As a highly infectious disease,the reproduction number of coro-navirus disease 2019 (COVID-19) was estimated to be as high as 6.47 in the early stage [1].Many studies have suggested that early interventions,such as the use of masks,social distancing,self-isolation,quarantine and even lockdown of entire regions and communities,are effective in containing or at least,mitigating the spread of the virus [2].It is thus crucial to detect the early-warning signal of the COVID-19 outbreak so that a timely public health strategy can be carried out to reduce the magnitude and spread of the pandemic.However,the complex characteristics of both biological and social systems lead to the challenge of achiev-ing the real-time prediction of infectious disease outbreaks.Fur-thermore,a surveillance system for such detection can be costly,thereby resulting in the failure to detect the potential progression of epidemics in many countries that lack adequate public health infrastructure [3,4].Machine learning methods have been devel-oped in the field of forecasting [5] but generally fail to predict out-breaks of infectious diseases when there are only limited samples.Statistical and mathematical models have been proposed to describe the transmission of the current COVID-19 epidemic [6],which helps clinicians understand its spread.However,unlike time series data prediction,an outbreak is a typical nonlinear event with characteristics that develop from gradual change to drastic transi-tion,thus making the prediction of a COVID-19 outbreak rather dif-ficult.Therefore,it is of great importance to develop an effective model-free method for directly predicting such nonlinear events or for detecting early-warning signals of infectious disease out-breaks based on real-time data such as daily new cases.