EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

From Data to Physics: Physics-Informed Machine Learning Frameworks in Interdisciplinary Applications

Carlos A. Valentim, Sergio A. David

Dynamics · 14.05.2026 · 6 (2) · 16

DOI: 10.3390/dynamics6020016 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Dynamics, online erschienen am 14.05.2026. Verfasst von Carlos A. Valentim und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 105 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Computational modeling and machine learning have impacted several different areas of science and accelerated advancements in multiple venues. Yet traditional machine learning models have many well-known drawbacks: besides demanding a significant amount of data, they may fail to generalize beyond training data, are often treated as “black boxes”, and may predict physically inconsistent results. In response to these limitations, Physics-Informed Machine Learning (PIML) has emerged as a new area that integrates domain knowledge, such as energy or mass conservation, directly into data-driven algorithms. This review paper examines the foundations and main strategies of PIML, organizing the approaches into three categories: automated discovery and system identification, continuous-time modeling, and operator learning. In addition, Physics-Informed Neural Networks are analyzed in a dedicated section that covers architecture fundamentals, forward and inverse problem formulations, loss function design and implementation challenges. The paper also presents a survey of interdisciplinary applications of PIML in materials science, biomedical engineering, and fractional calculus. In this context, the review also analyzes open challenges and outlines future directions in the field.

Zitieren

APA

Valentim, C. A., & David, S. A. (2026). From Data to Physics: Physics-Informed Machine Learning Frameworks in Interdisciplinary Applications. Dynamics, 6(2), 16. https://doi.org/10.3390/dynamics6020016

Vancouver

Valentim CA, David SA. From Data to Physics: Physics-Informed Machine Learning Frameworks in Interdisciplinary Applications. Dynamics. 2026;6(2):16. doi:10.3390/dynamics6020016

BibTeX
@article{Valentim2026,
  author = {Valentim, Carlos A. and David, Sergio A.},
  title = {From Data to Physics: Physics-Informed Machine Learning Frameworks in Interdisciplinary Applications},
  journal = {Dynamics},
  year = {2026},
  volume = {6},
  number = {2},
  pages = {16},
  doi = {10.3390/dynamics6020016}
}
Kostenlos starten →