Explore the vast range of titles available.

Radar echo extrapolation is a commonly used approach for convective nowcasting. The evolution of convective systems over a very short term can be foreseen according to the extrapolated reflectivity images. Recently, deep neural networks have been widely applied to radar echo extrapolation and have achieved better forecasting performance than traditional approaches. However, it is difficult for existing methods to combine predictive flexibility with the ability to capture temporal dependencies at the same time. To leverage the advantages of the previous networks while avoiding the mentioned limitations, a 3D-UNet-LSTM model, which has an extractor-forecaster architecture, is proposed in this paper. The extractor adopts 3D-UNet to extract comprehensive spatiotemporal features from the input radar images. In the forecaster, a newly designed Seq2Seq network exploits the extracted features and uses different convolutional long short-term memory (ConvLSTM) layers to iteratively generate hidden states for different future timestamps. Finally, the hidden states are transformed into predicted radar images through a convolutional layer. We conduct 0–1 h convective nowcasting experiments on the public MeteoNet dataset. Quantitative evaluations demonstrate the effectiveness of the 3D-UNet extractor, the newly designed forecaster, and their combination. In addition, case studies qualitatively demonstrate that the proposed model has a better spatiotemporal modeling ability for the complex nonlinear processes of convective echoes.

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-LSTM over recent models, e.g., PhyDNet, MIM and PredRNN++, etc. In particular, compared with the second-ranked model, 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.

Deep-learning-based radar echo extrapolation methods have achieved remarkable progress in the precipitation nowcasting field. However, they suffer from a common notorious problem—they tend to produce blurry predictions. Although some efforts have been made in recent years, the blurring problem is still under-addressed. In this work, we propose three effective strategies to assist deep-learning-based radar echo extrapolation methods to achieve more realistic and detailed prediction. Specifically, we propose a spatial generative adversarial network (GAN) and a spectrum GAN to improve image fidelity. The spatial and spectrum GANs aim at penalizing the distribution discrepancy between generated and real images from the spatial domain and spectral domain, respectively. In addition, a masked style loss is devised to further enhance the details by transferring the detailed texture of ground truth radar sequences to extrapolated ones. We apply a foreground mask to prevent the background noise from transferring to the outputs. Moreover, we also design a new metric termed the power spectral density score (PSDS) to quantify the perceptual quality from a frequency perspective. The PSDS metric can be applied as a complement to other visual evaluation metrics (e.g., LPIPS) to achieve a comprehensive measurement of image sharpness. We test our approaches with both ConvLSTM baseline and U-Net baseline, and comprehensive ablation experiments on the SEVIR dataset show that the proposed approaches are able to produce much more realistic radar images than baselines. Most notably, our methods can be readily applied to any deep-learning-based spatiotemporal forecasting models to acquire more detailed results.

This paper presents a viewpoint from computer vision to the radar echo extrapolation task in the precipitation nowcasting domain. Inspired by the success of some convolutional recurrent neural network models in this domain, including convolutional LSTM, convolutional GRU and trajectory GRU, we designed a new sequence-to-sequence neural network structure to leverage these models in a realistic data context. In this design, we decreased the numbers of channels in high abstract recurrent layers rather than increasing them. We formulated the task as a problem of encoding five radar images and predicting 10 steps ahead at the pixel level, and found that using only the common mean squared error can misguide the training and mislead the testing. Especially, the image quality of last predictions usually degraded rapidly. As a solution, we employed some visual image quality assessment techniques including Structural Similarity (SSIM) and multi-scale SSIM to train our models. Experimental results show that our structure was more tolerant to increasing uncertainty in the data, and the use of image quality metrics can significantly reduce the blurry image issue. Moreover, we found that using SSIM was very effective and a combination of SSIM with mean squared error and mean absolute error yielded the best prediction quality.

This article presents an investigation into the problem of 3D radar echo extrapolation in precipitation nowcasting, using recent AI advances, together with a viewpoint from Computer Vision. While Deep Learning methods, especially convolutional recurrent neural networks, have been developed to perform extrapolation, most works use 2D radar images rather than 3D images. In addition, the very few ones which try 3D data do not show a clear picture of results. Through this study, we found a potential problem in the convolution-based prediction of 3D data, which is similar to the cross-talk effect in multi-channel radar processing but has not been documented well in the literature, and discovered the root cause. The problem was that, when we generated different channels using one receptive field, some information in a channel, especially observation errors, might affect other channels unexpectedly. We found that, when using the early-stopping technique to avoid over-fitting, the receptive field did not learn enough to cancel unnecessary information. If we increased the number of training iterations, this effect could be reduced but that might worsen the over-fitting situation. We therefore proposed a new output generation block which generates each channel separately and showed the improvement. Moreover, we also found that common image augmentation techniques in Computer Vision can be helpful for radar echo extrapolation, improving testing mean squared error of employed models at least 20% in our experiments.

