Accurate precipitation nowcasting can provide great convenience to the public so they can conduct corresponding arrangements in advance to deal with the possible impact of upcoming heavy rain.Recent relevant research ...Accurate precipitation nowcasting can provide great convenience to the public so they can conduct corresponding arrangements in advance to deal with the possible impact of upcoming heavy rain.Recent relevant research activities have shown their concerns on various deep learning models for radar echo extrapolation,where radar echo maps were used to predict their consequent moment,so as to recognize potential severe convective weather events.However,these approaches suffer from an inaccurate prediction of echo dynamics and unreliable depiction of echo aggregation or dissipation,due to the size limitation of convolution filter,lack of global feature,and less attention to features from previous states.To address the problems,this paper proposes a CEMA-LSTM recurrent unit,which is embedded with a Contextual Feature Correlation Enhancement Block(CEB)and a Multi-Attention Mechanism Block(MAB).The CEB enhances contextual feature correlation and supports its model to memorize significant features for near-future prediction;the MAB uses a position and channel attention mechanism to capture global features of radar echoes.Two practical radar echo datasets were used involving the FREM and CIKM 2017 datasets.Both quantification and visualization of comparative experimental results have demonstrated outperformance of the proposed CEMA-LSTMover recentmodels,e.g.,PhyDNet,MIM and PredRNN++,etc.In particular,compared with the second-rankedmodel,its average POD,FAR and CSI have been improved by 3.87%,1.65%and 1.79%,respectively on the FREM,and by 1.42%,5.60%and 3.16%,respectively on the CIKM 2017.展开更多
This study proposes a novel radar echo extrapolation algorithm,OF-ConvGRU,which integrates Optical Flow(OF)and Convolutional Gated Recurrent Unit(ConvGRU)methods for improved nowcasting.Using the Standardized Radar Da...This study proposes a novel radar echo extrapolation algorithm,OF-ConvGRU,which integrates Optical Flow(OF)and Convolutional Gated Recurrent Unit(ConvGRU)methods for improved nowcasting.Using the Standardized Radar Dataset of the Guangdong-Hong Kong-Macao Greater Bay Area,the performance of OF-ConvGRU was evaluated against OF and ConvGRU methods.Threat Score(TS)and Bias Score(BIAS)were employed to assess extrapolation accuracy across various echo intensities(20-50 dBz)and weather phenomena.Results demonstrate that OF-ConvGRU significantly enhances prediction accuracy for moderate-intensity echoes(30-40 dBz),effectively combining OF s precise motion estimation with ConvGRU s nonlinear learning capabilities.However,challenges persist in low-intensity(20 dBz)and high-intensity(50 dBz)echo predictions.The study reveals distinct advantages of each method in specific contexts,highlighting the importance of multi-method approaches in operational nowcasting.OF-ConvGRU shows promise in balancing short-term accuracy with long-term stability,particularly for complex weather systems.展开更多
Weather radar echo extrapolation plays a crucial role in weather forecasting.However,traditional weather radar echo extrapolation methods are not very accurate and do not make full use of historical data.Deep learning...Weather radar echo extrapolation plays a crucial role in weather forecasting.However,traditional weather radar echo extrapolation methods are not very accurate and do not make full use of historical data.Deep learning algorithms based on Recurrent Neural Networks also have the problem of accumulating errors.Moreover,it is difficult to obtain higher accuracy by relying on a single historical radar echo observation.Therefore,in this study,we constructed the Fusion GRU module,which leverages a cascade structure to effectively combine radar echo data and mean wind data.We also designed the Top Connection so that the model can capture the global spatial relationship to construct constraints on the predictions.Based on the Jiangsu Province dataset,we compared some models.The results show that our proposed model,Cascade Fusion Spatiotemporal Network(CFSN),improved the critical success index(CSI)by 10.7%over the baseline at the threshold of 30 dBZ.Ablation experiments further validated the effectiveness of our model.Similarly,the CSI of the complete CFSN was 0.004 higher than the suboptimal solution without the cross-attention module at the threshold of 30 dBZ.展开更多
