GMA: An Improved Framework of Radar Extrapolation Based on Spatiotemporal Sequence Neural Network

Most previous current spatiotemporal sequence neural networks used for radar extrapolation have difficulties in learning long‐term spatiotemporal memories. This is because the spatiotemporal sequential neural networks only use the information from the previous time step node to update the prediction state, and the networks tend to rely on the convolution layers to capture the spatiotemporal features, which are local and inefficient. In order to capture the long‐term temporal characteristics and local abrupt spatial characteristics of radar echo sequence, we propose a new framework, Global Memory Attention (GMA), which has two contributions. The first is that we establish a global information flow between calculation units, extract the key historical memory from the global information flow, calculate the correlation between the historical key memory and the current time frame prediction state, and determine how much historical memory participates in the prediction state update. It alleviates the current network's difficulty in learning the long‐term spatial and temporal characteristics of radar echo sequences and the problem of short‐term dependence, and reduces the interference of image noise in the process of radar extrapolation prediction. The second is that the GMA module is a flexible additional module that can be applied to most radar extrapolation algorithms based on timing networks. GMA has reached the highest level on radar extrapolation tasks, and we have provided ablation studies to verify the effectiveness of GMA. Plain Language Summary Spatiotemporal sequence neural networks are widely used in radar echo extrapolation tasks. However, in the past, most spatiotemporal sequence networks have short‐term dependence and long‐term dilemma. In this study, we propose a new framework, which can be applied to any radar extrapolation algorithm based on spatiotemporal sequence network. It establishes the global information flow and updates the prediction state by extracting the key historical memory strongly associated with the current prediction state through the attention module. It improves the utilization rate of long‐term information and reduces the interference of radar echo image noise, and effectively improves the problem that the extrapolation effect decreases with the increase of extrapolation time. Key Points A new spatiotemporal sequence neural network framework is proposed for radar echo extrapolation Using a series of attention calculations to