Abstract Background: Coronavirus disease 2019 (COVID-19) was first reported in Wuhan, Hubei province, China. We aimed to describe the temporal and spatial distribution and the transmission dynamics of COVID-19 and to assess whether a hybrid model can forecast the trend of COVID-19 in Hubei Province, China. Method: The data of COVID-19 cases were obtained from the websites of Chinese Center for Disease Control and Prevention, whereas the data on the resident population were obtained from the websites of Hubei Provincial Bureau of Statistics. The temporal and spatial distribution and the transmission dynamics of COVID-19 were described. A combination of autoregressive integrated moving average (ARIMA) and support vector machine was constructed to forecast the trend of COVID-19. Results: A total of 56,062 confirmed COVID-19 cases, which were mainly concentrated in Wuhan, were reported from January 16 to March 16, 2020 in Hubei Province, China. The daily number of confirmed cases exponentially increased to 3,156 before February 4, 2020, fluctuated to 4,823 before February 13, 2020, and then markedly decreased to 1 after March 16, 2020. The highest mean reproduction number R(t) of 9.48 was recorded on January 16, 2020, after which it decreased to 2.15 on February 2, 2020 and further decreased to less than 1 on February 13, 2020. In the modeling stage, the mean square error, mean absolute error, and mean absolute percentage error of the hybrid ARIMA–SVM model decreased by 98.59%, 89.19% and 89.68%, and those of SVM decreased by 98.58%, 87.71%, and 88.94%, respectively, compared with the ARIMA model. Similar results were obtained in the forecasting stage.Conclusion: Public health interventions resulted in the terminal phase of COVID-19 in Hubei province. The hybrid ARIMA–SVM model may be a reliable tool for forecasting the trend of the COVID-19 epidemic.