The noise robustness and parameter estimation performance of the classical three-dimensional estimating signal parameter via rotational invariance techniques(3D-ESPRIT)algorithm are poor when the parameters of the geo...The noise robustness and parameter estimation performance of the classical three-dimensional estimating signal parameter via rotational invariance techniques(3D-ESPRIT)algorithm are poor when the parameters of the geometric theory of the diffraction(GTD)model are estimated at low signal-to-noise ratio(SNR).To solve this problem,a modified 3D-ESPRIT algorithm is proposed.The modified algorithm improves the parameter estimation accuracy by proposing a novel spatial smoothing technique.Firstly,we make cross-correlation of the auto-correlation matrices;then by averaging the cross-correlation matrices of the forward and backward spatial smoothing,we can obtain a novel equivalent spatial smoothing matrix.The formula of the modified algorithm is derived and the performance of this improved method is also analyzed.Then we compare root-meansquare-errors(RMSEs)of different parameters and the locating accuracy obtained by different algorithms.Furthermore,radar cross section(RCS)of radar targets is extrapolated.Simulation results verify the effectiveness and superiority of the modified 3DESPRIT algorithm.展开更多
Accurate nowcasting provides key information for disaster weather warnings.Nowcasting is mostly based on radar echo extrapolation,where the echo evolution results from complex interactions among cloud systems and vari...Accurate nowcasting provides key information for disaster weather warnings.Nowcasting is mostly based on radar echo extrapolation,where the echo evolution results from complex interactions among cloud systems and various thermal–dynamic features of the weather background.However,existing research has not integrated high spatiotemporal resolution weather background information.In this study,multiple data fusion units(Radarcells)integrating the radar mosaic and rapid-refresh data are constructed as input for the radar echo extrapolation network architecture designed according to Attention-Resnet Unet with Radarcells(ARUR).In addition,a self-defined loss function combining weighted mean square error and structural similarity index is further proposed to improve the extrapolation effect.The rapid-refresh data includes relative humidity,zonal wind,meridional wind,and vertical velocity within the range from 115.48 to 117.48°E,38.81 to 40.81°N during June–August from 2018 to 2021.Four ARUR-based models with different Radarcells as input and an ARU-based model(Attention-Resnet Unet,without fusing physical data)are trained for 120 min of extrapolation,respectively.The models are evaluated with the indicators,including critical success index(CSI),probability of detection(POD),and false alarm rate(FAR),by the test dataset.The results show that the performance of echo prediction and timeliness by ARUR-based models is better than the ARU-based model,especially for strong echo prediction.Under the reflectivity thresholds of 25 and 35 d BZ,the average values of CSI,FAR,and POD calculated by ARUR-based models are improved by 8.42%,7.76%,8.52%and 10.36%,7.36%,9.10%than those by ARU-based,respectively.The study suggests that integrating weather background information can significantly enhance the effect of extrapolation by means of improving the issues of echo blurriness,formation,and dissipation compared with the previous deep learning-based models.展开更多
Precipitation nowcasting is of great significance for severe convective weather warnings.Radar echo extrapolation is a commonly used precipitation nowcasting method.However,the traditional radar echo extrapolation met...Precipitation nowcasting is of great significance for severe convective weather warnings.Radar echo extrapolation is a commonly used precipitation nowcasting method.However,the traditional radar echo extrapolation methods are encountered with the dilemma of low prediction accuracy and extrapolation ambiguity.The reason is that those methods cannot retain important long-term information and fail to capture short-term motion information from the long-range data stream.In order to solve the above problems,we select the spatiotemporal long short-term memory(ST-LSTM)as the recurrent unit of the model and integrate the 3D convolution operation in it to strengthen the model’s ability to capture short-term motion information which plays a vital role in the prediction of radar echo motion trends.For the purpose of enhancing the model’s ability to retain long-term important information,we also introduce the channel attention mechanism to achieve this goal.In the experiment,the training and testing datasets are constructed using radar data of Shanghai,we compare our model with three benchmark models under the reflectance thresholds of 15 and 25.Experimental results demonstrate that the proposed model outperforms the three benchmark models in radar echo extrapolation task,which obtains a higher accuracy rate and improves the clarity of the extrapolated image.展开更多
基金funding from the Key Laboratory Foundation of National Defence Technology under Grant 61424010208National Natural Science Foundation of China(Nos.62002276,41911530242 and 41975142)+3 种基金5150 Spring Specialists(05492018012 and 05762018039)Major Program of the National Social Science Fund of China(Grant No.17ZDA092)333 High-LevelTalent Cultivation Project of Jiangsu Province(BRA2018332)Royal Society of Edinburgh,UK andChina Natural Science Foundation Council(RSE Reference:62967)_Liu)_2018)_2)under their Joint International Projects Funding Scheme and Basic Research Programs(Natural Science Foundation)of Jiangsu Province(BK20191398 and BK20180794).
