Setting the standard for machine learning in phase field prediction

ǂa ǂbenchmark dataset and baseline metrics

Laura Hannemose Rieger (Author), Klemen Zelič (Author), Igor Mele (Author), Tomaž Katrašnik (Author), Arghya Bhowmik (Author)

Abstract

Phase field models are an important mesoscale method that serves as a bridge between the atomic scale and the macroscale, used for modeling complex phenomena at the microstructure level. Machine learning can be employed to accelerate these simulations, enabling faster and more efficient analyses. However, the development of new machine learning algorithms depends on access to extensive datasets. This work introduces an accessible and well-documented dataset aimed at benchmarking new machine learning algorithms. We validate the dataset with a benchmark using U-Net regression, a widely used neural network architecture. Although direct comparisons are limited by the lack of existing benchmarks, our model’s error metrics are competitive with previous work and generalize across multiple domain sizes. This contribution provides a valuable resource for future efforts in machine learning model development for phase field simulations and demonstrates the potential of U-Net regression, highlighting the scope for novel method development in this area.

Keywords

machine learning;neural network;phase field model;dataset;

Data

Language:	English
Year of publishing:	2024
Typology:	1.03 - Short Scientific Article
Organization:	UL FS - Faculty of Mechanical Engineering
UDC:	004.85
COBISS:	216315651
ISSN:	2052-4463
Views:	257
Downloads:	30
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	Slovenian
Secondary keywords:	strojno učenje;nevronske mreže;model faznega polja;zbirka podatkov;
Type (COBISS):	Article
Pages:	str. 1-10
Issue:	ǂVol. ǂ11, [art. no.] 1275
Chronology:	2024
DOI:	10.1038/s41597-024-04128-9
ID:	25411433