Inverse resolution of spatially varying diffusion coefficient using Physics-Informed neural networks

no code implementations • 6 Mar 2024 • Sukirt Thakur, Ehsan Esmaili, Sarah Libring, Luis Solorio, Arezoo M. Ardekani

The robustness of the method as an inverse solver was tested using both numerical and experimental datasets.

Temporal Consistency Loss for Physics-Informed Neural Networks

no code implementations • 30 Jan 2023 • Sukirt Thakur, Maziar Raissi, Harsa Mitra, Arezoo Ardekani

This paper proposes a method for scaling the mean squared loss terms in the objective function used to train PINNs.