Predicting the transmission trend of respiratory viruses in new regions via geospatial similarity learning

Yunxiang Zhao, Mingda Hu, Yuan Jin, Fei Chen, Xin Wang, Boqian Wang, Junjie Yue, Hongguang Ren

Abstract: Highlights•We predict a region’s potential trend of early-stage respiratory infectious disease.•We collect data from NYC & SF containing geospatial features and COVID-19 case rates.•We propose RGED to generate (dis)similar regions by editing geospatial features.•We propose a trend prediction model by investigating geospatial features.