Scaling up Probabilistic PDE Simulators with Structured Volumetric Information
This work addresses scalability issues in probabilistic PDE simulation for scientific machine learning, offering incremental improvements over previous collocation-based techniques.
The paper tackles the challenge of scaling up probabilistic PDE simulators by combining the Finite Volume Method with numerical linear algebra, resulting in substantially improved scaling behavior demonstrated in a spatiotemporal tsunami simulation.
Modeling real-world problems with partial differential equations (PDEs) is a prominent topic in scientific machine learning. Classic solvers for this task continue to play a central role, e.g. to generate training data for deep learning analogues. Any such numerical solution is subject to multiple sources of uncertainty, both from limited computational resources and limited data (including unknown parameters). Gaussian process analogues to classic PDE simulation methods have recently emerged as a framework to construct fully probabilistic estimates of all these types of uncertainty. So far, much of this work focused on theoretical foundations, and as such is not particularly data efficient or scalable. Here we propose a framework combining a discretization scheme based on the popular Finite Volume Method with complementary numerical linear algebra techniques. Practical experiments, including a spatiotemporal tsunami simulation, demonstrate substantially improved scaling behavior of this approach over previous collocation-based techniques.