文摘Accurate precipitation nowcasting can provide great convenience to the public so they can conduct corresponding arrangements in advance to deal with the possible impact of upcoming heavy rain.Recent relevant research activities have shown their concerns on various deep learning models for radar echo extrapolation,where radar echo maps were used to predict their consequent moment,so as to recognize potential severe convective weather events.However,these approaches suffer from an inaccurate prediction of echo dynamics and unreliable depiction of echo aggregation or dissipation,due to the size limitation of convolution filter,lack of global feature,and less attention to features from previous states.To address the problems,this paper proposes a CEMA-LSTM recurrent unit,which is embedded with a Contextual Feature Correlation Enhancement Block(CEB)and a Multi-Attention Mechanism Block(MAB).The CEB enhances contextual feature correlation and supports its model to memorize significant features for near-future prediction;the MAB uses a position and channel attention mechanism to capture global features of radar echoes.Two practical radar echo datasets were used involving the FREM and CIKM 2017 datasets.Both quantification and visualization of comparative experimental results have demonstrated outperformance of the proposed CEMA-LSTMover recentmodels,e.g.,PhyDNet,MIM and PredRNN++,etc.In particular,compared with the second-rankedmodel,its average POD,FAR and CSI have been improved by 3.87%,1.65%and 1.79%,respectively on the FREM,and by 1.42%,5.60%and 3.16%,respectively on the CIKM 2017.
基金Scientific Research and Development Project of Hebei Meteorological Bureau(23ky08).
文摘This study proposes a novel radar echo extrapolation algorithm,OF-ConvGRU,which integrates Optical Flow(OF)and Convolutional Gated Recurrent Unit(ConvGRU)methods for improved nowcasting.Using the Standardized Radar Dataset of the Guangdong-Hong Kong-Macao Greater Bay Area,the performance of OF-ConvGRU was evaluated against OF and ConvGRU methods.Threat Score(TS)and Bias Score(BIAS)were employed to assess extrapolation accuracy across various echo intensities(20-50 dBz)and weather phenomena.Results demonstrate that OF-ConvGRU significantly enhances prediction accuracy for moderate-intensity echoes(30-40 dBz),effectively combining OF s precise motion estimation with ConvGRU s nonlinear learning capabilities.However,challenges persist in low-intensity(20 dBz)and high-intensity(50 dBz)echo predictions.The study reveals distinct advantages of each method in specific contexts,highlighting the importance of multi-method approaches in operational nowcasting.OF-ConvGRU shows promise in balancing short-term accuracy with long-term stability,particularly for complex weather systems.
基金National Natural Science Foundation of China(42375145)The Open Grants of China Meteorological Admin-istration Radar Meteorology Key Laboratory(2023LRM-A02)。
文摘Weather radar echo extrapolation plays a crucial role in weather forecasting.However,traditional weather radar echo extrapolation methods are not very accurate and do not make full use of historical data.Deep learning algorithms based on Recurrent Neural Networks also have the problem of accumulating errors.Moreover,it is difficult to obtain higher accuracy by relying on a single historical radar echo observation.Therefore,in this study,we constructed the Fusion GRU module,which leverages a cascade structure to effectively combine radar echo data and mean wind data.We also designed the Top Connection so that the model can capture the global spatial relationship to construct constraints on the predictions.Based on the Jiangsu Province dataset,we compared some models.The results show that our proposed model,Cascade Fusion Spatiotemporal Network(CFSN),improved the critical success index(CSI)by 10.7%over the baseline at the threshold of 30 dBZ.Ablation experiments further validated the effectiveness of our model.Similarly,the CSI of the complete CFSN was 0.004 higher than the suboptimal solution without the cross-attention module at the threshold of 30 dBZ.
基金This work was supported by the National Natural Science Foundation of China(61372033).
