An overview on deep learning-based approximation methods for partial differential equations

C Beck, M Hutzenthaler, A Jentzen… - arxiv preprint arxiv …, 2020 - arxiv.org
It is one of the most challenging problems in applied mathematics to approximatively solve
high-dimensional partial differential equations (PDEs). Recently, several deep learning …

Physics-informed neural network (PINN) evolution and beyond: A systematic literature review and bibliometric analysis

ZK Lawal, H Yassin, DTC Lai, A Che Idris - Big Data and Cognitive …, 2022 - mdpi.com
This research aims to study and assess state-of-the-art physics-informed neural networks
(PINNs) from different researchers' perspectives. The PRISMA framework was used for a …

When and why PINNs fail to train: A neural tangent kernel perspective

S Wang, X Yu, P Perdikaris - Journal of Computational Physics, 2022 - Elsevier
Physics-informed neural networks (PINNs) have lately received great attention thanks to
their flexibility in tackling a wide range of forward and inverse problems involving partial …

PINN-FORM: a new physics-informed neural network for reliability analysis with partial differential equation

Z Meng, Q Qian, M Xu, B Yu, AR Yıldız… - Computer Methods in …, 2023 - Elsevier
The first-order reliability method (FORM) is commonly used in the field of structural reliability
analysis, which transforms the reliability analysis problem into the solution of an optimization …

Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios

C Xu, BT Cao, Y Yuan, G Meschke - Computer Methods in Applied …, 2023 - Elsevier
Recently, a class of machine learning methods called physics-informed neural networks
(PINNs) has been proposed and gained prevalence in solving various scientific computing …

Monte Carlo fPINNs: Deep learning method for forward and inverse problems involving high dimensional fractional partial differential equations

L Guo, H Wu, X Yu, T Zhou - Computer Methods in Applied Mechanics and …, 2022 - Elsevier
We introduce a sampling-based machine learning approach, Monte Carlo fractional physics-
informed neural networks (MC-fPINNs), for solving forward and inverse fractional partial …

Meta-learning PINN loss functions

AF Psaros, K Kawaguchi, GE Karniadakis - Journal of computational …, 2022 - Elsevier
We propose a meta-learning technique for offline discovery of physics-informed neural
network (PINN) loss functions. We extend earlier works on meta-learning, and develop a …

Solving Inverse Stochastic Problems from Discrete Particle Observations Using the Fokker--Planck Equation and Physics-Informed Neural Networks

X Chen, L Yang, J Duan, GE Karniadakis - SIAM Journal on Scientific …, 2021 - SIAM
The Fokker--Planck (FP) equation governing the evolution of the probability density function
(PDF) is applicable to many disciplines, but it requires specification of the coefficients for …

Enhancing PINNs for solving PDEs via adaptive collocation point movement and adaptive loss weighting

J Hou, Y Li, S Ying - Nonlinear Dynamics, 2023 - Springer
Physics-informed neural networks (PINNs) are an emerging method for solving partial
differential equations (PDEs) and have been widely applied in the field of scientific …

Data-driven physics-informed constitutive metamodeling of complex fluids: A multifidelity neural network (MFNN) framework

M Mahmoudabadbozchelou, M Caggioni… - Journal of …, 2021 - pubs.aip.org
In this work, we introduce a comprehensive machine-learning algorithm, namely, a
multifidelity neural network (MFNN) architecture for data-driven constitutive metamodeling of …