Improved Uncertainty Quantification in Physics-Informed Neural Networks Using Error Bounds and Solution Bundles
This work addresses uncertainty quantification for researchers using PINNs in physics and cosmology, representing an incremental improvement over existing methods.
The paper tackles the problem of uncertainty quantification in Physics-Informed Neural Networks (PINNs) by proposing a two-step training procedure for Bayesian Neural Networks that incorporates error bounds to improve uncertainty estimation, achieving enhanced performance in forward and inverse problems in cosmology.
Physics-Informed Neural Networks (PINNs) have been widely used to obtain solutions to various physical phenomena modeled as Differential Equations. As PINNs are not naturally equipped with mechanisms for Uncertainty Quantification, some work has been done to quantify the different uncertainties that arise when dealing with PINNs. In this paper, we use a two-step procedure to train Bayesian Neural Networks that provide uncertainties over the solutions to differential equation systems provided by PINNs. We use available error bounds over PINNs to formulate a heteroscedastic variance that improves the uncertainty estimation. Furthermore, we solve forward problems and utilize the obtained uncertainties when doing parameter estimation in inverse problems in cosmology.