Prediction of Radar Echo Space-Time Sequence Based on Improving TrajGRU Deep-Learning Model

Abstract

Nowcasting of severe convective precipitation is of great importance in meteorological disaster prevention. Radar echo extrapolation is an effective method for short-term precipitation nowcasting. The traditional radar echo extrapolation methods lack the utilization of radar historical data as well as overlooking the nonlinear motion of small- to medium-sized convective systems in radar echoes. To solve this, we propose a deep-learning model combining CNN and RNN. The model T-UNet proposed in this paper uses an efficient convolutional neural network of UNet architecture with a residual network, where the encoder and decoder networks are connected by nested dense skip paths, while a TrajGRU recurrent neural network is added at each layer, to achieve the perceptual capability of time series. The quantitative statistical evaluation showed that the use of T-UNet could improve the nowcasting skill (CSI score, HSS score) by a maximum of 10.57% and 7.80% over a 60 min prediction cycle. Further evaluation showed that T-UNet also improved the prediction accuracy and prediction performance in the strong echo region.

Radar-Based Precipitation Nowcasting Based on Improved U-Net Model

“…In the echo extrapolation task of deep learning, the commonly used loss function was the mean square error (MSE), but a large number of studies had shown that it tends to cause blurring of the predicted images, making the extrapolation of strong echoes less effective [30,31]. The balanced mean square error (BMSE) could somewhat attenuate the blurring of the prediction images caused by the increase of the forecast lead time [23]. Therefore, in this study, the MSE and BMSE loss functions were used to carry out the model training, respectively, and compare the effects of different loss functions on the prediction.…”

“…According to Hu et al [18], the main benefits of U-Net are its straightforward structure and adaptability to task requirements, which makes it possible to provide more precise small-scale rainfall nowcasting. Therefore, many scholars have restructured and improved the U-Net model in terms of convolutional blocks, sampling layers, skip connection layers, and attention mechanisms to make it suitable for the echo extrapolation task, and compared it with the traditional echo extrapolation methods and reference models to show the good performance of the optimized model [19][20][21][22][23].…”

Research on Short term Rainfall Prediction Technology Based on Deep Learning

“…Due to meteorological features such as cloud convection, there has been a significant misalignment between the two images ,as shown in the sequence of 15 radar echo images in one and a half hours in Figure 3 Even the improvement proposed in this article is rooted in the fusion and enhancement of these five models. For instance, PredRNN++, E3DLSTM, MIM, PFST-LSTM, SmaAt-UNet [24][25][26][27][28][29] primarily focus on two aspects for improvement. Firstly, they optimize the network architecture by incorporating gradient highways and Unet models.…”

A Radar Echo Extrapolation Model Based on a Dual-Branch Encoder–Decoder and Spatiotemporal GRU

“…Among them, the centroid tracking method is primarily suitable for tracking strong echoes and making short-term predictions. When radar echoes are scattered or exhibit merging and splitting phenomena, the accuracy of extrapolation forecasts is significantly affected [10][11][12]. The cross-correlation method assumes that the evolution of echoes is linear and tracks the echo regions based on the optimal correlation coefficients between neighboring temporal regions.…”