Efficient data acquisition and training of collisional-radiative model artificial neural network surrogates through adaptive parameter space sampling

Nathan A. Garland; Romit Maulik; Qi Tang; Xian-Zhu Tang; Prasanna Balaprakash

doi:10.1088/2632-2153/ac93e7

Back

Efficient data acquisition and training of collisional-radiative model artificial neural network surrogates through adaptive parameter space sampling

Journal article

Open access

Peer reviewed

Efficient data acquisition and training of collisional-radiative model artificial neural network surrogates through adaptive parameter space sampling

Nathan A. Garland, Romit Maulik, Qi Tang, Xian-Zhu Tang and Prasanna Balaprakash

Machine learning: science and technology, Vol.3, pp.1-19

10/10/2022

DOI: https://doi.org/10.1088/2632-2153/ac93e7

Appears in Recent Faculty of Science and Engineering Publications

Files and links (2)

pdf

Efficient data acquisition and training of collisional-radiative model artificial neural network surrogates through adaptive parameter space sampling2.09 MBDownload View

Published (Version of record)CC BY V4.0, Open Access

url

Efficient data acquisition and training of collisional-radiative model artificial neural network surrogates through adaptive parameter space samplingView

Published (Version of record)CC BY V4.0, Open

Metrics

41 File views/ downloads

4 Record Views

See more details

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

Source: InCites

Abstract

Computer Science

Computer Science, Artificial Intelligence

Computer Science, Interdisciplinary Applications

Multidisciplinary Sciences

Science & Technology

Science & Technology - Other Topics

Technology

Effective plasma transport modeling of magnetically confined fusion devices relies on having an accurate understanding of the ion composition and radiative power losses of the plasma. Generally, these quantities can be obtained from solutions of a collisional-radiative (CR) model at each time step within a plasma transport simulation. However, even compact, approximate CR models can be computationally onerous to evaluate, and in-situ evaluation of these models within a larger plasma transport code can lead to a rigid bottleneck. As a way to bypass this bottleneck, we propose deploying artificial neural network (ANN) surrogates to allow rapid evaluation of the necessary plasma quantities. However, one issue with training an accurate ANN surrogate is the reliance on a sufficiently large and representative training and validation data set, which can be time-consuming to generate. In this work we explore a data-driven active learning and training routine to allow autonomous adaptive sampling of the problem parameter space to ensure a sufficiently large and meaningful set of training data is assembled for the network training. As a result, we can demonstrate approximately order-of-magnitude savings in required training data samples to produce an accurate surrogate.

Details

Title: Efficient data acquisition and training of collisional-radiative model artificial neural network surrogates through adaptive parameter space sampling
Creators: Nathan A. Garland - Griffith University
Romit Maulik - Argonne Natl Lab, Math & Comp Sci Div, Lemont, IL 60439 USA
Qi Tang - Los Alamos Natl Lab, Theoret Div, Los Alamos, NM 87545 USA
Xian-Zhu Tang - Los Alamos Natl Lab, Theoret Div, Los Alamos, NM 87545 USA
Prasanna Balaprakash - Argonne Natl Lab, Math & Comp Sci Div, Lemont, IL 60439 USA
Publication Details: Machine learning: science and technology, Vol.3, pp.1-19
Publisher: IOP Publishing Ltd
Number of pages: 18
Grant note: DEAC02-06CH11357 / U.S. Department of Energy (DOE), Office of Science, Office of Advanced Scientific Computing Research; United States Department of Energy (DOE) DOE-FOA-2493 / ASCR; Czech Academy of Sciences Office of Fusion Energy Sciences under the DeepFusion pilot project in scientific machine learning and artificial intelligence for fusion energy sciences DE-AC02-06CH11357 / DOE Office of Science User Facility; United States Department of Energy (DOE) 89233218CNA000001 / Office of Fusion Energy Sciences and Office of Advanced Scientific Computing Research under the Scientific Discovery through Advanced Computing (SciDAC) project of Tokamak Disruption Simulation at Los Alamos National Laboratory 20200356ER / US DOE Laboratory Directed Research and Development (LDRD) program
Identifiers: 991013062312902368
Copyright: © 2022 The Author(s). Published by IOP Publishing Ltd. Original content from this work may be used under the terms of the Creative Commons Attribution 4.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
Academic Unit: Faculty of Science and Engineering
Language: English
Resource Type: Journal article

Efficient data acquisition and training of collisional-radiative model artificial neural network surrogates through adaptive parameter space sampling

Files and links (2)

Metrics

UN Sustainable Development Goals (SDGs)

Abstract

Details

Southern Cross University Social media