• Home
  • Search
  • Physics Informed Neural Network using Finite Difference Method
  • Cite Icon23
  • https://doi.org/10.1109/smc53654.2022.9945171Copy DOI Icon

Physics Informed Neural Network using Finite Difference Method

  • Oct 9, 2022
  • Kart Leong Lim +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In recent engineering applications using deep learning, physics-informed neural network (PINN) is a new development as it can exploit the underlying physics of engineering systems. The novelty of PINN lies in the use of partial differential equations (PDE) for the loss function. Most PINNs are implemented using automatic differentiation (AD) for training the PDE loss functions. A lesser well-known study is the use of finite difference method (FDM) as an alternative. Unlike an AD based PINN, an immediate benefit of using a FDM based PINN is low implementation cost. In this paper, we propose the use of finite difference method for estimating the PDE loss functions in PINN. Our work is inspired by computational analysis in electromagnetic systems that traditionally solve Laplace’s equation using successive over-relaxation. In the case of Laplace’s equation, our PINN approach can be seen as taking the Laplacian filter response of the neural network output as the loss function. Thus, the implementation of PINN can be very simple. In our experiments, we tested PINN on Laplace’s equation and Burger’s equation. We showed that using FDM, PINN consistently outperforms non-PINN based deep learning. When comparing to AD based PINNs, we showed that our method is faster to compute as well as on par in terms of error reduction.

Similar Papers
  • PDF
  • Research Article
  • Citations8

An Extrinsic Approach Based on Physics-Informed Neural Networks for PDEs on Surfaces

  • Aug 11, 2022
  • Mathematics
  • Zhuochao Tang +2
  • Research Article
  • Citations299

CAN-PINN: A fast physics-informed neural network based on coupled-automatic–numerical differentiation method

  • Apr 28, 2022
  • Computer Methods in Applied Mechanics and Engineering
  • Pao-Hsiung Chiu +4
  • Dissertation

Baking physics into deep learning for modeling scientific problems

  • Jan 01, 2021
  • Chengping Rao
  • Research Article
  • Citations236

A novel sequential method to train physics informed neural networks for Allen Cahn and Cahn Hilliard equations

  • Jan 04, 2022
  • Computer Methods in Applied Mechanics and Engineering
  • Revanth Mattey +1
  • Dissertation

3D Concrete Printing Material Prediction and Flow Simulation Using Physics-Informed Neural Network

  • May 01, 2024
  • Tianjie Zhang
  • Research Article
  • Citations74

A novel meta-learning initialization method for physics-informed neural networks

  • May 08, 2022
  • Neural Computing and Applications
  • Xu Liu +4
  • Research Article
  • Citations81

Learning in Sinusoidal Spaces With Physics-Informed Neural Networks

  • Mar 01, 2024
  • IEEE Transactions on Artificial Intelligence
  • Jian Cheng Wong +3
  • Research Article

NDAWL-PINN: a new non-dimensionalization and multi-task learning approach for efficient training of physics-informed neural networks to solve the shallow water equations

  • Jul 21, 2025
  • Engineering Applications of Computational Fluid Mechanics
  • Xin Qi +4
  • Research Article
  • Citations137

Tackling the curse of dimensionality with physics-informed neural networks

  • May 07, 2024
  • Neural Networks
  • Zheyuan Hu +3
  • Conference Article
  • Citations38

Heat Transfer Prediction With Unknown Thermal Boundary Conditions Using Physics-Informed Neural Networks

  • Jul 13, 2020
  • Shengze Cai +3
  • PDF
  • Research Article
  • Citations10

Quantifying local and global mass balance errors in physics-informed neural networks

  • Jul 05, 2024
  • Scientific Reports
  • M L Mamud +3
  • Preprint Article

An Alternative Large-scale Sea Surface Wind Field Reconstruction Method Using Sparse Scatterometer Data Based on Physics-informed Neutral Network

  • Mar 18, 2025
  • Ran Bo +6
  • Research Article

Research on Numerical Solution Optimization of Partial Differential Equations Based on Physics-Informed Neural Network (PINN)

  • Apr 09, 2026
  • Transactions on Computer Science and Intelligent Systems Research
  • Qixuan Li
  • Research Article
  • Citations16

Physics-guided neural network-based framework for 3D modeling of slope stability

  • Oct 05, 2024
  • Computers and Geotechnics
  • Zilong Zhang +5
  • Research Article
  • Citations47

Deep neural network methods for solving forward and inverse problems of time fractional diffusion equations with conformable derivative

  • Aug 08, 2022
  • Neurocomputing
  • Yinlin Ye +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.