Pandemic model with data-driven phase detection, a study using COVID-19 data

The recent COVID-19 pandemic has promoted vigorous scientific activity in an effort to understand, advice and control the pandemic. Data is now freely available at a staggering rate worldwide. Unfortunately, this unprecedented level of information contains variety data sources formats, models do not always conform description data. Health officials have recognized need for more accurate that can adjust sudden changes, such as produced by changes behavior or social restrictions. In work we formulate model fits ``SIR''-type concurrently with statistical change detection test on result piece wise autonomous ordinary differential equation, whose parameters various points time (automatically learned from data). main contributions our are: (a) providing interpretation parameters, (b) determining which are important produce spread disease, (c) using data-driven discovery evolution Together, these characteristics provide new better describes situation thus, provides quality decision making.