Exploration on Physics-Informed Neural Networks on Partial Differential Equations (Student Abstract)


  • Hoa Ta University of California, Irvine
  • Shi Wen Wong South Dakota State University
  • Nathan McClanahan South Dakota State University
  • Jung-Han Kimn South Dakota State University
  • Kaiqun Fu South Dakota State University




Machine Learning, Partial Differential Equations, Physics-informed Neural Networks, Burgers' Equation


Data-driven related solutions are dominating various scientific fields with the assistance of machine learning and data analytics. Finding effective solutions has long been discussed in the area of machine learning. The recent decade has witnessed the promising performance of the Physics-Informed Neural Networks (PINN) in bridging the gap between real-world scientific problems and machine learning models. In this paper, we explore the behavior of PINN in a particular range of different diffusion coefficients under specific boundary conditions. In addition, different initial conditions of partial differential equations are solved by applying the proposed PINN. Our paper illustrates how the effectiveness of the PINN can change under various scenarios. As a result, we demonstrate a better insight into the behaviors of the PINN and how to make the proposed method more robust while encountering different scientific and engineering problems.




How to Cite

Ta, H., Wong, S. W., McClanahan, N., Kimn, J.-H., & Fu, K. (2023). Exploration on Physics-Informed Neural Networks on Partial Differential Equations (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 16344-16345. https://doi.org/10.1609/aaai.v37i13.27032