Graph Convolutional Neural Networks as Surrogate Models for Climate Simulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Potter, Kevin, Martinez, Carianne, Pradhan, Reina, Brozak, Samantha, Sleder, Steven, Wheeler, Lauren
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916401197875200
author Potter, Kevin
Martinez, Carianne
Pradhan, Reina
Brozak, Samantha
Sleder, Steven
Wheeler, Lauren
author_facet Potter, Kevin
Martinez, Carianne
Pradhan, Reina
Brozak, Samantha
Sleder, Steven
Wheeler, Lauren
contents Many climate processes are characterized using large systems of nonlinear differential equations; this, along with the immense amount of data required to parameterize complex interactions, means that Earth-System Model (ESM) simulations may take weeks to run on large clusters. Uncertainty quantification may require thousands of runs, making ESM simulations impractical for preliminary assessment. Alternatives may include simplifying the processes in the model, but recent efforts have focused on using machine learning to complement these models or even act as full surrogates. \textit{We leverage machine learning, specifically fully-connected neural networks (FCNNs) and graph convolutional neural networks (GCNNs), to enable rapid simulation and uncertainty quantification in order to inform more extensive ESM simulations.} Our surrogate simulated 80 years in approximately 310 seconds on a single A100 GPU, compared to weeks for the ESM model while having mean temperature errors below $0.1^{\circ}C$ and maximum errors below $2^{\circ}C$.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12815
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Graph Convolutional Neural Networks as Surrogate Models for Climate Simulation
Potter, Kevin
Martinez, Carianne
Pradhan, Reina
Brozak, Samantha
Sleder, Steven
Wheeler, Lauren
Atmospheric and Oceanic Physics
Artificial Intelligence
Many climate processes are characterized using large systems of nonlinear differential equations; this, along with the immense amount of data required to parameterize complex interactions, means that Earth-System Model (ESM) simulations may take weeks to run on large clusters. Uncertainty quantification may require thousands of runs, making ESM simulations impractical for preliminary assessment. Alternatives may include simplifying the processes in the model, but recent efforts have focused on using machine learning to complement these models or even act as full surrogates. \textit{We leverage machine learning, specifically fully-connected neural networks (FCNNs) and graph convolutional neural networks (GCNNs), to enable rapid simulation and uncertainty quantification in order to inform more extensive ESM simulations.} Our surrogate simulated 80 years in approximately 310 seconds on a single A100 GPU, compared to weeks for the ESM model while having mean temperature errors below $0.1^{\circ}C$ and maximum errors below $2^{\circ}C$.
title Graph Convolutional Neural Networks as Surrogate Models for Climate Simulation
topic Atmospheric and Oceanic Physics
Artificial Intelligence
url https://arxiv.org/abs/2409.12815