DeepAI AI Chat
Log In Sign Up

Coarse-grained and emergent distributed parameter systems from data

by   Hassan Arbabi, et al.

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.


page 3

page 5


Particles to Partial Differential Equations Parsimoniously

Equations governing physico-chemical processes are usually known at micr...

Particle-based simulations of reaction-diffusion processes with Aboria

Mathematical models of transport and reactions in biological systems hav...

Linking Machine Learning with Multiscale Numerics: Data-Driven Discovery of Homogenized Equations

The data-driven discovery of partial differential equations (PDEs) consi...

Emergent spaces for coupled oscillators

In this paper we present a systematic, data-driven approach to discoveri...

General Covariance Data Augmentation for Neural PDE Solvers

The growing body of research shows how to replace classical partial diff...

Coarse-scale PDEs from fine-scale observations via machine learning

Complex spatiotemporal dynamics of physicochemical processes are often m...

Stability selection enables robust learning of partial differential equations from limited noisy data

We present a statistical learning framework for robust identification of...