DeepAI AI Chat
Log In Sign Up

Physics-enhanced deep surrogates for PDEs

by   Raphaël Pestourie, et al.

We present a "physics-enhanced deep-surrogate ("PEDS") approach towards developing fast surrogate models for complex physical systems described by partial differential equations (PDEs) and similar models: we show how to combine a low-fidelity "coarse" solver with a neural network that generates "coarsified” inputs, trained end-to-end to globally match the output of an expensive high-fidelity numerical solver. In this way, by incorporating limited physical knowledge in the form of the low-fidelity model, we find that a PEDS surrogate can be trained with at least ∼ 10× less data than a "black-box” neural network for the same accuracy. Asymptotically, PEDS appears to learn with a steeper power law than black-box surrogates, and benefits even further when combined with active learning. We demonstrate feasibility and benefit of the proposed approach by using an example problem in electromagnetic scattering that appears in the design of optical metamaterials.


page 2

page 5

page 6


A multi-fidelity neural network surrogate sampling method for uncertainty quantification

We propose a multi-fidelity neural network surrogate sampling method for...

Active learning of deep surrogates for PDEs: Application to metasurface design

Surrogate models for partial-differential equations are widely used in t...

Surrogate Modeling for Physical Systems with Preserved Properties and Adjustable Tradeoffs

Determining the proper level of details to develop and solve physical mo...

Multi-fidelity Bayesian Neural Networks: Algorithms and Applications

We propose a new class of Bayesian neural networks (BNNs) that can be tr...

s-LIME: Reconciling Locality and Fidelity in Linear Explanations

The benefit of locality is one of the major premises of LIME, one of the...

Global Performance Guarantees for Neural Network Models of AC Power Flow

Machine learning can generate black-box surrogate models which are both ...