Learning variable-order time fractional diffusion equations using Physics-Informed Neural Networks
PLOS One · 23.06.2026 · 21 (6) · e0352016
DOI: 10.1371/journal.pone.0352016 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 23.06.2026. Verfasst von Lei Ren und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematics and Statistics, Shangqiu Normal University, Shangqiu, Henan, People's Republic of China. Hauptthemen laut MEDLINE: Neural Networks, Computer, Physics. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Key Scientific Research Projects of Colleges and Universities in Henan Province, National Natural Science Foundation of China.
Abstract (Originalsprache)
This paper introduces a novel approach using physics-informed neural networks (PINNs) to simultaneously solve variable-order time fractional diffusion equations and infer the time-dependent fractional order from data. By embedding the governing equations into the neural network’s loss function, our method achieves high accuracy and flexibility, even with sparse or noisy data. We present a dual-network architecture where one network approximates the solution u ( x , t ) while another learns the fractional order α ( t ) . Numerical experiments demonstrate the effectiveness of our approach, achieving mean squared errors below 10 −4 for solutions and 10 −3 for fractional orders in smooth cases, while also handling noisy data and non-smooth orders robustly.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Mathematics and Statistics, Shangqiu Normal University, Shangqiu, Henan, People's Republic of China.
ORCID-Profile: Lei Ren
Förderung
- the Key Scientific Research Projects of Colleges and Universities in Henan Province
- National Natural Science Foundation of China
Zitieren
APA
Ren, L., & Jin, S. (2026). Learning variable-order time fractional diffusion equations using Physics-Informed Neural Networks. PLOS One, 21(6), e0352016. https://doi.org/10.1371/journal.pone.0352016
Vancouver
Ren L, Jin S. Learning variable-order time fractional diffusion equations using Physics-Informed Neural Networks. PLOS One. 2026;21(6):e0352016. doi:10.1371/journal.pone.0352016
BibTeX
@article{Ren2026,
author = {Ren, Lei and Jin, Shixin},
title = {Learning variable-order time fractional diffusion equations using Physics-Informed Neural Networks},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {6},
pages = {e0352016},
doi = {10.1371/journal.pone.0352016}
}
EUVIMED