High-resolution short-term prediction of the COVID-19 epidemic based on spatial-temporal model modified by historical meteorological data

• DOI: 10.1016/j.fmre.2024.02.006
• Publication Date: 2024-03-05T17:37:01Z
• Authors: Bin Chen; Ruming Chen; Lin Zhao; Yuxiang Ren; Li Zhang; Yingjie Zhao; Xinbo Lian; Wei Yan; Shuoyuan Gao
• Keywords: Temporal resolution

In the global challenge of Coronavirus disease 2019 (COVID-19) pandemic, accurate prediction daily new cases is crucial for epidemic prevention and socioeconomic planning. contrast to traditional local, one-dimensional time-series data-based infection models, study introduces an innovative approach by formulating short-term problem in a region as multidimensional, gridded time series both input targets. A spatial-temporal depth model COVID-19 (ConvLSTM) presented, further ConvLSTM integrating historical meteorological factors (Meteor-ConvLSTM) refined, considering influence on propagation COVID-19. The correlation between 10 dynamic progression was evaluated, employing spatial analysis techniques (spatial autocorrelation analysis, trend surface etc.) describe temporal characteristics epidemic. Leveraging original ConvLSTM, artificial neural network layer introduced learn how impact spread, providing 5-day forecast at 0.01° × pixel resolution. Simulation results using real dataset from 3.15 outbreak Shanghai demonstrate efficacy Meteor-ConvLSTM, with reduced RMSE 0.110 increased