PINNslope: physics informed neural network slope prediction and interpolation with positional encoding

Francesco Brandolin, Matteo Ravasi, Tariq Alkhalifah

Research output: Contribution to conferencePaperpeer-review

Abstract

Under the assumption that seismic wavefields can be represented as superposition of local plane waves, we propose to interpolate seismic data utilizing a physics informed neural network (PINN) assisted by the local slope attribute. The implementation comprises two fully-connected neural networks trained using the local plane wave differential equation as well as the available data as two terms in the objective function. The main network assisted by positional encoding reconstructs the seismic data, while the smaller one predicts the local slope field that simultaneously satisfies the differential equation. In the proposed work, four different encoding functions (Linear Fourier Features, modified Linear Fourier Features, Random Fourier Features, Gaussian Encoding) are compared to evaluate which one will benefits our framework the most in terms of reconstruction accuracy and convergence speed. We find that our proposed modified Linear Fourier Feature helps our framework in achieving a faster and less oscillatory convergence while accurately reconstructing the data.

Original languageEnglish (US)
Pages1520-1524
Number of pages5
DOIs
StatePublished - Dec 14 2023
Event3rd International Meeting for Applied Geoscience and Energy, IMAGE 2023 - Houston, United States
Duration: Aug 28 2023Sep 1 2023

Conference

Conference3rd International Meeting for Applied Geoscience and Energy, IMAGE 2023
Country/TerritoryUnited States
CityHouston
Period08/28/2309/1/23

ASJC Scopus subject areas

  • Geotechnical Engineering and Engineering Geology
  • Geophysics

Fingerprint

Dive into the research topics of 'PINNslope: physics informed neural network slope prediction and interpolation with positional encoding'. Together they form a unique fingerprint.

Cite this