A two stages Deep Learning Architecture for Model Reduction of Parametric Time-Dependent Problems

TL;DR

This paper introduces a two-stage deep learning framework for efficiently reducing models of parametric time-dependent systems, enabling accurate predictions across parameter spaces with significantly less computational effort.

Contribution

The paper proposes a novel two-stage neural network approach that generalizes solutions of parametric time-dependent problems more efficiently than existing methods.

Findings

Achieved 97% reduction in computational time for Navier-Stokes simulations.

Successfully generalized predictions across a wide parameter space.

Demonstrated effectiveness on Rayleigh-Bernard cavity problem.

Abstract

Parametric time-dependent systems are of a crucial importance in modeling real phenomena, often characterized by non-linear behaviors too. Those solutions are typically difficult to generalize in a sufficiently wide parameter space while counting on limited computational resources available. As such, we present a general two-stages deep learning framework able to perform that generalization with low computational effort in time. It consists in a separated training of two pipe-lined predictive models. At first, a certain number of independent neural networks are trained with data-sets taken from different subsets of the parameter space. Successively, a second predictive model is specialized to properly combine the first-stage guesses and compute the right predictions. Promising results are obtained applying the framework to incompressible Navier-Stokes equations in a cavity (Rayleigh-Bernard cavity), obtaining a 97% reduction in the computational time comparing with its numerical resolution for a new value of the Grashof number.