SimPINNs: Simulation-Driven Physics-Informed Neural Networks for Enhanced Performance in Nonlinear Inverse Problems
This work addresses inverse problems in physics for researchers and practitioners, but it is incremental as it builds upon existing PINN methods with a simulation-driven enhancement.
The paper tackled the problem of inferring unknown parameters in nonlinear inverse physical systems by introducing a hybrid loss function that combines observed and simulated data within physics-informed neural networks, resulting in improved accuracy and robustness over standard PINNs as demonstrated on an orbit restitution problem.
This paper introduces a novel approach to solve inverse problems by leveraging deep learning techniques. The objective is to infer unknown parameters that govern a physical system based on observed data. We focus on scenarios where the underlying forward model demonstrates pronounced nonlinear behaviour, and where the dimensionality of the unknown parameter space is substantially smaller than that of the observations. Our proposed method builds upon physics-informed neural networks (PINNs) trained with a hybrid loss function that combines observed data with simulated data generated by a known (approximate) physical model. Experimental results on an orbit restitution problem demonstrate that our approach surpasses the performance of standard PINNs, providing improved accuracy and robustness.