文摘The noise robustness and parameter estimation performance of the classical three-dimensional estimating signal parameter via rotational invariance techniques(3D-ESPRIT)algorithm are poor when the parameters of the geometric theory of the diffraction(GTD)model are estimated at low signal-to-noise ratio(SNR).To solve this problem,a modified 3D-ESPRIT algorithm is proposed.The modified algorithm improves the parameter estimation accuracy by proposing a novel spatial smoothing technique.Firstly,we make cross-correlation of the auto-correlation matrices;then by averaging the cross-correlation matrices of the forward and backward spatial smoothing,we can obtain a novel equivalent spatial smoothing matrix.The formula of the modified algorithm is derived and the performance of this improved method is also analyzed.Then we compare root-meansquare-errors(RMSEs)of different parameters and the locating accuracy obtained by different algorithms.Furthermore,radar cross section(RCS)of radar targets is extrapolated.Simulation results verify the effectiveness and superiority of the modified 3DESPRIT algorithm.
基金Supported by the Key Laboratory of High Impact Weather(special)China Meteorological Administration(2024-K-02)+3 种基金Key Laboratory of South China Sea Meteorological Disaster Prevention and Mitigation of Hainan Province(SCSF202301)Natural Science Foundation of Hebei Province of China(D2024304002)Open Founds of China Meteorological Administration Hydro–Meteorology Key Laboratory(23SWQXM007)Innovation and Development Project of China Meteorological Administration(CXFZ2025J106)。
文摘Accurate nowcasting provides key information for disaster weather warnings.Nowcasting is mostly based on radar echo extrapolation,where the echo evolution results from complex interactions among cloud systems and various thermal–dynamic features of the weather background.However,existing research has not integrated high spatiotemporal resolution weather background information.In this study,multiple data fusion units(Radarcells)integrating the radar mosaic and rapid-refresh data are constructed as input for the radar echo extrapolation network architecture designed according to Attention-Resnet Unet with Radarcells(ARUR).In addition,a self-defined loss function combining weighted mean square error and structural similarity index is further proposed to improve the extrapolation effect.The rapid-refresh data includes relative humidity,zonal wind,meridional wind,and vertical velocity within the range from 115.48 to 117.48°E,38.81 to 40.81°N during June–August from 2018 to 2021.Four ARUR-based models with different Radarcells as input and an ARU-based model(Attention-Resnet Unet,without fusing physical data)are trained for 120 min of extrapolation,respectively.The models are evaluated with the indicators,including critical success index(CSI),probability of detection(POD),and false alarm rate(FAR),by the test dataset.The results show that the performance of echo prediction and timeliness by ARUR-based models is better than the ARU-based model,especially for strong echo prediction.Under the reflectivity thresholds of 25 and 35 d BZ,the average values of CSI,FAR,and POD calculated by ARUR-based models are improved by 8.42%,7.76%,8.52%and 10.36%,7.36%,9.10%than those by ARU-based,respectively.The study suggests that integrating weather background information can significantly enhance the effect of extrapolation by means of improving the issues of echo blurriness,formation,and dissipation compared with the previous deep learning-based models.
基金This work was supported by the National Natural Science Foundation of China(Grant No.42075007)the Open Grants of the State Key Laboratory of Severe Weather(No.2021LASW-B19).
文摘Precipitation nowcasting is of great significance for severe convective weather warnings.Radar echo extrapolation is a commonly used precipitation nowcasting method.However,the traditional radar echo extrapolation methods are encountered with the dilemma of low prediction accuracy and extrapolation ambiguity.The reason is that those methods cannot retain important long-term information and fail to capture short-term motion information from the long-range data stream.In order to solve the above problems,we select the spatiotemporal long short-term memory(ST-LSTM)as the recurrent unit of the model and integrate the 3D convolution operation in it to strengthen the model’s ability to capture short-term motion information which plays a vital role in the prediction of radar echo motion trends.For the purpose of enhancing the model’s ability to retain long-term important information,we also introduce the channel attention mechanism to achieve this goal.In the experiment,the training and testing datasets are constructed using radar data of Shanghai,we compare our model with three benchmark models under the reflectance thresholds of 15 and 25.Experimental results demonstrate that the proposed model outperforms the three benchmark models in radar echo extrapolation task,which obtains a higher accuracy rate and improves the clarity of the extrapolated image.
