The Autoencoder model is based on Lossy Data Compression from Tensorflow's official tutorial: https://www.tensorflow.org/tutorials/generative/data_compression
Training an autoencoder to compress vast Distributed Acoustic Sensing (DAS) data. The goal is to achieve data compression with minimal loss.
Code has been tested in Google Colab on T4, L4, V100, and A100 instances.
- Python (version 3.10.11)
- TensorFlow (version 2.12.0)
- NumPy (version 1.22.4)
- Matplotlib (version 3.7.1)
The data used in this project can potentially be obtained by contacting tculliso-[AT]-stanford-dot-edu
Haipeng Li
Thomas Cullison
Hassan Almomin
Department of Geophysics, Stanford University, 2024