Weather radar echo is the data detected by the weather radar sensor and reflects the intensity of meteorological targets. Using the technique of radar echo extrapolation, which is the prediction of future echoes based on historical echo observations, the approaching short-term weather conditions can be forecasted, and warnings can be raised with regard to disastrous weather. Recently, deep learning based extrapolation methods have been proposed and show significant application potential. However, there are two limitations of existing extrapolation methods which should be considered. First, few methods have investigated the impact of the evolutionary process of weather systems on extrapolation accuracy. Second, current deep learning methods usually encounter the problem of blurry echo prediction as extrapolation goes deeper. In this paper, we aim to address the two problems by proposing a Multi-Level Correlation Long Short-Term Memory (MLC-LSTM) and integrate the adversarial training into our approach. The MLC-LSTM can exploit the spatiotemporal correlation between multi-level radar echoes and model their evolution, while the adversarial training can help the model extrapolate realistic and sharp echoes. To train and test our model, we build a real-life multi-level weather radar echoes dataset based on raw CINRAD/SA radar observations provided by the National Meteorological Information Center, China. Extrapolation experiments show that our model can accurately forecast the motion and evolution of an echo while keeping the predicted echo looking realistic and fine-grained. For quantitative evaluation on probability of detection (POD), false alarm rate (FAR), critical success index (CSI), and Heidke skill score (HSS) metrics, our model can reach average scores of 0.6538 POD, 0.2818 FAR, 0.5348 CSI, and 0.6298 HSS, respectively when extrapolating 15 echoes into the future, which outperforms the current state-of-the-art extrapolation methods. Both the qualitative and quantitative experimental results demonstrate the effectiveness of our model, suggesting that it can be effectively applied to operational weather forecasting practice.

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.

The ability to monitor and predict sea temperature is crucial for determining the likelihood that ocean-related events will occur. However, most studies have focused on predicting sea surface temperature, and less attention has been paid to predicting sea subsurface temperature (SSbT), which can reflect the thermal state of the entire ocean. In this study, we use a 3D U-Net model to predict the SSbT in the upper 400 m of the Pacific Ocean and its adjacent oceans for lead times of 12 months. Two reconstructed SSbT products are added to the training set to solve the problem of insufficient observation data. Experimental results indicate that this method can predict the ocean temperature more accurately than previous methods in most depth layers. The root mean square error and mean absolute error of the predicted SSbT fields for all lead times are within 0.5–0.7 °C and 0.3–0.45 °C, respectively, while the average correlation coefficient scores of the predicted SSbT profiles are above 0.96 for almost all lead times. In addition, a case study qualitatively demonstrates that the 3D U-Net model can predict realistic SSbT variations in the study area and, thus, facilitate understanding of future changes in the thermal state of the subsurface ocean.

Radar quantitative precipitation estimation (RQPE) is the most common measurement for area rainfall estimation with high spatial and temporal resolution. The radar reflectivity ( $Z$ ) measured by the Doppler weather radar is strongly related to precipitation rate ( $R$ ). However, conventional RQPE methods have limited capability of modeling the complex relationship between the radar echoes and the precipitation field. In this article, we propose a graph neural network (GNN)-based RQPE model named categorical node graph attention network (CNGAT) to model complex spatial–temporal features of precipitation field reflected by the radar echo field. CNGAT is derived from graph attention networks (GAT) utilizing attention mechanism to learn the importance of neighboring points to the central point, which is beneficial for learning varying local spatial patterns. Furthermore, CNGAT can handle multiple types of graph nodes by using different transform functions for different types of nodes, which makes it better at capturing diverse features of precipitation field indicated by strong and weak radar echo areas. The proposed model was trained and tested on radar network and rain gauge data distributed in East China during 2017 and 2018. The results of several experiments show that CNGAT greatly improves the estimation precision and detection rate than $Z$ – $R$ relation models and conventional data-driven RQPE methods, and alleviates under-estimation of higher precipitation rates, which validates that CNGAT can effectively represent complex spatial–temporal features of precipitation field.

Weather radar echo is one of the fundamental data for meteorological workers to weather systems identification and classification. Through the technique of weather radar echo extrapolation, the future short-term weather conditions can be predicted and severe convection storms can be warned. However, traditional extrapolation methods cannot offer accurate enough extrapolation results since their modeling capacity is limited, the recent deep learning based methods make some progress but still remains a problem of blurry prediction when making deeper extrapolation, which may due to they choose the mean square error as their loss function and that will lead to losing echo details. To address this problem and make a more realistic and accurate extrapolation, we propose a deep learning model called Adversarial Extrapolation Neural Network (AENN), which is a Generative Adversarial Network (GAN) structure and consist of a conditional generator and two discriminators, echo-frame discriminator and echo-sequence discriminator. The generator and discriminators are trained alternately in an adversarial way to make the final extrapolation results be realistic and accurate. To evaluate the model, we conduct experiments on extrapolating 0.5h, 1h, and 1.5h imminent future echoes, the results show that our proposed AENN can achieve the expected effect and outperforms other models significantly, which has a powerful potential application value for short-term weather forecasting.