Thomas Izgin

Using Machine Learning to Design Time Step Size Controllers for Stable Time Integrators

Abstract We present a new method for developing time step controllers based on a technique from the field of machine learning. This method is applicable to stable time integrators that have an embedded scheme, i.e., that provide a local error estimate similar to Runge–Kutta pairs...

Using machine learning to enhance pandemic modeling: case study of COVID-19 dynamics in Ghana

Abstract In this study, five distinct COVID-19 models developed in different countries, each designed to reflect the prevailing epidemiological condition at the time of formulation, are examined. The models are reformulated while still maintaining their original compartmental str...