Coarse Graining with Neural Operators for Simulating Chaotic Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Chuwei, Berner, Julius, Li, Zongyi, Zhou, Di, Wang, Jiayun, Bae, Jane, Anandkumar, Anima
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916871676100608
author Wang, Chuwei
Berner, Julius
Li, Zongyi
Zhou, Di
Wang, Jiayun
Bae, Jane
Anandkumar, Anima
author_facet Wang, Chuwei
Berner, Julius
Li, Zongyi
Zhou, Di
Wang, Jiayun
Bae, Jane
Anandkumar, Anima
contents Accurately predicting the long-term behavior of chaotic systems is crucial for various applications such as climate modeling. However, achieving such predictions typically requires iterative computations over a dense spatiotemporal grid to account for the unstable nature of chaotic systems, which is expensive and impractical in many real-world situations. An alternative approach to such a full-resolved simulation is using a coarse grid and then correcting its errors through a \textit{closure model}, which approximates the overall information from fine scales not captured in the coarse-grid simulation. Recently, ML approaches have been used for closure modeling, but they typically require a large number of training samples from expensive fully-resolved simulations (FRS). In this work, we prove an even more fundamental limitation, i.e., the standard approach to learning closure models suffers from a large approximation error for generic problems, no matter how large the model is, and it stems from the non-uniqueness of the mapping. We propose an alternative end-to-end learning approach using a physics-informed neural operator (PINO) that overcomes this limitation by not using a closure model or a coarse-grid solver. We first train the PINO model on data from a coarse-grid solver and then fine-tune it with (a small amount of) FRS and physics-based losses on a fine grid. The discretization-free nature of neural operators means that they do not suffer from the restriction of a coarse grid that closure models face, and they can provably approximate the long-term statistics of chaotic systems. In our experiments, our PINO model achieves a 330x speedup compared to FRS with a relative error $\sim 10\%$. In contrast, the closure model coupled with a coarse-grid solver is $60$x slower than PINO while having a much higher error $\sim186\%$ when the closure model is trained on the same FRS dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2408_05177
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Coarse Graining with Neural Operators for Simulating Chaotic Systems
Wang, Chuwei
Berner, Julius
Li, Zongyi
Zhou, Di
Wang, Jiayun
Bae, Jane
Anandkumar, Anima
Machine Learning
Accurately predicting the long-term behavior of chaotic systems is crucial for various applications such as climate modeling. However, achieving such predictions typically requires iterative computations over a dense spatiotemporal grid to account for the unstable nature of chaotic systems, which is expensive and impractical in many real-world situations. An alternative approach to such a full-resolved simulation is using a coarse grid and then correcting its errors through a \textit{closure model}, which approximates the overall information from fine scales not captured in the coarse-grid simulation. Recently, ML approaches have been used for closure modeling, but they typically require a large number of training samples from expensive fully-resolved simulations (FRS). In this work, we prove an even more fundamental limitation, i.e., the standard approach to learning closure models suffers from a large approximation error for generic problems, no matter how large the model is, and it stems from the non-uniqueness of the mapping. We propose an alternative end-to-end learning approach using a physics-informed neural operator (PINO) that overcomes this limitation by not using a closure model or a coarse-grid solver. We first train the PINO model on data from a coarse-grid solver and then fine-tune it with (a small amount of) FRS and physics-based losses on a fine grid. The discretization-free nature of neural operators means that they do not suffer from the restriction of a coarse grid that closure models face, and they can provably approximate the long-term statistics of chaotic systems. In our experiments, our PINO model achieves a 330x speedup compared to FRS with a relative error $\sim 10\%$. In contrast, the closure model coupled with a coarse-grid solver is $60$x slower than PINO while having a much higher error $\sim186\%$ when the closure model is trained on the same FRS dataset.
title Coarse Graining with Neural Operators for Simulating Chaotic Systems
topic Machine Learning
url https://arxiv.org/abs/2408.05177