3-D Poststack Seismic Data Compression With a Deep Autoencoder

  • Ana Paula Schiavon UFJF
  • Kevyn Ribeiro UFJF
  • João Paulo Navarro NVIDIA
  • Marcelo Vieira UFJF
  • Pedro Mário Cruz e Silva NVIDIA


We approach the problem of 3-D poststack seismic data compression by training a model based on a deep autoencoder. Our network architecture is trained to consider the similarity between 3-D seismic sections drawn from one or multiple seismic volumes. A whole seismic volume is compressed with the latent representations of each of its composing volumetric sections. The goal is to compress the seismic data at very low bit rates with high-quality reconstruction. Our model is suitable for training general compressors from multiple seismic surveys or for specialized compression of a single seismic volume. Results show that our method can compress seismic data with extremely low bit rates, below 0.3 bits-per-voxel (bpv) while yielding peak signal-to-noise ratio (PSNR) values over 40 dB.
Palavras-chave: 3-D poststack data, autoencoder, deep learning, seismic data compression.
Como Citar

Selecione um Formato
SCHIAVON, Ana Paula; RIBEIRO, Kevyn; NAVARRO, João Paulo; VIEIRA, Marcelo; CRUZ E SILVA, Pedro Mário. 3-D Poststack Seismic Data Compression With a Deep Autoencoder. In: CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 33. , 2020, Evento Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2020 . p. 469-473.