Physics-guided, physics-informed, and physics-encoded neural networks in scientific computing
Recent breakthroughs in computing power have made it feasible to use machine learning
and deep learning to advance scientific computing in many fields, including fluid mechanics …
and deep learning to advance scientific computing in many fields, including fluid mechanics …
Physics-guided, physics-informed, and physics-encoded neural networks and operators in scientific computing: Fluid and solid mechanics
SA Faroughi, NM Pawar… - Journal of …, 2024 - asmedigitalcollection.asme.org
Advancements in computing power have recently made it possible to utilize machine
learning and deep learning to push scientific computing forward in a range of disciplines …
learning and deep learning to push scientific computing forward in a range of disciplines …
Epi-ckans: Elasto-plasticity informed kolmogorov-arnold networks using chebyshev polynomials
F Mostajeran, SA Faroughi - arxiv preprint arxiv:2410.10897, 2024 - arxiv.org
Multilayer perceptron (MLP) networks are predominantly used to develop data-driven
constitutive models for granular materials. They offer a compelling alternative to traditional …
constitutive models for granular materials. They offer a compelling alternative to traditional …
Angle of repose for superquadric particles: Investigating the effects of shape parameters
P Datta, SA Faroughi - Computers and Geotechnics, 2024 - Elsevier
This study develops a model for the angle of repose (AOR) of granular materials composed
of non-spherical particles represented by a superquadric function featuring five distinct …
of non-spherical particles represented by a superquadric function featuring five distinct …
Scaled-cPIKANs: Domain Scaling in Chebyshev-based Physics-informed Kolmogorov-Arnold Networks
F Mostajeran, SA Faroughi - arxiv preprint arxiv:2501.02762, 2025 - arxiv.org
Partial Differential Equations (PDEs) are integral to modeling many scientific and
engineering problems. Physics-informed Neural Networks (PINNs) have emerged as …
engineering problems. Physics-informed Neural Networks (PINNs) have emerged as …