Spatial Prediction of COVID-19 in China Based on Machine Learning Algorithms and Geographically Weighted Regression

Shao, Qi; Xu, Yongming; Wu, Hanyi

COVID-19 has swept through the world since December 2019 and caused a large number of patients and deaths. Spatial prediction on the spread of the epidemic is greatly important for disease control and management. In this study, we predicted the cumulative confirmed cases (CCCs) from Jan 17 to Mar 1, 2020, in mainland China at the city level, using machine learning algorithms, geographically weighted regression (GWR), and partial least squares regression (PLSR) based on population flow, geolocation, meteorological, and socioeconomic variables. The validation results showed that machine learning algorithms and GWR achieved good performances. These models could not effectively predict CCCs in Wuhan, the first city that reported COVID-19 cases in China, but performed well in other cities. Random Forest (RF) outperformed other methods with a CV‐R(2) of 0.84. In this model, the population flow from Wuhan to other cities (WP) was the most important feature and the other features also made considerable contributions to the prediction accuracy. Compared with RF, GWR showed a slightly worse performance (CV‐R(2) = 0.81) but required fewer spatial independent variables. This study explored the spatial prediction of the epidemic based on multisource spatial independent variables, providing references for the estimation of CCCs in the regions lacking accurate and timely.