Towards Gaussian Process for operator learning: An uncertainty aware resolution independent operator learning algorithm for computational mechanics
This paper presents a GP-based neural operator for parametric differential equations, achieving high accuracy, scalability, and robust uncertainty estimation, outperforming traditional models.
Dec 28, 2024
Neural Operator induced Gaussian Process framework for probabilistic solution of parametric partial differential equations
A novel framework, Neural Operator-induced Gaussian Process (NOGaP), is proposed for solving PDEs with improved prediction accuracy and quantifiable uncertainty, evaluated on various examples like Burger’s equation and Darcy flow.
Apr 29, 2024