In the field of weather forecasting, improving the accuracy of nowcasting is a highly researched topic, and radar echo extrapolation technology plays a crucial role in this process. Aiming to address the limitations of existing deep learning methods in radar echo extrapolation, this paper proposes a spatio-temporal long short-term memory (LSTM) network model that integrates an attention mechanism and the full-dimensional dynamic convolution technique. The multi-scale spatial and temporal features of radar images can be fully extracted by an efficient multi-scale attention module to enhance the model’s ability to perceive global and local information. The full-dimensional dynamic convolutional module introduces the dynamic attention mechanism in the spatial position and input and output channels of the convolutional kernel, adaptively adjusts the weight of the convolutional kernel, and improves the flexibility and efficiency of feature extraction. Combined with the network constructed by the above modules, the accuracy and time dependence of the model for predicting the strong echo region are significantly improved. Our experiments based on Jiangsu meteorological radar data show that the model achieved excellent results in terms of the Critical Success Index (CSI) and Heidke Skill Score (HSS), which show its efficiency and stability in predicting radar echo, especially under the condition of a high 35 dBZ threshold, and its prediction performance improved significantly. It provides an effective solution for fine short-term impending precipitation forecasting.

Radar echo extrapolation is a critical technique for short-term weather forecasting. Timely warnings of severe convective weather events can be provided according to the extrapolated images. However, traditional echo extrapolation methods fail to fully utilize historical radar echo data, resulting in limited accuracy for future radar echo prediction. Existing deep learning echo extrapolation methods often face issues such as high-threshold echo attenuation and blurring distortion. In this paper, we propose a UNet-based multi-branch feature extraction model named MBFE-UNet for radar echo extrapolation to mitigate these issues. We design a Multi-Branch Feature Extraction Block, which extracts spatiotemporal features of radar echo data from various perspectives. Additionally, we introduce a Temporal Cross Attention Fusion Unit to model the temporal correlation between features from different network layers, which helps the model to better capture the temporal evolution patterns of radar echoes. Experimental results indicate that, compared to the Transformer-based Rainformer, the MBFE-UNet achieves an average increase of 4.8% in the critical success index (CSI), 5.5% in the probability of detection (POD), and 3.8% in the Heidke skill score (HSS).

The task of precipitation nowcasting is significant in the operational weather forecast. The radar echo map extrapolation plays a vital role in this task. Recently, deep learning techniques such as Convolutional Recurrent Neural Network (ConvRNN) models have been designed to solve the task. These models, albeit performing much better than conventional optical flow based approaches, suffer from a common problem of underestimating the high echo value parts. The drawback is fatal to precipitation nowcasting, as the parts often lead to heavy rains that may cause natural disasters. In this paper, we propose a novel interaction dual attention long short-term memory (IDA-LSTM) model to address the drawback. In the method, an interaction framework is developed for the ConvRNN unit to fully exploit the short-term context information by constructing a serial of coupled convolutions on the input and hidden states. Moreover, a dual attention mechanism on channels and positions is developed to recall the forgotten information in the long term. Comprehensive experiments have been conducted on CIKM AnalytiCup 2017 data sets, and the results show the effectiveness of the IDA-LSTM in addressing the underestimation drawback. The extrapolation performance of IDA-LSTM is superior to that of the state-of-the-art methods.

Weather radar, as a crucial component of remote sensing data, plays a vital role in convective weather forecasting through radar echo extrapolation techniques. To address the limitations of existing deep learning methods in radar echo extrapolation, this paper proposes a radar echo extrapolation model based on video vision transformer and spatiotemporal sparse attention (ViViT-Prob). The model takes historical sequences as input and initially maps them into a fixed-dimensional vector space through 3D convolutional patch encoding. Subsequently, a multi-head spatiotemporal fusion module with sparse attention encodes these vectors, effectively capturing spatiotemporal relationships between different regions in the sequences. The sparse constraint enables better utilization of data structural information, enhanced focus on critical regions, and reduced computational complexity. Finally, a parallel output decoder generates all time step predictions simultaneously, then maps back to the prediction space through a deconvolution module to reconstruct high-resolution images. Our experimental results on the Moving MNIST and real radar echo dataset demonstrate that the proposed model achieves superior performance in spatiotemporal sequence prediction and improves the prediction accuracy while maintaining structural consistency in radar echo extrapolation tasks, providing an effective solution for short-term precipitation forecasting.

Precipitation nowcasting is mainly achieved by the radar echo extrapolation method. Due to the timing characteristics of radar echo extrapolation, convolutional recurrent neural networks (ConvRNNs) have been used to solve the task. Most ConvRNNs have been proven to perform far better than traditional optical flow methods, but they still have fatal problems. These models lack differentiation in the prediction of echoes of different intensities, which leads to the omission of responses from regions with high intensities. Moreover, because it is difficult for these models to capture long-term feature dependencies among multiple echo maps, the extrapolation effect declines sharply over time. This paper proposes an embedded multi-layer attention module (MLAM) to address the shortcomings of ConvRNNs. Specifically, an MLAM mainly enhances attention to critical regions in echo images and the processing of long-term spatiotemporal features through the interaction between input and memory features in the current moment. Comprehensive experiments were conducted on the radar dataset HKO-7 provided by the Hong Kong Observatory and the radar dataset HMB provided by the Hunan Meteorological Bureau. Experiments show that ConvRNNs embedded with MLAMs achieve more advanced results than standard ConvRNNs.