Encoder-Decoder Architecture for 3D Seismic Inversion

TL;DR

This paper introduces a deep learning encoder-decoder model that efficiently reconstructs realistic 3D geological structures from large, noisy seismic datasets, offering a faster alternative to traditional iterative methods.

Contribution

It presents a novel convolutional encoder-decoder architecture capable of processing entire seismic datasets for 3D inversion, reducing computational load compared to standard techniques.

Findings

Achieved SSIM of 0.8554 on noisy seismic data

Successfully processed hundreds of seismic shot-gather cubes

Demonstrated robustness to field noise at 10dB SNR

Abstract

Inverting seismic data to build 3D geological structures is a challenging task due to the overwhelming amount of acquired seismic data, and the very-high computational load due to iterative numerical solutions of the wave equation, as required by industry-standard tools such as Full Waveform Inversion (FWI). For example, in an area with surface dimensions of 4.5km $\times$ 4.5km, hundreds of seismic shot-gather cubes are required for 3D model reconstruction, leading to Terabytes of recorded data. This paper presents a deep learning solution for the reconstruction of realistic 3D models in the presence of field noise recorded in seismic surveys. We implement and analyze a convolutional encoder-decoder architecture that efficiently processes the entire collection of hundreds of seismic shot-gather cubes. The proposed solution demonstrates that realistic 3D models can be reconstructed with a structural similarity index measure (SSIM) of 0.8554 (out of 1.0) in the presence of field noise at 10dB signal-to-noise ratio.