Corpus ID: 209439636

Approaching geoscientific inverse problems with adversarial vector-to-image domain transfer networks

@article{Laloy2019ApproachingGI,
  title={Approaching geoscientific inverse problems with adversarial vector-to-image domain transfer networks},
  author={E. Laloy and N. Linde and D. Jacques},
  journal={arXiv: Geophysics},
  year={2019}
}
We present vec2pix, a deep neural network designed to predict categorical or continuous 2D subsurface property fields from one-dimensional measurement data (e.g., time series), thereby, offering a new way to solve inverse problems. The performance of the method is investigated through two types of synthetic inverse problems: (a) a crosshole ground penetrating radar (GPR) tomography experiment with GPR travel times being used to infer a 2D velocity field, and (2) a multi-well pumping experiment… Expand

References

SHOWING 1-10 OF 35 REFERENCES
Discovering state-parameter mappings in subsurface models using generative adversarial networks
  • A. Sun
  • Computer Science, Physics
  • ArXiv
  • 2018
Parametric generation of conditional geological realizations using generative neural networks
Probabilistic neural network-based 2D travel-time tomography
Reconstruction of three-dimensional porous media using generative adversarial neural networks
Deep-learning inversion: a next generation seismic velocity-model building method
...
1
2
3
4
...