mlsanityData to 7 Oct 2026

Transfer Learning Enhanced Full Waveform Inversion

arXiv 2302.11259 ↗First posted 22 Feb 2023cs.LG physics.comp-ph physics.geo-phcited by 4

Not on the map. Why?

Abstract (arXiv)

We propose a way to favorably employ neural networks in the field of non-destructive testing using Full Waveform Inversion (FWI). The presented methodology discretizes the unknown material distribution in the domain with a neural network within an adjoint optimization. To further increase efficiency of the FWI, pretrained neural networks are used to provide a good starting point for the inversion. This reduces the number of iterations in the Full Waveform Inversion for specific, yet generalizable settings.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 12 of its 41 references that are in the map. First posted on arXiv 22 Feb 2023.

Builds on

12 of 41 references.

References · 12

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  3. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  4. 2017Visualizing the Loss Landscape of Neural Netscited by 1,126
  5. 2017On weight initialization in deep neural networkscited by 67
  6. 2019Deep-learning inversion: a next generation seismic velocity-model building methodcited by 48
  7. 2019Deep-Learning Inversion of Seismic Datacited by 30
  8. 2019Deep Recurrent Architectures for Seismic Tomographycited by 8
  9. 2021Quantitative reconstruction of defects in multi-layered bonded composites using fully convolutional network-based ultrasonic inversioncited by 5
  10. 2023On the Use of Neural Networks for Full Waveform Inversioncited by 5
  11. 2019Petrophysical Property Estimation from Seismic Data Using Recurrent Neural Networkscited by 3
  12. 2022Immersed boundary parametrizations for full waveform inversioncited by 2

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3.

4 papers.

  1. 2023Deep Learning in Deterministic Computational Mechanicscited by 21
  2. 2024Physics-Informed Neural Networks for High-Frequency and Multi-Scale Problems using Transfer Learningcited by 9
  3. 2024Neural Networks for Generating Better Local Optima in Topology Optimizationcited by 3
  4. 2024Accelerating Full Waveform Inversion By Transfer Learningcited by 0