A3 Kirjan tai muun kokoomateoksen osa
Generation of Error Indicators for Partial Differential Equations by Machine Learning Methods (2022)

Muzalevskiy, A., Neittaanmäki, P., & Repin, S. (2022). Generation of Error Indicators for Partial Differential Equations by Machine Learning Methods. In T. T. Tuovinen, J. Periaux, & P. Neittaanmäki (Eds.), Computational Sciences and Artificial Intelligence in Industry : New Digital Technologies for Solving Future Societal and Economical Challenges (pp. 63-96). Springer. Intelligent Systems, Control and Automation: Science and Engineering, 76. https://doi.org/10.1007/978-3-030-70787-3_6

JYU-tekijät tai -toimittajat

Julkaisun tiedot

Julkaisun kaikki tekijät tai toimittajat: Muzalevskiy, Alexey; Neittaanmäki, Pekka; Repin, Sergey

Emojulkaisu: Computational Sciences and Artificial Intelligence in Industry : New Digital Technologies for Solving Future Societal and Economical Challenges

Emojulkaisun toimittajat: Tuovinen, Tero T.; Periaux, Jacques; Neittaanmäki, Pekka

ISBN: 978-3-030-70786-6

eISBN: 978-3-030-70787-3

Lehti tai sarja: Intelligent Systems, Control and Automation: Science and Engineering

ISSN: 2213-8986

eISSN: 2213-8994

Julkaisuvuosi: 2022

Sarjan numero: 76

Artikkelin sivunumerot: 63-96

Kirjan kokonaissivumäärä: 275

Kustantaja: Springer

Kustannuspaikka: Cham

Julkaisumaa: Sveitsi

Julkaisun kieli: englanti

DOI: https://doi.org/10.1007/978-3-030-70787-3_6

Julkaisun avoin saatavuus: Ei avoin

Julkaisukanavan avoin saatavuus: 

Julkaisu on rinnakkaistallennettu (JYX): https://jyx.jyu.fi/handle/123456789/84830

Lisätietoja: The CSAI 2019 Conference (Computational Science and AI in Industry: New Digital Technologies for Solving Future Societal and Economical Challenges) took place at Jyväskylä, Finland, on June 12–14, 2019.

Tiivistelmä

Computer simulation methods for models based on partial differential equations usually apply adaptive strategies that generate sequences of approximations for consequently refined meshes. In this process, error indicators play a crucial role because a new (refined) mesh is created by analysis of an approximate solution computed for the previous (coarser) mesh. Different error indicators exploit various analytical and heuristic arguments. The main goal of this paper is to show that effective indicators of approximation errors can be created by machine learning methods and presented by relatively simple networks. We use the “supervised learning” conception where sequences of teaching examples are constructed due to earlier developed tools of a posteriori error analysis known as “functional type error majorants”. Insensitivity to specific features of approximations is an important property of error majorants, which allows us to generate arbitrarily long series of diverse training examples without restrictions on the type of approximate solutions. These new (network) error indicators are compared with known indicators. The results show that after a proper machine learning procedure, we obtain a network with the same (or even better) quality of error indication level as the most efficient indicators used in classical computer simulation methods. The final trained network is approximately as effective as the gradient averaging error indicator, but has an important advantage because it is valid for a much wider set of approximate solutions.

YSO-asiasanat: matemaattiset mallit; simulointi; osittaisdifferentiaaliyhtälöt; approksimointi; virheanalyysi; koneoppiminen

Vapaat asiasanat: mesh adaptive methods; machine learning; network error indicator

Liittyvät organisaatiot

OKM-raportointi: Kyllä

VIRTA-lähetysvuosi: 2022

JUFO-taso: 2