Improved Weather Radar Echo Extrapolation Through Wind Speed Data Fusion Using a New Spatiotemporal Neural Network Model

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.

CEMA-LSTM:Enhancing Contextual Feature Correlation for Radar Extrapolation Using Fine-Grained Echo Datasets

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.

A Novel Method for Precipitation Nowcasting Based on ST-LSTM

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.

Wavefield-extrapolation imaging for echo data of sea-bed sediment layers

Imaging sea-bed sediment layers from echo data, which are collected by a system composed of a seismic profiler and a hydrophone streamer towed behind the profiler, is a way to reconstruct the structure of sedimeat layers with acoustic wav equation. The equation which describes the wave propagation is used for backward extrapolation of echo data observed at sea surface. When the medium is homogeneous or horizontally layered, time imaging approach is valid. However, in the case where a considerable lateral variation in velocity exists, the image section processed with the time approach does not represent the real structure, because of distortions caused by thin-lens effect similar as in optics. In this case, depth imaging approach must be used for both the time-shift correction of refraction terms and the convergence of diffractions simultaneously as wavefields are downward continued. As a result, the good image can be derived to determine the structure of sea-bed sediment layers.