EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning in Fluid Dynamics—Physics-Informed Neural Networks (PINNs) Using Sparse Data: A Review

Mouhammad El Hassan, Ali Mjalled, Philippe Miron, Martin Mönnigmann, Nikolay Bukharin

Fluids · 28.08.2025 · 10 (9) · 226

DOI: 10.3390/fluids10090226 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Fluids, online erschienen am 28.08.2025. Verfasst von Mouhammad El Hassan und 4 weiteren Autor:innen. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 100 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fluid mechanics often involves complex systems characterized by a large number of physical parameters, which are usually described by experimental and numerical sparse data (temporal or spatial). The difficulty of obtaining complete spatio-temporal datasets is a common issue with conventional approaches, such as computational fluid dynamics (CFDs) and various experimental methods, particularly when evaluating and modeling turbulent flows. This review paper focuses on the integration of machine learning (ML), specifically physics-informed neural networks (PINNs), as a means to address this challenge. By directly incorporating governing physical equations into neural network training, PINNs present a novel method that allows for the reconstruction of flow from sparse and noisy data. This review examines various applications in fluid mechanics where sparse data is a common problem and evaluates the effectiveness of PINNs in enhancing flow prediction accuracy. An overview of diverse PINNs methods, their applications, and outcomes is discussed, demonstrating their flexibility and effectiveness in addressing challenges related to sparse data and illustrating that the future of fluid mechanics lies in the synergy between data-driven approaches and established physical theories.

Zitieren

APA

Hassan, M. E., Mjalled, A., Miron, P., Mönnigmann, M., & Bukharin, N. (2025). Machine Learning in Fluid Dynamics—Physics-Informed Neural Networks (PINNs) Using Sparse Data: A Review. Fluids, 10(9), 226. https://doi.org/10.3390/fluids10090226

Vancouver

Hassan ME, Mjalled A, Miron P, Mönnigmann M, Bukharin N. Machine Learning in Fluid Dynamics—Physics-Informed Neural Networks (PINNs) Using Sparse Data: A Review. Fluids. 2025;10(9):226. doi:10.3390/fluids10090226

BibTeX
@article{Hassan2025,
  author = {Hassan, Mouhammad El and Mjalled, Ali and Miron, Philippe and Mönnigmann, Martin and Bukharin, Nikolay},
  title = {Machine Learning in Fluid Dynamics—Physics-Informed Neural Networks (PINNs) Using Sparse Data: A Review},
  journal = {Fluids},
  year = {2025},
  volume = {10},
  number = {9},
  pages = {226},
  doi = {10.3390/fluids10090226}
}
Kostenlos starten →