Model-parallel Fourier neural operators as learned surrogates for large-scale parametric PDEs

Grady T.J.; Louboutin M.; Yin Z.Herrmann F.J.Khan R.Witte P.A.Chandra R.Hewett R.J.

首页> 外文期刊>Computers & geosciences >Model-parallel Fourier neural operators as learned surrogates for large-scale parametric PDEs

【24h】

Model-parallel Fourier neural operators as learned surrogates for large-scale parametric PDEs

机译：Model-parallel Fourier neural operators as learned surrogates for large-scale parametric PDEs

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相关主题

摘要

? 2023 Elsevier LtdFourier neural operators (FNOs) are a recently introduced neural network architecture for learning solution operators of partial differential equations (PDEs), which have been shown to perform significantly better than comparable deep learning approaches. Once trained, FNOs can achieve speed-ups of multiple orders of magnitude over conventional numerical PDE solvers. However, due to the high dimensionality of their input data and network weights, FNOs have so far only been applied to two-dimensional or small three-dimensional problems. To remove this limited problem-size barrier, we propose a model-parallel version of FNOs based on domain-decomposition of both the input data and network weights. We demonstrate that our model-parallel FNO is able to predict time-varying PDE solutions of over 2.6 billion variables on Perlmutter using up to 512 A100 GPUs and show an example of training a distributed FNO on the Azure cloud for simulating multiphase CO2 dynamics in the Earth's subsurface.

著录项

来源
《Computers & geosciences》 |2023年第9期|1.1-1.10|共10页
作者
Grady T.J.; Louboutin M.; Yin Z.Herrmann F.J.Khan R.Witte P.A.Chandra R.Hewett R.J.;
展开▼
作者单位

Georgia Institute of Technology;

Extreme Scale Solutions;

MicrosoftMicrosoft||Virginia Tech;

展开▼
收录信息
原文格式 PDF
正文语种英语
中图分类计算机的应用;天文学、地球科学;
关键词
Carbon capture sequestration; Deep learning; Learned surrogates; Model parallelism; Multiphase flow; Operator learning;

Model-parallel Fourier neural operators as learned surrogates for large-scale parametric PDEs

摘要

著录项

相关主题

期刊订阅