A modified physics-informed neural network with positional encoding
Xinquan Huang, Tariq Alkhalifah, Chao Song
9/1/2021
Keywords: Fundamentals, Science & Engineering, Supervision by Gradient (PDE)
Venue: IMAGE 2021
Bibtex:
@inbook{huang2021a,
author = {Xinquan Huang and Tariq Alkhalifah and Chao Song},
booktitle = {First International Meeting for Applied Geoscience \& Energy},
organization = {Society of Exploration Geophysicists},
pages = {2480--2484},
title = {A modified physics-informed neural network with positional encoding},
year = {2021},
doi = {10.1190/segam2021-3584127.1},
url = {https://library.seg.org/doi/abs/10.1190/segam2021-3584127.1},
entrytype = {inbook},
id = {huang2021a}
}
Abstract
Recently developed physics-informed neural network (PINN) for solving for the scattered wavefield in the Helmholtz equation showed large potential in seismic modeling because of its flexibility, low memory requirement, and no limitations on the shape of the solution space. However, the predicted solutions were somewhat smooth and the convergence of the training was slow. Thus, we propose a modified PINN using sinusoidal activation functions and positional encoding, aiming to accelerate the convergence and fit better. We transform
Citation Graph
(Double click on nodes to open corresponding papers' pages)
(Double click on nodes to open corresponding papers' pages)
* Showing citation graph for papers within our database. Data retrieved from Semantic Scholar. For full citation graphs, visit ConnectedPapers.