This study explores wavefield reconstruction using machine learning methods for data compression and wavefield separation. We test various architectures to treat DAS data as two-dimensional arrays, such as the Implicit Neural Representation
(INR) models and the SHallow REcurrent Decoder
(SHRED) model.
All codes are implemented in PyTorch.
- SHallow REcurrent Decoder (SHRED, Williams et al., 2023): notebooks/SHRED_KKFLS_training.ipynb
- Random Fourier Feature Network (RFFN, Tancik et al., 2020): notebooks/RFFN_KKFLS_training.ipynb
- Sinusoidal Representation Network (SIREN, Sitzmann et al., 2020): notebooks/SIREN_KKFLS_training.ipynb
The earthquake data from the Cook Inlet DAS experiment are available at https://dasway.ess.washington.edu/gci/index.html. Events are updated daily.
Due to the huge size of the data used in this study, we cannot upload it directly in this repository. However, we prepared a Python script to download these data from our archival server. Please refer to download.py in this directory.
Comments and sugguestions are welcomed. Please report all issues under this repository.