Exploring SEIR Epidemiological Modeling Using Physics-Informed Neural Networks

This paper explores the use of Physics-Informed Neural Networks (PINNs) as a tool for teaching mathematical and public health concepts. PINNs integrate physical laws with machine learning to solve complex systems, offering a novel approach to teaching differential equations and epidemiological models. The paper addresses the challenge of teaching these models to interdisciplinary students, who often face gaps in mathematical, computational, and domain-specific knowledge. Using the SEIR model, we demonstrate how PINNs enhance student understanding by bridging theory and real-world applications. This work advocates for incorporating PINNs into curricula to improve interdisciplinary learning and equip students with the skills to tackle complex problems in applied mathematics and public health.