Coarse-grained and emergent distributed parameter systems from data
This addresses the classical identification problem in distributed parameter systems for researchers in computational science, but it appears incremental as it builds on existing techniques like Diffusion Maps.
The paper tackles the problem of deriving partial differential equations (PDEs) from spatiotemporal data without prior knowledge of the variables, using manifold learning and neural networks, and demonstrates it on established PDE examples.
We explore the derivation of distributed parameter system evolution laws (and in particular, partial differential operators and associated partial differential equations, PDEs) from spatiotemporal data. This is, of course, a classical identification problem; our focus here is on the use of manifold learning techniques (and, in particular, variations of Diffusion Maps) in conjunction with neural network learning algorithms that allow us to attempt this task when the dependent variables, and even the independent variables of the PDE are not known a priori and must be themselves derived from the data. The similarity measure used in Diffusion Maps for dependent coarse variable detection involves distances between local particle distribution observations; for independent variable detection we use distances between local short-time dynamics. We demonstrate each approach through an illustrative established PDE example. Such variable-free, emergent space identification algorithms connect naturally with equation-free multiscale computation tools.