BeCaked+: An Explainable AI Model to Forecast Delta-Spreading Covid-19 Situations for Ho Chi Minh City

Cuong Nguyen, Minh Nguyen, Duc Nguyen, Thinh Nguyen, Khuong Nguyen-An, Chon Le, Tho Quan

Abstract: Covid-19 is a global disaster that needs computing power to analyze, predict and interpret. So far, there have been several models doing the job. With a huge amount of daily data, deep learning models can be trained to achieve highly accurate forecasts but their mechanism lacks explainability. Epidemiological models, e.g. SIR, on the other hand, can provide insightful analyses, but they require appropriate parameter values, which might be complicated in certain locations. The fourth wave of the pandemic in Ho Chi Minh City (HCMC), Vietnam in 2021, brought valuable lessons along with accurate and specific data. Hence, we introduce an explainable AI model, known as BeCaked+, to predict and analyze the pandemic situation efficiently from the collected data. BeCaked+ combined deep learning and epidemiological models enhanced by specific parameters related to the policies endorsed by the government. Such a combination makes BeCaked+ so accurate and a tool that provides information for policymakers to respond appropriately. One take a try BeCaked+ at http://www.cse.hcmut.edu.vn/BeCaked .