Prediction of Spread Trend of Epidemic Based on Spatial-Temporal Sequence

Coronavirus Disease 2019 (COVID-19) continues to spread throughout the world, and it is necessary for us implement effective methods prevent control of epidemic. In this paper, we propose a new model called Spatial–Temporal Attention Graph Convolutional Networks (STAGCN) that can analyze long-term trend COVID-19 epidemic with high accuracy. The STAGCN employs spatial graph attention network layer temporal gated convolutional capture features infectious disease data, respectively. While inherits symmetric “space-time space” structure (STGCN), enhances its ability identify diseases using spatial–temporal correlation by replacing pay more important based on adaptively adjusted feature weights at different time points. experimental results show our has lowest error rate compared other models. paper also analyzes prediction interpretable analysis provide reliable guide decision-making process during prevention control.