Physics-Informed Neural Network-Based Inverse Framework for Time-Fractional Differential Equations for Rheology
Biology · 27.06.2025 · 14 (7) · 779
DOI: 10.3390/biology14070779 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biology, online erschienen am 27.06.2025. Verfasst von Sukirt Thakur und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical Engineering, Purdue University, West Lafayette, IN 47907, USA. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: U.S. National Science Foundation, National Science Foundation (NSF).
Abstract (Originalsprache)
Inverse problems involving time-fractional differential equations have become increasingly important for modeling systems with memory-dependent dynamics, particularly in biotransport and viscoelastic materials. Despite their potential, these problems remain challenging due to issues of stability, non-uniqueness, and limited data availability. Recent advancements in Physics-Informed Neural Networks (PINNs) offer a data-efficient framework for solving such inverse problems, yet most implementations are restricted to integer-order derivatives. In this work, we develop a PINN-based framework tailored for inverse problems involving time-fractional derivatives. We consider two representative applications: anomalous diffusion and fractional viscoelasticity. Using both synthetic and experimental datasets, we infer key physical parameters including the generalized diffusion coefficient and the fractional derivative order in the diffusion model and the relaxation parameters in a fractional Maxwell model. Our approach incorporates a customized residual loss function scaled by the standard deviation of observed data to enhance robustness. Even under 25% Gaussian noise, our method recovers model parameters with relative errors below 10%. Additionally, the framework accurately predicts relaxation moduli in porcine tissue experiments, achieving similar error margins. These results demonstrate the framework’s effectiveness in learning fractional dynamics from noisy and sparse data, paving the way for broader applications in complex biological and mechanical systems.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Mechanical Engineering, Purdue University, West Lafayette, IN 47907, USA.
ORCID-Profile: Harsa Mitra, Arezoo M Ardekani
Förderung
- U.S. National Science Foundation
- National Science Foundation (NSF)
Zitieren
APA
Thakur, S., Mitra, H., & Ardekani, A. M. (2025). Physics-Informed Neural Network-Based Inverse Framework for Time-Fractional Differential Equations for Rheology. Biology, 14(7), 779. https://doi.org/10.3390/biology14070779
Vancouver
Thakur S, Mitra H, Ardekani AM. Physics-Informed Neural Network-Based Inverse Framework for Time-Fractional Differential Equations for Rheology. Biology. 2025;14(7):779. doi:10.3390/biology14070779
BibTeX
@article{Thakur2025,
author = {Thakur, Sukirt and Mitra, Harsa and Ardekani, Arezoo M},
title = {Physics-Informed Neural Network-Based Inverse Framework for Time-Fractional Differential Equations for Rheology},
journal = {Biology},
year = {2025},
volume = {14},
number = {7},
pages = {779},
doi = {10.3390/biology14070779}
}
EUVIMED