A hierarchical sparse Gaussian process for in situ inference in expensive physics simulations

Kellin Rumsey; Michael Grosskopf; Earl Lawrence; Ayan Biswas; Nathan Urban

doi:10.1117/12.2633427

3 October 2022 A hierarchical sparse Gaussian process for in situ inference in expensive physics simulations

Kellin Rumsey, Michael Grosskopf, Earl Lawrence, Ayan Biswas, Nathan Urban

Proceedings Volume 12227, Applications of Machine Learning 2022; 122270J (2022) https://doi.org/10.1117/12.2633427
Event: SPIE Optical Engineering + Applications, 2022, San Diego, California, United States

Abstract

High-fidelity physics simulations, such as the Energy Exascale Earth System Model (E3SM), are generating ever increasing quantities of data. In the near future, it will be infeasible to store the full computation after the simulation. To facilitate the training of complex machine learning models in the future, there is a glaring need for in-situ inference algorithms. In this work, we focus on the need for spatio-temporal inference models which are (i) highly scalable, (ii) distributed, (iii) able to capture small-scale, high-resolution structures, and (iv) longrange global structure. One possible approach is to leverage algorithms for fast approximate Gaussian process regression, such as the sparse variational Gaussian process (SVGP). In this work, we present a Hierarchical SVGP (HSVGP) model in which local models capture small-scale structures in-situ, while large-scale structures are captured and communicated by a global SVGP. We also consider the simpler approach in which independent, parallel sparse Gaussian processes are fit to each local region with no additional global information. Using both synthetic data and E3SM model output, we show the success of the HSVGP approach in some settings, but also the surprisingly good performance of the independent approach.

Conference Presentation

Citation Download Citation

Kellin Rumsey, Michael Grosskopf, Earl Lawrence, Ayan Biswas, and Nathan Urban "A hierarchical sparse Gaussian process for in situ inference in expensive physics simulations", Proc. SPIE 12227, Applications of Machine Learning 2022, 122270J (3 October 2022); https://doi.org/10.1117/12.2633427

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available