, vertical velocity, potential vorticity, potential height, specific humidity, relative humidity, and temperature. S2. Convert the radar reflectivity data at each radar scanning moment from a polar coordinate system into three-dimensional data in a Cartesian coordinate system. Use interpolation to convert the matching real-time precipitation data of the next hour into a two-dimensional precipitation grid field. Use a bilinear interpolation algorithm to convert the environmental field element data into a three-dimensional equidistant grid field. Use the three-dimensional radar reflectivity data and the environmental field element data as input and the corresponding two-dimensional precipitation grid field of the next hour as labels to create a sample set. S3. Using three-dimensional radar reflectivity data that incorporates environmental field elements within one hour as input and the precipitation grid field within the next hour as output, a precipitation nowcasting model is built. The precipitation nowcasting model uses a three-layer ConvLSTM network based on 3D convolution to extract features from the three-dimensional radar reflectivity data for six minutes every hour, and uses the convolutional attention module CBAM to improve the spatiotemporal receptive field of the convolution module, so that the model pays more attention to strong reflectivity areas and three-dimensional clouds related to precipitation. Upsampling and 3D convolution are used to process and extract the features of environmental field elements, so that the feature size of the environmental field matches the feature size of the three-dimensional radar reflectivity output by the last layer of ConvLSTM and then fuses them. Then, upsampling is used to fuse with the output result of the previous layer, and the processing is sequentially processed to finally output a two-dimensional precipitation grid field with a resolution of 4km×4km. S4. Samples with strong radar reflectivity in the sample set are selected and divided into a training set, a validation set, and a test set. The precipitation nowcasting model is trained on the training set, hyperparameters are tuned on the validation set, and the model is tested on the test set. The precipitation nowcasting model is trained to mask the influence of precipitation in the ocean area on the results, and the masked weighted mean square loss (MWMSE) is used as the loss function of the model, which is defined as follows: Where, I (x,y) Represents the precipitation intensity at (x, y) in the observed image, I′ (x,y) Represents the precipitation intensity at (x, y) in the predicted image, Mask (x,y) is a land mask, where the land points within the radar scanning range are 1 and the rest are 0. (x,y) The weight corresponding to this point is set according to the actual precipitation, so that the model pays more attention to the heavy precipitation area. S5. Using the environmental field data and radar reflectivity data within any hour, the radar reflectivity data at each radar scanning moment is converted from a polar coordinate system to three-dimensional data in a Cartesian coordinate system using the method in S2, and the environmental field of each hour is converted from equal longitude and latitude to equal-distance three-dimensional grid field data. The radar reflectivity data and environmental field data within the hour are used as inputs to the model, and the model output is the precipitation nowcast field corresponding to the next hour.

2. The precipitation nowcasting method integrating three-dimensional radar reflectivity and environmental factor fields according to claim 1 is characterized by: The data collected by S1 include radar reflectivity data within one hour, the longitude, latitude, hourly precipitation data of the ground rain gauge corresponding to the radar scanning area, and environmental field data corresponding to the radar scanning area.

3. The precipitation nowcasting method integrating three-dimensional radar reflectivity and environmental factor fields according to claim 1 is characterized by: The S2 converts the radar reflectivity data from the polar coordinate system into three-dimensional data in the Cartesian coordinate system, which means first using bilinear interpolation in the horizontal dimension to convert the radar base data from the polar coordinate system to the Cartesian coordinate system, and then interpolating in the vertical dimension to obtain three-dimensional equidistant grid field data with a horizontal resolution of 4km×4km and a vertical resolution of 0.5km.

4. The precipitation nowcasting method integrating three-dimensional radar reflectivity and environmental factor fields according to claim 1 is characterized by: The S2 converts the original environmental field data of the 0.25°×0.25° equal longitude and latitude grid field into a three-dimensional equidistant grid environmental field, which means first establishing a three-dimensional equidistant grid field in the target area, where the grid center is the location of the radar site, and for each grid point to be interpolated, selecting the four nearest equal longitude and latitude grid points nearby and using bilinear interpolation to obtain the final equidistant grid field data.

5. The precipitation nowcasting method integrating three-dimensional radar reflectivity and environmental factor fields according to claim 1 is characterized by: The S2 converts the matched actual precipitation data into a two-dimensional precipitation grid field by using an interpolation method, which means using an inverse distance interpolation method to interpolate precipitation record points into a two-dimensional precipitation grid field with a horizontal resolution of 4km×4km.

Images