| Abstract: |
| Modeling and Data analysis continues to provide useful insights to understand the early transmission dynamics of infectious diseases such as COVID-19. Along with the development of mathematical modeling, there have also been a variety of data-driven approaches that have been introduced to estimate the parameters in these models such as the transmission, infection, quarantine and recovery using real data. While there have been significant advances in estimating parameters, there is still a great need to develop efficient, reliable and fast data-driven approaches. Moreover, the need to develop realistic epidemic models incorporating behavioral responses of compliance and adherence, makes the associated modeling and prediction more complex. In this talk, we will introduce some models for understanding spread of COVID-19 along with physics-informed neural network data-driven approaches to study dynamics and to estimate parameters in these models. We will also discuss the importance of data science education to help students at all levels to engage in research in the areas of modeling and data analysis. |
|